# dataset_id image_id annotator_id caption timed_caption traces voice_recording_path audio_bytes
1
ADE20k
ADE_train_00001084
67
At the bottom of the image there is a road. Behind the road there is railing. Behind the railing there is a car on the road. And also there is a pole with a board. In the background there is a building with text and logos on it. At the top of the image there is sky.
[
{
"utterance": "At",
"start_time": 0.0,
"end_time": 0.0
},
{
"utterance": "the",
"start_time": 0.0,
"end_time": 0.4000000059604645
},
{
"utterance": "bottom",
"start_time": 0.4000000059604645,
"end_time": 0.699999988079071
},
{
"utterance": "of",
"start_time": 0.699999988079071,
"end_time": 0.800000011920929
},
{
"utterance": "the image there",
"start_time": 0.800000011920929,
"end_time": 1.0
},
{
"utterance": "is",
"start_time": 1.0,
"end_time": 1.100000023841858
},
{
"utterance": "a",
"start_time": 1.100000023841858,
"end_time": 1.2000000476837158
},
{
"utterance": "road.",
"start_time": 1.2000000476837158,
"end_time": 1.600000023841858
},
{
"utterance": "Behind",
"start_time": 1.600000023841858,
"end_time": 1.7000000476837158
},
{
"utterance": "the road",
"start_time": 1.7000000476837158,
"end_time": 1.7000000476837158
},
{
"utterance": "there",
"start_time": 1.7000000476837158,
"end_time": 2.4000000953674316
},
{
"utterance": "is",
"start_time": 2.4000000953674316,
"end_time": 2.5999999046325684
},
{
"utterance": "railing.",
"start_time": 2.5999999046325684,
"end_time": 2.9000000953674316
},
{
"utterance": "Behind",
"start_time": 2.9000000953674316,
"end_time": 3.200000047683716
},
{
"utterance": "the",
"start_time": 3.200000047683716,
"end_time": 3.200000047683716
},
{
"utterance": "railing",
"start_time": 3.200000047683716,
"end_time": 3.799999952316284
},
{
"utterance": "there",
"start_time": 3.799999952316284,
"end_time": 3.9000000953674316
},
{
"utterance": "is",
"start_time": 3.9000000953674316,
"end_time": 4.099999904632568
},
{
"utterance": "a",
"start_time": 4.099999904632568,
"end_time": 4.099999904632568
},
{
"utterance": "car",
"start_time": 4.099999904632568,
"end_time": 4.300000190734863
},
{
"utterance": "on",
"start_time": 4.300000190734863,
"end_time": 4.599999904632568
},
{
"utterance": "the",
"start_time": 4.599999904632568,
"end_time": 4.699999809265137
},
{
"utterance": "road. And also",
"start_time": 4.699999809265137,
"end_time": 4.800000190734863
},
{
"utterance": "there",
"start_time": 4.800000190734863,
"end_time": 5.699999809265137
},
{
"utterance": "is",
"start_time": 5.699999809265137,
"end_time": 5.699999809265137
},
{
"utterance": "a",
"start_time": 5.699999809265137,
"end_time": 5.800000190734863
},
{
"utterance": "pole",
"start_time": 5.800000190734863,
"end_time": 6.5
},
{
"utterance": "with",
"start_time": 6.5,
"end_time": 6.699999809265137
},
{
"utterance": "a",
"start_time": 6.699999809265137,
"end_time": 6.800000190734863
},
{
"utterance": "board.",
"start_time": 6.800000190734863,
"end_time": 7.199999809265137
},
{
"utterance": "In",
"start_time": 7.199999809265137,
"end_time": 7.800000190734863
},
{
"utterance": "the",
"start_time": 7.800000190734863,
"end_time": 7.900000095367432
},
{
"utterance": "background",
"start_time": 7.900000095367432,
"end_time": 8.300000190734863
},
{
"utterance": "there",
"start_time": 8.300000190734863,
"end_time": 8.699999809265137
},
{
"utterance": "is",
"start_time": 8.699999809265137,
"end_time": 8.800000190734863
},
{
"utterance": "a",
"start_time": 8.800000190734863,
"end_time": 8.899999618530273
},
{
"utterance": "building",
"start_time": 8.899999618530273,
"end_time": 9.199999809265137
},
{
"utterance": "with",
"start_time": 9.199999809265137,
"end_time": 10.100000381469727
},
{
"utterance": "text",
"start_time": 10.100000381469727,
"
[
[
{
"x": 0.18170000612735748,
"y": 0.5163999795913696,
"t": 0.012000000104308128
},
{
"x": 0.20090000331401825,
"y": 0.5776000022888184,
"t": 0.026000000536441803
},
{
"x": 0.21690000593662262,
"y": 0.6245999932289124,
"t": 0.041999999433755875
},
{
"x": 0.23510000109672546,
"y": 0.6744999885559082,
"t": 0.05900000035762787
},
{
"x": 0.27889999747276306,
"y": 0.7513999938964844,
"t": 0.07599999755620956
},
{
"x": 0.30660000443458557,
"y": 0.7883999943733215,
"t": 0.09300000220537186
},
{
"x": 0.3269999921321869,
"y": 0.8054999709129333,
"t": 0.10999999940395355
},
{
"x": 0.33340001106262207,
"y": 0.8112000226974487,
"t": 0.12600000202655792
},
{
"x": 0.3375999927520752,
"y": 0.815500020980835,
"t": 0.1770000010728836
},
{
"x": 0.34619998931884766,
"y": 0.8339999914169312,
"t": 0.1940000057220459
},
{
"x": 0.362199991941452,
"y": 0.862500011920929,
"t": 0.210999995470047
},
{
"x": 0.37610000371932983,
"y": 0.8881000280380249,
"t": 0.2280000001192093
},
{
"x": 0.3910999894142151,
"y": 0.9052000045776367,
"t": 0.24400000274181366
},
{
"x": 0.40389999747276306,
"y": 0.9108999967575073,
"t": 0.25999999046325684
},
{
"x": 0.4124000072479248,
"y": 0.9138000011444092,
"t": 0.2759999930858612
},
{
"x": 0.4156000018119812,
"y": 0.9165999889373779,
"t": 0.2930000126361847
},
{
"x": 0.42739999294281006,
"y": 0.9279999732971191,
"t": 0.3089999854564667
},
{
"x": 0.45190000534057617,
"y": 0.9508000016212463,
"t": 0.32600000500679016
},
{
"x": 0.47859999537467957,
"y": 0.9721999764442444,
"t": 0.34299999475479126
},
{
"x": 0.5084999799728394,
"y": 0.9878000020980835,
"t": 0.35899999737739563
},
{
"x": 0.536300003528595,
"y": 0.9921000003814697,
"t": 0.37700000405311584
},
{
"x": 0.5565999746322632,
"y": 0.9934999942779541,
"t": 0.39399999380111694
},
{
"x": 0.5737000107765198,
"y": 0.9934999942779541,
"t": 0.41100001335144043
},
{
"x": 0.5855000019073486,
"y": 0.9878000020980835,
"t": 0.4269999861717224
},
{
"x": 0.5971999764442444,
"y": 0.9793000221252441,
"t": 0.4440000057220459
},
{
"x": 0.6057999730110168,
"y": 0.97079998254776,
"t": 0.460999995470047
},
{
"x": 0.6111000180244446,
"y": 0.9564999938011169,
"t": 0.47699999809265137
},
{
"x": 0.6111000180244446,
"y": 0.942300021648407,
"t": 0.49300000071525574
},
{
"x": 0.6047000288963318,
"y": 0.9265999794006348,
"t": 0.5099999904632568
},
{
"x": 0.588699996471405,
"y": 0.909500002861023,
"t": 0.5270000100135803
},
{
"x": 0.5662000179290771,
"y": 0.8995000123977661,
"t": 0.5440000295639038
},
{
"x": 0.5278000235557556,
"y": 0.883899986743927,
"t": 0.5600000023841858
},
{
"x": 0.48190000653266907,
"y": 0.8752999901771545,
"t": 0.5770000219345093
},
{
"x": 0.4284000098705292,
"y": 0.8652999997138977,
"t": 0.5929999947547913
},
{
"x": 0.3781999945640564,
"y": 0.8582000136375427,
"t": 0.6100000143051147
},
{
"x": 0.33550000190734863,
"y": 0.8539000153541565,
"t": 0.6269999742507935
},
{
"x": 0.30880001187324524,
"y": 0.8539000153541565,
"t": 0.6430000066757202
},
{
"x": 0.296999990940094,
"y": 0.8597000241279602,
"t": 0.6600
ade20k_train/ade20k_train_0000000000001084_67.ogg
2
ADE20k
ADE_train_00019182
125
In this image I can see the auditorium.
[
{
"utterance": "In",
"start_time": 0.0,
"end_time": 0.4000000059604645
},
{
"utterance": "this",
"start_time": 0.4000000059604645,
"end_time": 0.5
},
{
"utterance": "image",
"start_time": 0.5,
"end_time": 1.100000023841858
},
{
"utterance": "I",
"start_time": 1.100000023841858,
"end_time": 1.2000000476837158
},
{
"utterance": "can",
"start_time": 1.2000000476837158,
"end_time": 1.5
},
{
"utterance": "see",
"start_time": 1.5,
"end_time": 1.7999999523162842
},
{
"utterance": "the",
"start_time": 1.7999999523162842,
"end_time": 5.599999904632568
},
{
"utterance": "auditorium.",
"start_time": 5.599999904632568,
"end_time": 6.099999904632568
}
]
[
[
{
"x": 0.48080000281333923,
"y": 0.08699999749660492,
"t": 0.02500000037252903
},
{
"x": 0.47350001335144043,
"y": 0.17110000550746918,
"t": 0.04100000113248825
},
{
"x": 0.45890000462532043,
"y": 0.321399986743927,
"t": 0.07500000298023224
},
{
"x": 0.4625000059604645,
"y": 0.39309999346733093,
"t": 0.10899999737739563
},
{
"x": 0.48899999260902405,
"y": 0.445499986410141,
"t": 0.1420000046491623
},
{
"x": 0.5612999796867371,
"y": 0.4772999882698059,
"t": 0.17499999701976776
},
{
"x": 0.614300012588501,
"y": 0.47999998927116394,
"t": 0.19099999964237213
},
{
"x": 0.7257999777793884,
"y": 0.4675999879837036,
"t": 0.22499999403953552
},
{
"x": 0.7742999792098999,
"y": 0.44690001010894775,
"t": 0.24199999868869781
},
{
"x": 0.8355000019073486,
"y": 0.39309999346733093,
"t": 0.2750000059604645
},
{
"x": 0.8400999903678894,
"y": 0.3668999969959259,
"t": 0.29100000858306885
},
{
"x": 0.8273000121116638,
"y": 0.33239999413490295,
"t": 0.30799999833106995
},
{
"x": 0.7861999869346619,
"y": 0.2856000065803528,
"t": 0.32499998807907104
},
{
"x": 0.6672999858856201,
"y": 0.2110999971628189,
"t": 0.3409999907016754
},
{
"x": 0.5785999894142151,
"y": 0.17659999430179596,
"t": 0.35600000619888306
},
{
"x": 0.5045999884605408,
"y": 0.1696999967098236,
"t": 0.37299999594688416
},
{
"x": 0.45339998602867126,
"y": 0.1696999967098236,
"t": 0.38999998569488525
},
{
"x": 0.413100004196167,
"y": 0.1876000016927719,
"t": 0.4090000092983246
},
{
"x": 0.3774999976158142,
"y": 0.2110999971628189,
"t": 0.42500001192092896
},
{
"x": 0.34549999237060547,
"y": 0.24690000712871552,
"t": 0.4410000145435333
},
{
"x": 0.3271999955177307,
"y": 0.28690001368522644,
"t": 0.4560000002384186
},
{
"x": 0.3199000060558319,
"y": 0.32829999923706055,
"t": 0.4729999899864197
},
{
"x": 0.31529998779296875,
"y": 0.3752000033855438,
"t": 0.49000000953674316
},
{
"x": 0.31529998779296875,
"y": 0.4138000011444092,
"t": 0.5070000290870667
},
{
"x": 0.31709998846054077,
"y": 0.4772999882698059,
"t": 0.5249999761581421
},
{
"x": 0.33090001344680786,
"y": 0.5228000283241272,
"t": 0.5410000085830688
},
{
"x": 0.35920000076293945,
"y": 0.565500020980835,
"t": 0.5590000152587891
},
{
"x": 0.4066999852657318,
"y": 0.6014000177383423,
"t": 0.574999988079071
},
{
"x": 0.4697999954223633,
"y": 0.621999979019165,
"t": 0.5910000205039978
},
{
"x": 0.5465999841690063,
"y": 0.6288999915122986,
"t": 0.6079999804496765
},
{
"x": 0.6306999921798706,
"y": 0.6233999729156494,
"t": 0.625
},
{
"x": 0.7734000086784363,
"y": 0.54339998960495,
"t": 0.6579999923706055
},
{
"x": 0.805400013923645,
"y": 0.5034000277519226,
"t": 0.675000011920929
},
{
"x": 0.8126999735832214,
"y": 0.4634000062942505,
"t": 0.6909999847412109
},
{
"x": 0.8108999729156494,
"y": 0.41929998993873596,
"t": 0.7089999914169312
},
{
"x": 0.7742999792098999,
"y": 0.3476000130176544,
"t": 0.7250000238418579
},
{
"x": 0.7404999732971191,
"y": 0.30489999055862427,
"t": 0.7419999837875366
},
{
"x": 0.6847000122070312,
"y": 0.26350000500679016,
"t": 0.75900000333
ade20k_train/ade20k_train_0000000000019182_125.ogg
3
ADE20k
ADE_train_00018710
163
In this picture I can see there is a road, there are few vehicles parked and few people crossing the road, there are buildings on the left and on the right side and there is a pole on the left and I can see the sky and this is a blurred image.
[
{
"utterance": "In this",
"start_time": 0.0,
"end_time": 0.6000000238418579
},
{
"utterance": "picture",
"start_time": 0.6000000238418579,
"end_time": 1.2000000476837158
},
{
"utterance": "I",
"start_time": 1.2000000476837158,
"end_time": 2.200000047683716
},
{
"utterance": "can",
"start_time": 2.200000047683716,
"end_time": 2.4000000953674316
},
{
"utterance": "see",
"start_time": 2.4000000953674316,
"end_time": 2.700000047683716
},
{
"utterance": "there",
"start_time": 2.700000047683716,
"end_time": 2.700000047683716
},
{
"utterance": "is",
"start_time": 2.700000047683716,
"end_time": 3.0
},
{
"utterance": "a",
"start_time": 3.0,
"end_time": 3.200000047683716
},
{
"utterance": "road,",
"start_time": 3.200000047683716,
"end_time": 3.5999999046325684
},
{
"utterance": "there are few",
"start_time": 3.5999999046325684,
"end_time": 3.799999952316284
},
{
"utterance": "vehicles",
"start_time": 3.799999952316284,
"end_time": 4.300000190734863
},
{
"utterance": "parked",
"start_time": 4.300000190734863,
"end_time": 4.800000190734863
},
{
"utterance": "and",
"start_time": 4.800000190734863,
"end_time": 5.300000190734863
},
{
"utterance": "few",
"start_time": 5.300000190734863,
"end_time": 5.5
},
{
"utterance": "people",
"start_time": 5.5,
"end_time": 5.800000190734863
},
{
"utterance": "crossing",
"start_time": 5.800000190734863,
"end_time": 6.199999809265137
},
{
"utterance": "the",
"start_time": 6.199999809265137,
"end_time": 6.400000095367432
},
{
"utterance": "road,",
"start_time": 6.400000095367432,
"end_time": 6.599999904632568
},
{
"utterance": "there are",
"start_time": 6.599999904632568,
"end_time": 7.199999809265137
},
{
"utterance": "buildings",
"start_time": 7.199999809265137,
"end_time": 7.599999904632568
},
{
"utterance": "on",
"start_time": 7.599999904632568,
"end_time": 7.800000190734863
},
{
"utterance": "the",
"start_time": 7.800000190734863,
"end_time": 7.900000095367432
},
{
"utterance": "left",
"start_time": 7.900000095367432,
"end_time": 8.100000381469727
},
{
"utterance": "and",
"start_time": 8.100000381469727,
"end_time": 8.300000190734863
},
{
"utterance": "on the",
"start_time": 8.300000190734863,
"end_time": 8.300000190734863
},
{
"utterance": "right",
"start_time": 8.300000190734863,
"end_time": 8.600000381469727
},
{
"utterance": "side",
"start_time": 8.600000381469727,
"end_time": 9.300000190734863
},
{
"utterance": "and",
"start_time": 9.300000190734863,
"end_time": 9.699999809265137
},
{
"utterance": "there is a",
"start_time": 9.699999809265137,
"end_time": 9.800000190734863
},
{
"utterance": "pole",
"start_time": 9.800000190734863,
"end_time": 10.699999809265137
},
{
"utterance": "on",
"start_time": 10.699999809265137,
"end_time": 10.899999618530273
},
{
"utterance": "the",
"start_time": 10.899999618530273,
"end_time": 10.899999618530273
},
{
"utterance": "left",
"start_time": 10.899999618530273,
"end_time": 11.300000190734863
},
{
"utterance": "and",
"start_time": 11.300000190734863,
"end_time": 11.5
},
{
"utterance": "I",
"start_time": 11.5,
"end_time": 11.600000381469727
},
{
"utterance": "can",
"start_time": 11.600000381469727,
"end_time": 11.699999809265137
},
{
"utterance": "see",
"start_time": 11.699999809265137,
"end_time": 11.899999618530273
},
{
"utterance": "the",
"start_time": 11.899999618530273,
"end_time": 12.0
},
{
"utterance": "sky",
"start_time": 12.0,
"end_time": 12.399
[
[
{
"x": 0.6761999726295471,
"y": 0.4837000072002411,
"t": 0.013000000268220901
},
{
"x": 0.6743999719619751,
"y": 0.5108000040054321,
"t": 0.02800000086426735
},
{
"x": 0.6743999719619751,
"y": 0.546999990940094,
"t": 0.04399999976158142
},
{
"x": 0.6743999719619751,
"y": 0.5831000208854675,
"t": 0.06199999898672104
},
{
"x": 0.6743999719619751,
"y": 0.6047999858856201,
"t": 0.07800000160932541
},
{
"x": 0.6743999719619751,
"y": 0.6119999885559082,
"t": 0.09399999678134918
},
{
"x": 0.6743999719619751,
"y": 0.6065999865531921,
"t": 0.14499999582767487
},
{
"x": 0.6923999786376953,
"y": 0.5903000235557556,
"t": 0.16099999845027924
},
{
"x": 0.7141000032424927,
"y": 0.5651000142097473,
"t": 0.1770000010728836
},
{
"x": 0.7159000039100647,
"y": 0.5415999889373779,
"t": 0.19499999284744263
},
{
"x": 0.7141000032424927,
"y": 0.5325000286102295,
"t": 0.210999995470047
},
{
"x": 0.6725000143051147,
"y": 0.5289000272750854,
"t": 0.2280000001192093
},
{
"x": 0.6183000206947327,
"y": 0.5289000272750854,
"t": 0.24400000274181366
},
{
"x": 0.5785999894142151,
"y": 0.5396999716758728,
"t": 0.25999999046325684
},
{
"x": 0.5623000264167786,
"y": 0.5741000175476074,
"t": 0.27799999713897705
},
{
"x": 0.5623000264167786,
"y": 0.6771000027656555,
"t": 0.29499998688697815
},
{
"x": 0.5569000244140625,
"y": 0.7674000263214111,
"t": 0.3109999895095825
},
{
"x": 0.5569000244140625,
"y": 0.8378999829292297,
"t": 0.328000009059906
},
{
"x": 0.5641000270843506,
"y": 0.8722000122070312,
"t": 0.3449999988079071
},
{
"x": 0.567799985408783,
"y": 0.8740000128746033,
"t": 0.3610000014305115
},
{
"x": 0.5767999887466431,
"y": 0.8632000088691711,
"t": 0.39399999380111694
},
{
"x": 0.5875999927520752,
"y": 0.8378999829292297,
"t": 0.41100001335144043
},
{
"x": 0.6003000140190125,
"y": 0.805400013923645,
"t": 0.42800000309944153
},
{
"x": 0.6075000166893005,
"y": 0.7818999886512756,
"t": 0.4449999928474426
},
{
"x": 0.6075000166893005,
"y": 0.7674000263214111,
"t": 0.4620000123977661
},
{
"x": 0.5949000120162964,
"y": 0.754800021648407,
"t": 0.47699999809265137
},
{
"x": 0.5605000257492065,
"y": 0.756600022315979,
"t": 0.4950000047683716
},
{
"x": 0.5315999984741211,
"y": 0.8126000165939331,
"t": 0.5109999775886536
},
{
"x": 0.4936999976634979,
"y": 0.9138000011444092,
"t": 0.527999997138977
},
{
"x": 0.4666000008583069,
"y": 1.0149999856948853,
"t": 0.5450000166893005
},
{
"x": 0.46299999952316284,
"y": 1.0547000169754028,
"t": 0.5609999895095825
},
{
"x": 0.46299999952316284,
"y": 1.05649995803833,
"t": 0.578000009059906
},
{
"x": 0.4684000015258789,
"y": 1.052899956703186,
"t": 0.5950000286102295
},
{
"x": 0.4918999969959259,
"y": 1.0257999897003174,
"t": 0.6110000014305115
},
{
"x": 0.524399995803833,
"y": 0.9787999987602234,
"t": 0.628000020980835
},
{
"x": 0.5533000230789185,
"y": 0.9264000058174133,
"t": 0.6449999809265137
},
{
"x": 0.571399986743927,
"y": 0.8866999745368958,
"t": 0.6610000133514404
},
{
"x": 0.5821999907493591,
"y": 0.8486999869346619,
"t": 0.6779999732971191
},
ade20k_train/ade20k_train_0000000000018710_163.ogg
4
ADE20k
ADE_train_00008479
0
In this picture we can see a partial part of a car on the ground. In the background we can see containers and a bag in the racks. At the top of the image we can see the ceiling. On the right side of the picture through the window glass we can see trees. We can see cupboards and drawers on the wall. We can see holders with some objects. We can see tools, bags, bats, a skating board and sticks on the wall. We can see the reflections on the ground.
[
{
"utterance": "In",
"start_time": 0.0,
"end_time": 0.20000000298023224
},
{
"utterance": "this",
"start_time": 0.20000000298023224,
"end_time": 0.4000000059604645
},
{
"utterance": "picture",
"start_time": 0.4000000059604645,
"end_time": 0.699999988079071
},
{
"utterance": "we",
"start_time": 0.699999988079071,
"end_time": 0.8999999761581421
},
{
"utterance": "can",
"start_time": 0.8999999761581421,
"end_time": 1.100000023841858
},
{
"utterance": "see",
"start_time": 1.100000023841858,
"end_time": 1.5
},
{
"utterance": "a",
"start_time": 1.5,
"end_time": 1.5
},
{
"utterance": "partial",
"start_time": 1.5,
"end_time": 2.4000000953674316
},
{
"utterance": "part",
"start_time": 2.4000000953674316,
"end_time": 2.700000047683716
},
{
"utterance": "of",
"start_time": 2.700000047683716,
"end_time": 2.799999952316284
},
{
"utterance": "a",
"start_time": 2.799999952316284,
"end_time": 2.9000000953674316
},
{
"utterance": "car",
"start_time": 2.9000000953674316,
"end_time": 3.200000047683716
},
{
"utterance": "on",
"start_time": 3.200000047683716,
"end_time": 3.9000000953674316
},
{
"utterance": "the",
"start_time": 3.9000000953674316,
"end_time": 4.0
},
{
"utterance": "ground.",
"start_time": 4.0,
"end_time": 5.699999809265137
},
{
"utterance": "In",
"start_time": 5.699999809265137,
"end_time": 6.900000095367432
},
{
"utterance": "the",
"start_time": 6.900000095367432,
"end_time": 6.900000095367432
},
{
"utterance": "background",
"start_time": 6.900000095367432,
"end_time": 7.400000095367432
},
{
"utterance": "we can see",
"start_time": 7.400000095367432,
"end_time": 8.199999809265137
},
{
"utterance": "containers",
"start_time": 8.199999809265137,
"end_time": 9.600000381469727
},
{
"utterance": "and",
"start_time": 9.600000381469727,
"end_time": 10.5
},
{
"utterance": "a",
"start_time": 10.5,
"end_time": 10.600000381469727
},
{
"utterance": "bag",
"start_time": 10.600000381469727,
"end_time": 11.0
},
{
"utterance": "in",
"start_time": 11.0,
"end_time": 11.199999809265137
},
{
"utterance": "the",
"start_time": 11.199999809265137,
"end_time": 11.300000190734863
},
{
"utterance": "racks. At the",
"start_time": 11.300000190734863,
"end_time": 11.300000190734863
},
{
"utterance": "top",
"start_time": 11.300000190734863,
"end_time": 13.0
},
{
"utterance": "of",
"start_time": 13.0,
"end_time": 13.100000381469727
},
{
"utterance": "the",
"start_time": 13.100000381469727,
"end_time": 13.199999809265137
},
{
"utterance": "image",
"start_time": 13.199999809265137,
"end_time": 13.5
},
{
"utterance": "we",
"start_time": 13.5,
"end_time": 13.600000381469727
},
{
"utterance": "can",
"start_time": 13.600000381469727,
"end_time": 13.800000190734863
},
{
"utterance": "see",
"start_time": 13.800000190734863,
"end_time": 14.0
},
{
"utterance": "the",
"start_time": 14.0,
"end_time": 14.100000381469727
},
{
"utterance": "ceiling.",
"start_time": 14.100000381469727,
"end_time": 14.600000381469727
},
{
"utterance": "On",
"start_time": 14.600000381469727,
"end_time": 14.699999809265137
},
{
"utterance": "the",
"start_time": 14.699999809265137,
"end_time": 14.800000190734863
},
{
"utterance": "right",
"start_time": 14.800000190734863,
"end_time": 15.100000381469727
},
{
"utterance": "side",
"start_time": 15.100000381469727,
"end_time": 15.199999809265137
},
{
"utterance": "of",
"start_time": 15.199999809265137,
"end_time": 15.30000
[
[
{
"x": 0.3003999888896942,
"y": 0.7929999828338623,
"t": 0.026000000536441803
},
{
"x": 0.39730000495910645,
"y": 0.9488999843597412,
"t": 0.05700000002980232
},
{
"x": 0.45399999618530273,
"y": 1.0008000135421753,
"t": 0.07400000095367432
},
{
"x": 0.5236999988555908,
"y": 1.0355000495910645,
"t": 0.09099999815225601
},
{
"x": 0.5814999938011169,
"y": 1.044100046157837,
"t": 0.10700000077486038
},
{
"x": 0.6446999907493591,
"y": 1.044100046157837,
"t": 0.12399999797344208
},
{
"x": 0.7056999802589417,
"y": 1.044100046157837,
"t": 0.14100000262260437
},
{
"x": 0.7526000142097473,
"y": 1.044100046157837,
"t": 0.15800000727176666
},
{
"x": 0.7842000126838684,
"y": 1.044100046157837,
"t": 0.17399999499320984
},
{
"x": 0.8113999962806702,
"y": 1.0355000495910645,
"t": 0.1899999976158142
},
{
"x": 0.8288000226020813,
"y": 1.0181000232696533,
"t": 0.2070000022649765
},
{
"x": 0.838699996471405,
"y": 0.9973999857902527,
"t": 0.2240000069141388
},
{
"x": 0.8474000096321106,
"y": 0.9731000065803528,
"t": 0.2409999966621399
},
{
"x": 0.8517000079154968,
"y": 0.9453999996185303,
"t": 0.25699999928474426
},
{
"x": 0.8550000190734863,
"y": 0.9038000106811523,
"t": 0.27399998903274536
},
{
"x": 0.8561000227928162,
"y": 0.8500999808311462,
"t": 0.29100000858306885
},
{
"x": 0.8561000227928162,
"y": 0.7894999980926514,
"t": 0.3070000112056732
},
{
"x": 0.8517000079154968,
"y": 0.737500011920929,
"t": 0.3240000009536743
},
{
"x": 0.8429999947547913,
"y": 0.6924999952316284,
"t": 0.3409999907016754
},
{
"x": 0.8234000205993652,
"y": 0.6335999965667725,
"t": 0.3580000102519989
},
{
"x": 0.7972999811172485,
"y": 0.5746999979019165,
"t": 0.37400001287460327
},
{
"x": 0.7656999826431274,
"y": 0.5332000255584717,
"t": 0.39100000262260437
},
{
"x": 0.7515000104904175,
"y": 0.5245000123977661,
"t": 0.40700000524520874
},
{
"x": 0.7439000010490417,
"y": 0.5245000123977661,
"t": 0.42399999499320984
},
{
"x": 0.7383999824523926,
"y": 0.5245000123977661,
"t": 0.4410000145435333
},
{
"x": 0.7318999767303467,
"y": 0.527999997138977,
"t": 0.4580000042915344
},
{
"x": 0.7231000065803528,
"y": 0.5400999784469604,
"t": 0.4740000069141388
},
{
"x": 0.7045999765396118,
"y": 0.5695000290870667,
"t": 0.4909999966621399
},
{
"x": 0.6827999949455261,
"y": 0.6111000180244446,
"t": 0.5080000162124634
},
{
"x": 0.6589000225067139,
"y": 0.6682999730110168,
"t": 0.5239999890327454
},
{
"x": 0.6381999850273132,
"y": 0.7253999710083008,
"t": 0.5429999828338623
},
{
"x": 0.6283000111579895,
"y": 0.7860000133514404,
"t": 0.5580000281333923
},
{
"x": 0.6273000240325928,
"y": 0.8500999808311462,
"t": 0.5740000009536743
},
{
"x": 0.6491000056266785,
"y": 0.9574999809265137,
"t": 0.5899999737739563
},
{
"x": 0.6773999929428101,
"y": 1.0198999643325806,
"t": 0.6069999933242798
},
{
"x": 0.722100019454956,
"y": 1.0770000219345093,
"t": 0.6240000128746033
}
],
[
{
"x": 1.0085999965667725,
"y": 0.8467000126838684,
"t": 0.7919999957084656
},
{
"x": 0.993399977684021,
"y": 0.7791000008583069,
"t": 0.80800002813
ade20k_train/ade20k_train_0000000000008479_0.ogg
5
ADE20k
ADE_train_00006847
25
In the picture I can see chairs, a table, a mat on the floor, windows, a chandelier attached to the ceiling and some other objects. In the background I can see trees and plants. This is an inside view of a room.
[
{
"utterance": "In",
"start_time": 0.10000000149011612,
"end_time": 0.10000000149011612
},
{
"utterance": "the",
"start_time": 0.10000000149011612,
"end_time": 0.6000000238418579
},
{
"utterance": "picture",
"start_time": 0.6000000238418579,
"end_time": 0.800000011920929
},
{
"utterance": "I",
"start_time": 0.800000011920929,
"end_time": 0.8999999761581421
},
{
"utterance": "can",
"start_time": 0.8999999761581421,
"end_time": 1.2000000476837158
},
{
"utterance": "see",
"start_time": 1.2000000476837158,
"end_time": 1.2999999523162842
},
{
"utterance": "chairs, a",
"start_time": 1.2999999523162842,
"end_time": 1.2999999523162842
},
{
"utterance": "table,",
"start_time": 1.2999999523162842,
"end_time": 4.0
},
{
"utterance": "a",
"start_time": 4.0,
"end_time": 5.0
},
{
"utterance": "mat",
"start_time": 5.0,
"end_time": 7.0
},
{
"utterance": "on",
"start_time": 7.0,
"end_time": 7.300000190734863
},
{
"utterance": "the",
"start_time": 8.899999618530273,
"end_time": 9.699999809265137
},
{
"utterance": "floor,",
"start_time": 9.699999809265137,
"end_time": 11.0
},
{
"utterance": "windows,",
"start_time": 11.0,
"end_time": 12.800000190734863
},
{
"utterance": "a",
"start_time": 12.800000190734863,
"end_time": 14.199999809265137
},
{
"utterance": "chandelier",
"start_time": 14.199999809265137,
"end_time": 14.399999618530273
},
{
"utterance": "attached to",
"start_time": 14.399999618530273,
"end_time": 14.399999618530273
},
{
"utterance": "the",
"start_time": 14.399999618530273,
"end_time": 14.899999618530273
},
{
"utterance": "ceiling",
"start_time": 14.899999618530273,
"end_time": 15.199999809265137
},
{
"utterance": "and",
"start_time": 15.199999809265137,
"end_time": 16.0
},
{
"utterance": "some",
"start_time": 16.0,
"end_time": 16.0
},
{
"utterance": "other objects.",
"start_time": 16.0,
"end_time": 16.700000762939453
},
{
"utterance": "In",
"start_time": 16.700000762939453,
"end_time": 17.0
},
{
"utterance": "the",
"start_time": 17.0,
"end_time": 17.100000381469727
},
{
"utterance": "background",
"start_time": 17.100000381469727,
"end_time": 17.399999618530273
},
{
"utterance": "I can see trees and",
"start_time": 17.399999618530273,
"end_time": 18.200000762939453
},
{
"utterance": "plants. This is an",
"start_time": 18.200000762939453,
"end_time": 19.100000381469727
},
{
"utterance": "inside",
"start_time": 19.100000381469727,
"end_time": 20.700000762939453
},
{
"utterance": "view",
"start_time": 20.700000762939453,
"end_time": 21.0
},
{
"utterance": "of",
"start_time": 21.0,
"end_time": 21.100000381469727
},
{
"utterance": "a",
"start_time": 21.100000381469727,
"end_time": 21.100000381469727
},
{
"utterance": "room.",
"start_time": 21.100000381469727,
"end_time": 21.600000381469727
}
]
[
[
{
"x": 0.8009999990463257,
"y": 0.4381999969482422,
"t": 0.00800000037997961
},
{
"x": 0.7530999779701233,
"y": 0.5468000173568726,
"t": 0.026000000536441803
},
{
"x": 0.625,
"y": 0.6671000123023987,
"t": 0.057999998331069946
},
{
"x": 0.48919999599456787,
"y": 0.6704000234603882,
"t": 0.1080000028014183
},
{
"x": 0.48809999227523804,
"y": 0.6603999733924866,
"t": 0.1420000046491623
},
{
"x": 0.6039000153541565,
"y": 0.6887999773025513,
"t": 0.17599999904632568
},
{
"x": 0.7297000288963318,
"y": 0.7789999842643738,
"t": 0.20800000429153442
},
{
"x": 0.7307999730110168,
"y": 0.8291000127792358,
"t": 0.24300000071525574
},
{
"x": 0.6205999851226807,
"y": 0.8073999881744385,
"t": 0.2770000100135803
},
{
"x": 0.4390999972820282,
"y": 0.6654000282287598,
"t": 0.30799999833106995
},
{
"x": 0.4068000018596649,
"y": 0.6169000267982483,
"t": 0.32499998807907104
},
{
"x": 0.40450000762939453,
"y": 0.5918999910354614,
"t": 0.3409999907016754
},
{
"x": 0.42570000886917114,
"y": 0.5802000164985657,
"t": 0.3580000102519989
},
{
"x": 0.47360000014305115,
"y": 0.5717999935150146,
"t": 0.37400001287460327
},
{
"x": 0.5436999797821045,
"y": 0.5767999887466431,
"t": 0.39100000262260437
},
{
"x": 0.641700029373169,
"y": 0.6320000290870667,
"t": 0.40700000524520874
},
{
"x": 0.6930000185966492,
"y": 0.6771000027656555,
"t": 0.42399999499320984
},
{
"x": 0.7063000202178955,
"y": 0.7038000226020813,
"t": 0.4410000145435333
},
{
"x": 0.7074000239372253,
"y": 0.717199981212616,
"t": 0.4569999873638153
},
{
"x": 0.6952000260353088,
"y": 0.7271999716758728,
"t": 0.4740000069141388
},
{
"x": 0.6696000099182129,
"y": 0.7271999716758728,
"t": 0.4909999966621399
},
{
"x": 0.6340000033378601,
"y": 0.7105000019073486,
"t": 0.5080000162124634
},
{
"x": 0.5893999934196472,
"y": 0.6754000186920166,
"t": 0.5249999761581421
},
{
"x": 0.5616000294685364,
"y": 0.638700008392334,
"t": 0.5410000085830688
},
{
"x": 0.5548999905586243,
"y": 0.6202999949455261,
"t": 0.5580000281333923
},
{
"x": 0.5570999979972839,
"y": 0.6118999719619751,
"t": 0.574999988079071
},
{
"x": 0.5871999859809875,
"y": 0.6068999767303467,
"t": 0.5910000205039978
},
{
"x": 0.6273000240325928,
"y": 0.6136000156402588,
"t": 0.6079999804496765
},
{
"x": 0.6729000210762024,
"y": 0.6370000243186951,
"t": 0.625
},
{
"x": 0.7164000272750854,
"y": 0.6686999797821045,
"t": 0.640999972820282
},
{
"x": 0.737500011920929,
"y": 0.6988000273704529,
"t": 0.6579999923706055
},
{
"x": 0.7408999800682068,
"y": 0.7138000130653381,
"t": 0.675000011920929
},
{
"x": 0.737500011920929,
"y": 0.723800003528595,
"t": 0.6909999847412109
},
{
"x": 0.7185999751091003,
"y": 0.7289000153541565,
"t": 0.7080000042915344
},
{
"x": 0.6884999871253967,
"y": 0.7289000153541565,
"t": 0.7250000238418579
},
{
"x": 0.6495000123977661,
"y": 0.7055000066757202,
"t": 0.7409999966621399
},
{
"x": 0.6039000153541565,
"y": 0.6754000186920166,
"t": 0.7580000162124634
},
{
"x": 0.5593000054359436,
"y": 0.6320000290870667,
"t": 0.7749999761581421
},
{
"x": 0.5
ade20k_train/ade20k_train_0000000000006847_25.ogg
6
ADE20k
ADE_train_00011825
93
In this picture I can see a building, there is fence, grass, there are plants, shed, vehicle, there are trees, hills, and in the background there is the sky.
[
{
"utterance": "In this",
"start_time": 0.0,
"end_time": 0.0
},
{
"utterance": "picture",
"start_time": 0.0,
"end_time": 0.6000000238418579
},
{
"utterance": "I",
"start_time": 0.6000000238418579,
"end_time": 0.699999988079071
},
{
"utterance": "can",
"start_time": 0.699999988079071,
"end_time": 0.8999999761581421
},
{
"utterance": "see",
"start_time": 0.8999999761581421,
"end_time": 1.100000023841858
},
{
"utterance": "a",
"start_time": 1.100000023841858,
"end_time": 1.100000023841858
},
{
"utterance": "building,",
"start_time": 1.100000023841858,
"end_time": 1.600000023841858
},
{
"utterance": "there",
"start_time": 2.299999952316284,
"end_time": 3.799999952316284
},
{
"utterance": "is",
"start_time": 3.799999952316284,
"end_time": 3.9000000953674316
},
{
"utterance": "fence,",
"start_time": 3.9000000953674316,
"end_time": 4.0
},
{
"utterance": "grass,",
"start_time": 4.0,
"end_time": 4.300000190734863
},
{
"utterance": "there",
"start_time": 4.300000190734863,
"end_time": 4.599999904632568
},
{
"utterance": "are",
"start_time": 4.599999904632568,
"end_time": 4.599999904632568
},
{
"utterance": "plants,",
"start_time": 4.599999904632568,
"end_time": 4.699999809265137
},
{
"utterance": "shed,",
"start_time": 4.699999809265137,
"end_time": 4.699999809265137
},
{
"utterance": "vehicle,",
"start_time": 4.699999809265137,
"end_time": 5.599999904632568
},
{
"utterance": "there",
"start_time": 5.599999904632568,
"end_time": 7.599999904632568
},
{
"utterance": "are",
"start_time": 7.599999904632568,
"end_time": 7.699999809265137
},
{
"utterance": "trees,",
"start_time": 7.699999809265137,
"end_time": 8.300000190734863
},
{
"utterance": "hills,",
"start_time": 8.300000190734863,
"end_time": 8.800000190734863
},
{
"utterance": "and",
"start_time": 8.800000190734863,
"end_time": 8.800000190734863
},
{
"utterance": "in",
"start_time": 8.800000190734863,
"end_time": 8.899999618530273
},
{
"utterance": "the",
"start_time": 8.899999618530273,
"end_time": 8.899999618530273
},
{
"utterance": "background",
"start_time": 8.899999618530273,
"end_time": 9.399999618530273
},
{
"utterance": "there is",
"start_time": 9.399999618530273,
"end_time": 9.699999809265137
},
{
"utterance": "the",
"start_time": 9.699999809265137,
"end_time": 9.899999618530273
},
{
"utterance": "sky.",
"start_time": 9.899999618530273,
"end_time": 10.199999809265137
}
]
[
[
{
"x": 0.1932000070810318,
"y": 0.43869999051094055,
"t": 0.008999999612569809
},
{
"x": 0.24690000712871552,
"y": 0.6136000156402588,
"t": 0.028999999165534973
},
{
"x": 0.41839998960494995,
"y": 0.8794999718666077,
"t": 0.06400000303983688
},
{
"x": 0.6797999739646912,
"y": 1.0047999620437622,
"t": 0.09700000286102295
},
{
"x": 0.875,
"y": 0.9758999943733215,
"t": 0.1120000034570694
},
{
"x": 1.0444999933242798,
"y": 0.7871999740600586,
"t": 0.14499999582767487
}
],
[
{
"x": 1.0166000127792358,
"y": 0.29409998655319214,
"t": 0.210999995470047
},
{
"x": 0.9380000233650208,
"y": 0.17010000348091125,
"t": 0.23000000417232513
},
{
"x": 0.839900016784668,
"y": 0.0723000019788742,
"t": 0.24300000071525574
},
{
"x": 0.730400025844574,
"y": -0.0035000001080334187,
"t": 0.25999999046325684
},
{
"x": 0.6157000064849854,
"y": -0.05169999971985817,
"t": 0.2770000100135803
},
{
"x": 0.49900001287460327,
"y": -0.0640999972820282,
"t": 0.29499998688697815
},
{
"x": 0.3935999870300293,
"y": -0.0640999972820282,
"t": 0.3109999895095825
},
{
"x": 0.2953999936580658,
"y": -0.01720000058412552,
"t": 0.328000009059906
},
{
"x": 0.1817999929189682,
"y": 0.1136000007390976,
"t": 0.34700000286102295
},
{
"x": 0.13330000638961792,
"y": 0.24169999361038208,
"t": 0.35899999737739563
},
{
"x": 0.09610000252723694,
"y": 0.4043000042438507,
"t": 0.3779999911785126
},
{
"x": 0.08370000123977661,
"y": 0.5612999796867371,
"t": 0.3959999978542328
},
{
"x": 0.08780000358819962,
"y": 0.6948999762535095,
"t": 0.4090000092983246
},
{
"x": 0.12809999287128448,
"y": 0.8065000176429749,
"t": 0.4300000071525574
},
{
"x": 0.2045000046491623,
"y": 0.920799970626831,
"t": 0.44600000977516174
},
{
"x": 0.3192000091075897,
"y": 1.0227999687194824,
"t": 0.46000000834465027
}
],
[
{
"x": 0.9090999960899353,
"y": 0.9455999732017517,
"t": 0.5440000295639038
},
{
"x": 0.9587000012397766,
"y": 0.828499972820282,
"t": 0.5600000023841858
},
{
"x": 0.9825000166893005,
"y": 0.6922000050544739,
"t": 0.578000009059906
},
{
"x": 0.9876000285148621,
"y": 0.5626999735832214,
"t": 0.5929999947547913
},
{
"x": 0.980400025844574,
"y": 0.42489999532699585,
"t": 0.6110000014305115
},
{
"x": 0.953499972820282,
"y": 0.2996000051498413,
"t": 0.6269999742507935
},
{
"x": 0.9143000245094299,
"y": 0.1907999962568283,
"t": 0.6439999938011169
},
{
"x": 0.875,
"y": 0.10949999839067459,
"t": 0.6589999794960022
},
{
"x": 0.8191999793052673,
"y": 0.03370000049471855,
"t": 0.6779999732971191
},
{
"x": 0.7520999908447266,
"y": -0.03099999949336052,
"t": 0.6959999799728394
}
],
[
{
"x": 0.29030001163482666,
"y": -0.013100000098347664,
"t": 0.8109999895095825
},
{
"x": 0.2313999980688095,
"y": 0.07639999687671661,
"t": 0.828000009059906
},
{
"x": 0.17149999737739563,
"y": 0.1907999962568283,
"t": 0.8450000286102295
},
{
"x": 0.12189999967813492,
"y": 0.3091999888420105,
"t": 0.8619999885559082
},
{
"x": 0.08259999752044678,
"y": 0.4221999943256378,
"t": 0.8790000081062317
},
{
"x": 0.05779999867081642,
"y": 0.5281999707221985,
ade20k_train/ade20k_train_0000000000011825_93.ogg
7
ADE20k
ADE_train_00010279
51
In this image, we can see a stove and dishwasher. There is a window on the left side of the image. There is a sink on the right side of the image. There is a cupboard at the top of the image.
[
{
"utterance": "In",
"start_time": 0.0,
"end_time": 0.5
},
{
"utterance": "this image,",
"start_time": 0.5,
"end_time": 0.699999988079071
},
{
"utterance": "we can see",
"start_time": 0.699999988079071,
"end_time": 1.100000023841858
},
{
"utterance": "a",
"start_time": 1.100000023841858,
"end_time": 1.399999976158142
},
{
"utterance": "stove",
"start_time": 1.399999976158142,
"end_time": 1.600000023841858
},
{
"utterance": "and",
"start_time": 1.600000023841858,
"end_time": 2.5999999046325684
},
{
"utterance": "dishwasher.",
"start_time": 2.5999999046325684,
"end_time": 3.200000047683716
},
{
"utterance": "There",
"start_time": 3.200000047683716,
"end_time": 5.900000095367432
},
{
"utterance": "is",
"start_time": 5.900000095367432,
"end_time": 6.0
},
{
"utterance": "a",
"start_time": 6.0,
"end_time": 6.0
},
{
"utterance": "window",
"start_time": 6.0,
"end_time": 6.400000095367432
},
{
"utterance": "on",
"start_time": 6.400000095367432,
"end_time": 6.699999809265137
},
{
"utterance": "the",
"start_time": 6.699999809265137,
"end_time": 6.800000190734863
},
{
"utterance": "left",
"start_time": 6.800000190734863,
"end_time": 7.0
},
{
"utterance": "side",
"start_time": 7.0,
"end_time": 7.099999904632568
},
{
"utterance": "of",
"start_time": 7.099999904632568,
"end_time": 7.199999809265137
},
{
"utterance": "the",
"start_time": 7.199999809265137,
"end_time": 7.5
},
{
"utterance": "image.",
"start_time": 7.5,
"end_time": 7.699999809265137
},
{
"utterance": "There",
"start_time": 7.699999809265137,
"end_time": 9.100000381469727
},
{
"utterance": "is a",
"start_time": 9.100000381469727,
"end_time": 9.300000190734863
},
{
"utterance": "sink",
"start_time": 9.300000190734863,
"end_time": 9.699999809265137
},
{
"utterance": "on the",
"start_time": 9.699999809265137,
"end_time": 10.800000190734863
},
{
"utterance": "right side",
"start_time": 10.800000190734863,
"end_time": 10.899999618530273
},
{
"utterance": "of the",
"start_time": 10.899999618530273,
"end_time": 11.300000190734863
},
{
"utterance": "image.",
"start_time": 11.300000190734863,
"end_time": 11.600000381469727
},
{
"utterance": "There",
"start_time": 11.600000381469727,
"end_time": 12.800000190734863
},
{
"utterance": "is",
"start_time": 12.800000190734863,
"end_time": 13.0
},
{
"utterance": "a",
"start_time": 13.0,
"end_time": 13.0
},
{
"utterance": "cupboard",
"start_time": 13.0,
"end_time": 13.399999618530273
},
{
"utterance": "at",
"start_time": 13.399999618530273,
"end_time": 14.399999618530273
},
{
"utterance": "the",
"start_time": 14.399999618530273,
"end_time": 14.5
},
{
"utterance": "top",
"start_time": 14.5,
"end_time": 14.699999809265137
},
{
"utterance": "of",
"start_time": 14.699999809265137,
"end_time": 14.800000190734863
},
{
"utterance": "the",
"start_time": 14.800000190734863,
"end_time": 14.899999618530273
},
{
"utterance": "image.",
"start_time": 14.899999618530273,
"end_time": 15.199999809265137
}
]
[
[
{
"x": 0.11760000139474869,
"y": -0.060499999672174454,
"t": 0.014000000432133675
},
{
"x": 0.11860000342130661,
"y": 0.017899999395012856,
"t": 0.0430000014603138
},
{
"x": 0.12290000170469284,
"y": 0.056299999356269836,
"t": 0.05900000035762787
},
{
"x": 0.12610000371932983,
"y": 0.0877000018954277,
"t": 0.07800000160932541
},
{
"x": 0.14749999344348907,
"y": 0.14890000224113464,
"t": 0.11100000143051147
},
{
"x": 0.17100000381469727,
"y": 0.19300000369548798,
"t": 0.12700000405311584
},
{
"x": 0.19449999928474426,
"y": 0.21299999952316284,
"t": 0.14399999380111694
},
{
"x": 0.226500004529953,
"y": 0.2272000014781952,
"t": 0.16099999845027924
},
{
"x": 0.26820001006126404,
"y": 0.22869999706745148,
"t": 0.1770000010728836
},
{
"x": 0.31200000643730164,
"y": 0.2272000014781952,
"t": 0.1940000057220459
},
{
"x": 0.3546999990940094,
"y": 0.21160000562667847,
"t": 0.20999999344348907
},
{
"x": 0.3910999894142151,
"y": 0.19589999318122864,
"t": 0.2280000001192093
},
{
"x": 0.41990000009536743,
"y": 0.18019999563694,
"t": 0.24300000071525574
},
{
"x": 0.4498000144958496,
"y": 0.163100004196167,
"t": 0.25999999046325684
},
{
"x": 0.4796999990940094,
"y": 0.15320000052452087,
"t": 0.2770000100135803
},
{
"x": 0.505299985408783,
"y": 0.1446000039577484,
"t": 0.2939999997615814
},
{
"x": 0.5289000272750854,
"y": 0.13750000298023224,
"t": 0.3089999854564667
},
{
"x": 0.5394999980926514,
"y": 0.13179999589920044,
"t": 0.3269999921321869
},
{
"x": 0.5394999980926514,
"y": 0.13459999859333038,
"t": 0.3930000066757202
},
{
"x": 0.5267000198364258,
"y": 0.15600000321865082,
"t": 0.4099999964237213
},
{
"x": 0.5031999945640564,
"y": 0.19300000369548798,
"t": 0.4269999861717224
},
{
"x": 0.47540000081062317,
"y": 0.23440000414848328,
"t": 0.4440000057220459
},
{
"x": 0.45089998841285706,
"y": 0.26570001244544983,
"t": 0.460999995470047
},
{
"x": 0.4284000098705292,
"y": 0.28850001096725464,
"t": 0.47699999809265137
},
{
"x": 0.41449999809265137,
"y": 0.30410000681877136,
"t": 0.49399998784065247
},
{
"x": 0.40389999747276306,
"y": 0.3140999972820282,
"t": 0.5099999904632568
},
{
"x": 0.39640000462532043,
"y": 0.3312000036239624,
"t": 0.5260000228881836
},
{
"x": 0.3921000063419342,
"y": 0.34119999408721924,
"t": 0.5429999828338623
},
{
"x": 0.3910999894142151,
"y": 0.35120001435279846,
"t": 0.5600000023841858
},
{
"x": 0.3910999894142151,
"y": 0.35830000042915344,
"t": 0.5759999752044678
},
{
"x": 0.3921000063419342,
"y": 0.3610999882221222,
"t": 0.5929999947547913
},
{
"x": 0.40070000290870667,
"y": 0.3682999908924103,
"t": 0.6119999885559082
},
{
"x": 0.4187999963760376,
"y": 0.3682999908924103,
"t": 0.6259999871253967
},
{
"x": 0.445499986410141,
"y": 0.3682999908924103,
"t": 0.6439999938011169
},
{
"x": 0.48399999737739563,
"y": 0.3596999943256378,
"t": 0.6600000262260437
},
{
"x": 0.5267000198364258,
"y": 0.34119999408721924,
"t": 0.6769999861717224
},
{
"x": 0.5619999766349792,
"y": 0.32839998602867126,
"t": 0.6940000057220459
},
{
"x": 0.5843999981880188,
"y": 0.32120001
ade20k_train/ade20k_train_0000000000010279_51.ogg
8
ADE20k
ADE_train_00016121
67
In the image there are elephants walking on the ground. And also there are trees and rocks. Behind those rocks there is water. At the top of the image there is sky with clouds.
[
{
"utterance": "In the image there are elephants",
"start_time": 0.0,
"end_time": 1.2999999523162842
},
{
"utterance": "walking",
"start_time": 1.2999999523162842,
"end_time": 1.600000023841858
},
{
"utterance": "on",
"start_time": 1.600000023841858,
"end_time": 1.7999999523162842
},
{
"utterance": "the",
"start_time": 1.7999999523162842,
"end_time": 1.899999976158142
},
{
"utterance": "ground.",
"start_time": 1.899999976158142,
"end_time": 2.200000047683716
},
{
"utterance": "And",
"start_time": 2.200000047683716,
"end_time": 2.299999952316284
},
{
"utterance": "also",
"start_time": 2.299999952316284,
"end_time": 2.5999999046325684
},
{
"utterance": "there",
"start_time": 2.5999999046325684,
"end_time": 2.700000047683716
},
{
"utterance": "are",
"start_time": 2.700000047683716,
"end_time": 2.700000047683716
},
{
"utterance": "trees",
"start_time": 2.700000047683716,
"end_time": 3.299999952316284
},
{
"utterance": "and",
"start_time": 3.299999952316284,
"end_time": 3.4000000953674316
},
{
"utterance": "rocks.",
"start_time": 3.4000000953674316,
"end_time": 3.9000000953674316
},
{
"utterance": "Behind",
"start_time": 3.9000000953674316,
"end_time": 4.599999904632568
},
{
"utterance": "those",
"start_time": 4.599999904632568,
"end_time": 4.800000190734863
},
{
"utterance": "rocks",
"start_time": 4.800000190734863,
"end_time": 5.199999809265137
},
{
"utterance": "there",
"start_time": 5.199999809265137,
"end_time": 5.400000095367432
},
{
"utterance": "is",
"start_time": 5.400000095367432,
"end_time": 5.599999904632568
},
{
"utterance": "water. At",
"start_time": 5.599999904632568,
"end_time": 5.900000095367432
},
{
"utterance": "the",
"start_time": 5.900000095367432,
"end_time": 6.0
},
{
"utterance": "top",
"start_time": 6.0,
"end_time": 6.300000190734863
},
{
"utterance": "of",
"start_time": 6.300000190734863,
"end_time": 6.400000095367432
},
{
"utterance": "the",
"start_time": 6.400000095367432,
"end_time": 6.5
},
{
"utterance": "image there is",
"start_time": 6.5,
"end_time": 6.5
},
{
"utterance": "sky",
"start_time": 6.5,
"end_time": 7.300000190734863
},
{
"utterance": "with",
"start_time": 7.300000190734863,
"end_time": 7.599999904632568
},
{
"utterance": "clouds.",
"start_time": 7.599999904632568,
"end_time": 7.699999809265137
}
]
[
[
{
"x": 0.5324000120162964,
"y": 0.29679998755455017,
"t": 0.01600000075995922
},
{
"x": 0.5256999731063843,
"y": 0.3952000141143799,
"t": 0.04800000041723251
},
{
"x": 0.5181000232696533,
"y": 0.42660000920295715,
"t": 0.06499999761581421
},
{
"x": 0.5085999965667725,
"y": 0.45649999380111694,
"t": 0.08100000023841858
},
{
"x": 0.49810001254081726,
"y": 0.483599990606308,
"t": 0.09799999743700027
},
{
"x": 0.4848000109195709,
"y": 0.510699987411499,
"t": 0.11299999803304672
},
{
"x": 0.47909998893737793,
"y": 0.517799973487854,
"t": 0.12999999523162842
},
{
"x": 0.47530001401901245,
"y": 0.5220999717712402,
"t": 0.1469999998807907
},
{
"x": 0.4675999879837036,
"y": 0.5278000235557556,
"t": 0.16300000250339508
},
{
"x": 0.461899995803833,
"y": 0.52920001745224,
"t": 0.18000000715255737
},
{
"x": 0.45910000801086426,
"y": 0.5307000279426575,
"t": 0.19699999690055847
},
{
"x": 0.4562000036239624,
"y": 0.5335000157356262,
"t": 0.24799999594688416
},
{
"x": 0.42669999599456787,
"y": 0.5619999766349792,
"t": 0.27799999713897705
},
{
"x": 0.39430001378059387,
"y": 0.579200029373169,
"t": 0.2980000078678131
},
{
"x": 0.3686000108718872,
"y": 0.5906000137329102,
"t": 0.31299999356269836
},
{
"x": 0.3458000123500824,
"y": 0.5976999998092651,
"t": 0.32899999618530273
},
{
"x": 0.33149999380111694,
"y": 0.5990999937057495,
"t": 0.34700000286102295
},
{
"x": 0.32010000944137573,
"y": 0.6047999858856201,
"t": 0.36399999260902405
},
{
"x": 0.3068000078201294,
"y": 0.607699990272522,
"t": 0.38100001215934753
},
{
"x": 0.29249998927116394,
"y": 0.6090999841690063,
"t": 0.3970000147819519
},
{
"x": 0.27630001306533813,
"y": 0.6133999824523926,
"t": 0.414000004529953
},
{
"x": 0.2619999945163727,
"y": 0.6161999702453613,
"t": 0.4300000071525574
},
{
"x": 0.24490000307559967,
"y": 0.6248000264167786,
"t": 0.44600000977516174
},
{
"x": 0.22679999470710754,
"y": 0.6376000046730042,
"t": 0.46299999952316284
},
{
"x": 0.20589999854564667,
"y": 0.6489999890327454,
"t": 0.47999998927116394
},
{
"x": 0.18870000541210175,
"y": 0.6646999716758728,
"t": 0.4959999918937683
},
{
"x": 0.17640000581741333,
"y": 0.6790000200271606,
"t": 0.5130000114440918
},
{
"x": 0.1754000037908554,
"y": 0.6931999921798706,
"t": 0.5299999713897705
},
{
"x": 0.1754000037908554,
"y": 0.7017999887466431,
"t": 0.546999990940094
},
{
"x": 0.17820000648498535,
"y": 0.7160000205039978,
"t": 0.5640000104904175
},
{
"x": 0.19249999523162842,
"y": 0.7317000031471252,
"t": 0.5809999704360962
},
{
"x": 0.23250000178813934,
"y": 0.7516999840736389,
"t": 0.597000002861023
},
{
"x": 0.2734000086784363,
"y": 0.7645000219345093,
"t": 0.6129999756813049
},
{
"x": 0.3172000050544739,
"y": 0.7702000141143799,
"t": 0.6299999952316284
},
{
"x": 0.3562999963760376,
"y": 0.7702000141143799,
"t": 0.6470000147819519
},
{
"x": 0.38960000872612,
"y": 0.7702000141143799,
"t": 0.6629999876022339
},
{
"x": 0.4219000041484833,
"y": 0.7616999745368958,
"t": 0.6800000071525574
},
{
"x": 0.4438000023365021,
"y": 0.7502999901771545,
"t": 0.
ade20k_train/ade20k_train_0000000000016121_67.ogg
9
ADE20k
ADE_train_00008118
166
It is a blurry image. In this image there are plants and trees.
[
{
"utterance": "It",
"start_time": 0.0,
"end_time": 0.30000001192092896
},
{
"utterance": "is",
"start_time": 0.30000001192092896,
"end_time": 0.5
},
{
"utterance": "a",
"start_time": 0.5,
"end_time": 0.5
},
{
"utterance": "blurry",
"start_time": 0.5,
"end_time": 0.800000011920929
},
{
"utterance": "image.",
"start_time": 0.800000011920929,
"end_time": 1.0
},
{
"utterance": "In",
"start_time": 1.0,
"end_time": 1.7000000476837158
},
{
"utterance": "this",
"start_time": 1.7000000476837158,
"end_time": 1.7999999523162842
},
{
"utterance": "image",
"start_time": 1.7999999523162842,
"end_time": 2.200000047683716
},
{
"utterance": "there",
"start_time": 2.200000047683716,
"end_time": 2.5
},
{
"utterance": "are",
"start_time": 2.5,
"end_time": 2.5999999046325684
},
{
"utterance": "plants",
"start_time": 2.5999999046325684,
"end_time": 3.299999952316284
},
{
"utterance": "and",
"start_time": 3.299999952316284,
"end_time": 4.0
},
{
"utterance": "trees.",
"start_time": 4.0,
"end_time": 4.5
}
]
[
[
{
"x": 0.11900000274181366,
"y": 0.9747999906539917,
"t": 0.014000000432133675
},
{
"x": 0.16169999539852142,
"y": 0.9793999791145325,
"t": 0.024000000208616257
},
{
"x": 0.3095000088214874,
"y": 0.9435999989509583,
"t": 0.04100000113248825
},
{
"x": 0.5485000014305115,
"y": 0.8432000279426575,
"t": 0.05700000002980232
},
{
"x": 0.7609000205993652,
"y": 0.7265999913215637,
"t": 0.07400000095367432
},
{
"x": 0.8614000082015991,
"y": 0.6273000240325928,
"t": 0.09099999815225601
},
{
"x": 0.8995000123977661,
"y": 0.5371999740600586,
"t": 0.10700000077486038
},
{
"x": 0.9041000008583069,
"y": 0.48410001397132874,
"t": 0.12399999797344208
},
{
"x": 0.8763999938964844,
"y": 0.43790000677108765,
"t": 0.14000000059604645
},
{
"x": 0.7678999900817871,
"y": 0.3952000141143799,
"t": 0.15700000524520874
},
{
"x": 0.6074000000953674,
"y": 0.39169999957084656,
"t": 0.17299999296665192
},
{
"x": 0.4422999918460846,
"y": 0.4194999933242798,
"t": 0.19099999964237213
},
{
"x": 0.28290000557899475,
"y": 0.4875999987125397,
"t": 0.2070000022649765
},
{
"x": 0.17440000176429749,
"y": 0.5719000101089478,
"t": 0.2240000069141388
},
{
"x": 0.11550000309944153,
"y": 0.7196999788284302,
"t": 0.2409999966621399
},
{
"x": 0.11089999973773956,
"y": 0.7612000107765198,
"t": 0.257999986410141
},
{
"x": 0.1281999945640564,
"y": 0.8420000076293945,
"t": 0.27300000190734863
},
{
"x": 0.16859999299049377,
"y": 0.8640000224113464,
"t": 0.29100000858306885
},
{
"x": 0.27720001339912415,
"y": 0.8686000108718872,
"t": 0.30799999833106995
},
{
"x": 0.4514999985694885,
"y": 0.8420000076293945,
"t": 0.3240000009536743
},
{
"x": 0.6870999932289124,
"y": 0.7601000070571899,
"t": 0.3400000035762787
},
{
"x": 0.8822000026702881,
"y": 0.6377000212669373,
"t": 0.35600000619888306
},
{
"x": 0.9998999834060669,
"y": 0.5245000123977661,
"t": 0.37299999594688416
},
{
"x": 1.0404000282287598,
"y": 0.41830000281333923,
"t": 0.38999998569488525
},
{
"x": 1.0449999570846558,
"y": 0.3386000096797943,
"t": 0.40799999237060547
},
{
"x": 1.0091999769210815,
"y": 0.2831999957561493,
"t": 0.4230000078678131
},
{
"x": 0.8382999897003174,
"y": 0.2290000021457672,
"t": 0.4410000145435333
},
{
"x": 0.692799985408783,
"y": 0.23589999973773956,
"t": 0.4569999873638153
},
{
"x": 0.5231000185012817,
"y": 0.3005000054836273,
"t": 0.4740000069141388
},
{
"x": 0.4018999934196472,
"y": 0.38370001316070557,
"t": 0.49000000953674316
},
{
"x": 0.3222000002861023,
"y": 0.4726000130176544,
"t": 0.5070000290870667
},
{
"x": 0.28060001134872437,
"y": 0.5834000110626221,
"t": 0.5239999890327454
},
{
"x": 0.2655999958515167,
"y": 0.6676999926567078,
"t": 0.5410000085830688
},
{
"x": 0.2655999958515167,
"y": 0.7045999765396118,
"t": 0.5569999814033508
},
{
"x": 0.272599995136261,
"y": 0.7161999940872192,
"t": 0.5730000138282776
},
{
"x": 0.3037000000476837,
"y": 0.7149999737739563,
"t": 0.5910000205039978
},
{
"x": 0.4077000021934509,
"y": 0.663100004196167,
"t": 0.6069999933242798
},
{
"x": 0.5415999889373779,
"y": 0.5602999925613403,
"t
ade20k_train/ade20k_train_0000000000008118_166.ogg
10
ADE20k
ADE_train_00012550
174
In this picture I can see few vehicles and people on the path in front. On the both sides of this picture, I can see the buildings and I can see the boards on which there are words written. In the background, I can see the clear sky. On the right side of this picture, I can see the leaves.
[
{
"utterance": "In",
"start_time": 0.0,
"end_time": 0.0
},
{
"utterance": "this",
"start_time": 0.0,
"end_time": 1.7999999523162842
},
{
"utterance": "picture",
"start_time": 1.7999999523162842,
"end_time": 2.0
},
{
"utterance": "I",
"start_time": 2.0,
"end_time": 3.5
},
{
"utterance": "can",
"start_time": 3.5,
"end_time": 3.700000047683716
},
{
"utterance": "see",
"start_time": 3.700000047683716,
"end_time": 3.9000000953674316
},
{
"utterance": "few",
"start_time": 3.9000000953674316,
"end_time": 4.599999904632568
},
{
"utterance": "vehicles",
"start_time": 4.599999904632568,
"end_time": 6.300000190734863
},
{
"utterance": "and",
"start_time": 6.300000190734863,
"end_time": 6.599999904632568
},
{
"utterance": "people",
"start_time": 6.599999904632568,
"end_time": 7.099999904632568
},
{
"utterance": "on",
"start_time": 7.099999904632568,
"end_time": 7.300000190734863
},
{
"utterance": "the",
"start_time": 7.300000190734863,
"end_time": 7.400000095367432
},
{
"utterance": "path",
"start_time": 7.400000095367432,
"end_time": 7.900000095367432
},
{
"utterance": "in",
"start_time": 7.900000095367432,
"end_time": 8.100000381469727
},
{
"utterance": "front.",
"start_time": 8.100000381469727,
"end_time": 8.5
},
{
"utterance": "On",
"start_time": 8.5,
"end_time": 9.5
},
{
"utterance": "the",
"start_time": 9.5,
"end_time": 9.600000381469727
},
{
"utterance": "both",
"start_time": 9.600000381469727,
"end_time": 9.800000190734863
},
{
"utterance": "sides",
"start_time": 9.800000190734863,
"end_time": 10.100000381469727
},
{
"utterance": "of",
"start_time": 10.100000381469727,
"end_time": 10.199999809265137
},
{
"utterance": "this",
"start_time": 10.199999809265137,
"end_time": 10.399999618530273
},
{
"utterance": "picture,",
"start_time": 10.399999618530273,
"end_time": 10.5
},
{
"utterance": "I",
"start_time": 10.5,
"end_time": 11.0
},
{
"utterance": "can",
"start_time": 11.0,
"end_time": 11.300000190734863
},
{
"utterance": "see",
"start_time": 11.300000190734863,
"end_time": 11.399999618530273
},
{
"utterance": "the",
"start_time": 11.399999618530273,
"end_time": 11.5
},
{
"utterance": "buildings",
"start_time": 11.5,
"end_time": 13.0
},
{
"utterance": "and",
"start_time": 13.0,
"end_time": 15.100000381469727
},
{
"utterance": "I",
"start_time": 15.100000381469727,
"end_time": 15.600000381469727
},
{
"utterance": "can",
"start_time": 15.600000381469727,
"end_time": 15.899999618530273
},
{
"utterance": "see",
"start_time": 15.899999618530273,
"end_time": 16.200000762939453
},
{
"utterance": "the",
"start_time": 16.200000762939453,
"end_time": 16.399999618530273
},
{
"utterance": "boards",
"start_time": 16.399999618530273,
"end_time": 18.0
},
{
"utterance": "on",
"start_time": 18.0,
"end_time": 18.600000381469727
},
{
"utterance": "which",
"start_time": 18.600000381469727,
"end_time": 18.799999237060547
},
{
"utterance": "there",
"start_time": 18.799999237060547,
"end_time": 18.799999237060547
},
{
"utterance": "are words",
"start_time": 18.799999237060547,
"end_time": 21.399999618530273
},
{
"utterance": "written.",
"start_time": 21.399999618530273,
"end_time": 21.899999618530273
},
{
"utterance": "In",
"start_time": 21.899999618530273,
"end_time": 22.899999618530273
},
{
"utterance": "the",
"start_time": 22.899999618530273,
"end_time": 23.0
},
{
"utterance": "background,",
"start_time": 23.0,
[
[
{
"x": 0.3686999976634979,
"y": 0.29679998755455017,
"t": 0.593999981880188
},
{
"x": 0.3650999963283539,
"y": 0.29679998755455017,
"t": 0.843999981880188
},
{
"x": 0.35899999737739563,
"y": 0.29679998755455017,
"t": 0.8619999885559082
},
{
"x": 0.34940001368522644,
"y": 0.29679998755455017,
"t": 0.8790000081062317
},
{
"x": 0.3312999904155731,
"y": 0.29679998755455017,
"t": 0.8949999809265137
},
{
"x": 0.29280000925064087,
"y": 0.2935999929904938,
"t": 0.9120000004768372
},
{
"x": 0.2687000036239624,
"y": 0.2856000065803528,
"t": 0.9290000200271606
},
{
"x": 0.2361000031232834,
"y": 0.2775000035762787,
"t": 0.9449999928474426
},
{
"x": 0.1964000016450882,
"y": 0.2727000117301941,
"t": 0.9620000123977661
},
{
"x": 0.13860000669956207,
"y": 0.2549999952316284,
"t": 0.9789999723434448
},
{
"x": 0.08070000261068344,
"y": 0.23569999635219574,
"t": 0.9959999918937683
},
{
"x": 0.0421999990940094,
"y": 0.21490000188350677,
"t": 1.0119999647140503
},
{
"x": 0.015699999406933784,
"y": 0.2003999948501587,
"t": 1.0290000438690186
},
{
"x": 0.0012000000569969416,
"y": 0.1843000054359436,
"t": 1.0449999570846558
},
{
"x": -0.007199999876320362,
"y": 0.17149999737739563,
"t": 1.062999963760376
},
{
"x": -0.00839999970048666,
"y": 0.14900000393390656,
"t": 1.0779999494552612
},
{
"x": -0.003599999938160181,
"y": 0.10400000214576721,
"t": 1.0950000286102295
},
{
"x": 0.025299999862909317,
"y": 0.06390000134706497,
"t": 1.1139999628067017
},
{
"x": 0.09880000352859497,
"y": 0.014100000262260437,
"t": 1.128000020980835
},
{
"x": 0.21199999749660492,
"y": -0.02930000051856041,
"t": 1.1449999809265137
},
{
"x": 0.34700000286102295,
"y": -0.061400000005960464,
"t": 1.1610000133514404
},
{
"x": 0.508400022983551,
"y": -0.07429999858140945,
"t": 1.1779999732971191
},
{
"x": 0.6614000201225281,
"y": -0.07429999858140945,
"t": 1.1959999799728394
},
{
"x": 0.8047999739646912,
"y": -0.016499999910593033,
"t": 1.2139999866485596
},
{
"x": 0.944599986076355,
"y": 0.10080000013113022,
"t": 1.2300000190734863
},
{
"x": 1.0529999732971191,
"y": 0.2775000035762787,
"t": 1.2450000047683716
}
],
[
{
"x": 1.0289000272750854,
"y": 0.9185000061988831,
"t": 1.3450000286102295
},
{
"x": 0.9301000237464905,
"y": 0.8960000276565552,
"t": 1.3619999885559082
},
{
"x": 0.8047999739646912,
"y": 0.838100016117096,
"t": 1.378999948501587
},
{
"x": 0.6675000190734863,
"y": 0.7450000047683716,
"t": 1.3960000276565552
},
{
"x": 0.5590000152587891,
"y": 0.6421999931335449,
"t": 1.4110000133514404
},
{
"x": 0.4903999865055084,
"y": 0.555400013923645,
"t": 1.4290000200271606
},
{
"x": 0.4505999982357025,
"y": 0.47350001335144043,
"t": 1.4459999799728394
},
{
"x": 0.43860000371932983,
"y": 0.39320001006126404,
"t": 1.4630000591278076
},
{
"x": 0.4348999857902527,
"y": 0.30320000648498535,
"t": 1.4789999723434448
},
{
"x": 0.448199987411499,
"y": 0.20520000159740448,
"t": 1.496000051498413
},
{
"x": 0.5169000029563904,
"y": 0.07029999792575836,
"t": 1.5130000114440918
},
{
"x": 0.5674999952316284,
"y": 0.0156999
ade20k_train/ade20k_train_0000000000012550_174.ogg