-
Notifications
You must be signed in to change notification settings - Fork 0
/
index.html
601 lines (507 loc) · 24 KB
/
index.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
---
title: "Ayao's Homepage"
layout: default
---
<!-- <div style="position: fixed; bottom: 15px; right:1px;">
<a href=""> <img src="{{ site.baseurl }}/static/img/logo/cn.png" width="50%"; /> </a>
</div> -->
<!-- About -->
<section id="about">
<div class="container">
<br>
<br>
<!-- personal image -->
<div id="profile" class="profile-img col-md-4">
<div class="team-member">
<a href="https://ayameyao.github.io/">
<img class="mx-auto rounded-circle" src="{{site.baseurl}}/static/img/profile/guangyaoli.jpg" />
</a>
<div class="porfile-name"><h3>Guangyao Li</h3></div>
<div class="profile-student text-muted"><h5>PhD Candidate</h5></div>
<h6><a href="https://www.ruc.edu.cn/">Renmin University of China</a></h6>
</div>
<ul class="network-icon" aria-hidden="true">
<li>
<a itemprop="sameAs" href="mailto:guangyaoli@ruc.edu.au" target="_blank" rel="noopener">
<i class="fa fa-envelope big-icon"></i>
</a>
</li>
<li>
<a itemprop="sameAs" href="https://scholar.google.com/citations?view_op=list_works&hl=zh-CN&user=i_KZwgQAAAAJ" target="_blank" rel="noopener">
<i class="ai ai-google-scholar big-icon"></i>
</a>
</li>
<li>
<a itemprop="sameAs" href="https://github.com/ayameyao" target="_blank" rel="noopener">
<i class="fa fa-github big-icon"></i>
</a>
</li>
</ul>
<br>
<br>
<br>
</div>
<div class="profile-img col-md-8" style="float:right">
<h1>Biography</h1>
<p class="text-muted">
I am a postdoctoral researcher at Tsinghua University, working with
Prof. <a href="https://scholar.google.com/citations?user=7t2jzpgAAAAJ&hl=en">Wenwu Zhu </a>
and
Prof. <a href = "https://mn.cs.tsinghua.edu.cn/xinwang/">Xin Wang</a>.
I received my Ph.D. from Renmin University of China, supervised by
Prof. <a href="https://gewu-lab.github.io/">Di Hu</a>
at the Gaoling School of Artificial Intelligence.
My recently research interests include audio-visual learning, scene understanding and Embodied AI.
<!-- Here are my <a href="https://scholar.google.com/citations?view_op=list_works&hl=zh-CN&user=i_KZwgQAAAAJ">Google Scholar</a>. -->
</p>
<div class="row">
<div class="col-lg-12 text-left">
<h4 class="section-subheading" style="text-align:left;">News</h4>
<ul class="text-muted">
<li>[07-2024] One paper accepted by ACMMM, thanks to all co-authors!</li>
<li>[05-2024] One paper accepted by TOMM, thanks to all co-authors!</li>
<li>[05-2024] One paper accepted by CVPR Workshop, thanks to all co-authors!</li>
<li>[07-2023] One paper accepted by ACMMM, thanks to all co-authors!</li>
<li>[05-2023] One paper accepted by INTERSPEECH (<font color="#dc3545"><b>Oral</b></font>), thanks to all co-authors!</li>
<!-- <li>[11-2022] One paper accepted by IJAEOG, thanks to all co-authors!</li> -->
<li>[03-2022] One paper accepted by CVPR (<font color="#dc3545"><b>Oral</b></font>), thanks to all co-authors!</li>
<!-- <li>[03-2021] Predicting sound by clicking on Google Earth! One collaborative work with TUM, DLR and MIT. Here are the <a href="https://arxiv.org/abs/2108.00688">paper</a> and <a href="https://www.youtube.com/watch?v=gD_fNJPBWhs">demo</a>!</li> -->
<li>[08-2020] I will join <a href="https://dtaoo.github.io/group.html">GeWu-Lab</a> to pursue a PhD degree at <a href="https://www.ruc.edu.cn/">Renmin University of China</a>!</li>
</ul>
</div>
</div>
</div>
</div>
</section>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<!-- Publications -->
<section class="bg-light" id="publications" style="clear:both;">
<div class="container">
<!-- <div class="row justify-content-md-center text-center"> -->
<div class="row text-center">
<div class="col-md-12" style="text-align:left">
<h1 class="section-subheading" style="text-align:left; margin-left:-14px">Selected Publications</h1>
</div>
<hr/>
<p style="text-align:left"> <sup>†</sup> indicates equal contribution. </p>
<p style="text-align:left"> Most recent publications on
<a href="https://scholar.google.com/citations?view_op=list_works&hl=zh-CN&user=i_KZwgQAAAAJ">Google Scholar</a>. </p>
<!-- publication 12 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2024_ACMMM2.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Boosting Audio Visual Question Answering via Key Semantic-Aware Cues</h5>
<div class="pub-authors">
<b>Guangyao Li</b>, Henghui Du, Di Hu
</div>
<div class="pub-publication">
<i>Proc. ACM International Conference on Multimedia (ACM MM)</i>, 2024.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="">[Paper]</a>
<a href="">[arXiv]</a>
<a href="">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 11 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2024_CVPRW.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">AVQA-CoT: When CoT Meets Question Answering in Audio-Visual Scenarios </h5>
<div class="pub-authors">
<b>Guangyao Li</b>, Henghui Du, Di Hu
</div>
<div class="pub-publication">
<i>CVPR Sight and Sound Workshops</i>, 2024.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://sightsound.org/papers/2024/Li_AVQA-CoT_When_CoT_Meets_Question_Answering_in_Audio-Visual_Scenarios.pdf">[Paper]</a>
<a href="">[arXiv]</a>
<a href="">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 10 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2023_lfav.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Towards Long Form Audio-visual Video Understanding </h5>
<div class="pub-authors">
Wenxuan Hou<sup>†</sup>, <b>Guangyao Li<sup>†</sup></b>, Yapeng Tian, Di Hu
</div>
<div class="pub-publication">
<i>ACM Transactions on Multimedia Computing, Communications and Applications (TOMM)</i>, 2024.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://gewu-lab.github.io/LFAV/">[Project]</a>
<!-- <a href="https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Learning_To_Answer_Questions_in_Dynamic_Audio-Visual_Scenarios_CVPR_2022_paper.pdf">[Paper]</a> -->
<!-- </a><a href="{{ site.baseurl }}/static/files/MUSIC-AVQA-supp.pdf">[Supp]</a> -->
<!-- </a><a href="https://openaccess.thecvf.com/content/CVPR2022/supplemental/Li_Learning_To_Answer_CVPR_2022_supplemental.pdf">[Supp]</a> -->
<a href="https://arxiv.org/abs/2306.09431">[arXiv]</a>
<!-- <a href="{{ site.baseurl }}/static/files/MUSIC-AVQA-poster.pdf">[Poster]</a> -->
<!-- <a href="https://www.youtube.com/watch?v=JH3t5gwe9Xw">[YouTube]</a> -->
<!-- <a href="https://www.bilibili.com/video/BV1Br4y1q7YN/">[Bilibili]</a> -->
<a href="https://github.com/GeWu-Lab/LFAV">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 09 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2023_iccv.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Prompting Segmentation with Sound is Generalizable Audio-Visual Source Localizer</h5>
<div class="pub-authors">
Yaoting Wang, Weisong Liu, <b>Guangyao Li</b>, Jian Ding, Di Hu, Xi Li
</div>
<div class="pub-publication">
<!-- <i>Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022. -->
<i>The 38th Annual AAAI Conference on Artificial Intelligence (AAAI)</i>, 2024.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://ojs.aaai.org/index.php/AAAI/article/view/28378">[Paper]</a>
<a href="https://arxiv.org/abs/2309.07929">[arXiv]</a>
<a href="https://github.com/GeWu-Lab/Generalizable-Audio-Visual-Segmentation">[Code]</a>
<a href="https://underline.io/lecture/93666-prompting-segmentation-with-sound-is-generalizable-audio-visual-source-localizer">[Video]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 08 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2023_acmmm_avqa2.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Progressive Spatio-temporal Perception for Audio-Visual Question Answering</h5>
<div class="pub-authors">
<b>Guangyao Li</b>, Wenxuan Hou, Di Hu
</div>
<div class="pub-publication">
<!-- <i>Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022. -->
<i>Proc. ACM International Conference on Multimedia (ACM MM)</i>, 2023.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://arxiv.org/abs/2308.05421">[Paper]</a>
<a href="https://arxiv.org/abs/2308.05421">[arXiv]</a>
<a href="https://github.com/GeWu-Lab/PSTP-Net">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 07 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2020_Interspeech_aqa1.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Multi-Scale Attention for Audio Question Answering (<font color="#dc3545"><b>Oral</b></font>)</h5>
<div class="pub-authors">
<b>Guangyao Li</b>, Yixin Xu, Di Hu
</div>
<div class="pub-publication">
<!-- <i>Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022. -->
<i>Proc. Conference of the International Speech Communication Association (INTERSPEECH)</i>, 2023.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://arxiv.org/abs/2305.17993">[Paper]</a>
<a href="https://arxiv.org/abs/2305.17993">[arXiv]</a>
<a href="https://github.com/GeWu-Lab/MWAFM">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 06 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/music-avqa.png" />
</div>
<div class="publication-right" >
<div class="text-muted publication-content">
<h5 class="pub-title">Learning to Answer Questions in Dynamic Audio-Visual Scenarios (<font color="#dc3545"><b>Oral</b></font>)</h5>
<div class="pub-authors">
<b>Guangyao Li<sup>†</sup></b>, Yake Wei<sup>†</sup>, Yapeng Tian<sup>†</sup>, Chenliang Xu, Ji-Rong Wen and Di Hu
</div>
<div class="pub-publication">
<i>Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022.
<!-- <i>In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022. -->
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://gewu-lab.github.io/MUSIC-AVQA/">[Project]</a>
<a href="https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Learning_To_Answer_Questions_in_Dynamic_Audio-Visual_Scenarios_CVPR_2022_paper.pdf">[Paper]</a>
<!-- </a><a href="{{ site.baseurl }}/static/files/MUSIC-AVQA-supp.pdf">[Supp]</a> -->
</a><a href="https://openaccess.thecvf.com/content/CVPR2022/supplemental/Li_Learning_To_Answer_CVPR_2022_supplemental.pdf">[Supp]</a>
<a href="https://arxiv.org/abs/2203.14072">[arXiv]</a>
<a href="{{ site.baseurl }}/static/files/MUSIC-AVQA-poster.pdf">[Poster]</a>
<a href="https://www.youtube.com/watch?v=JH3t5gwe9Xw">[YouTube]</a>
<a href="https://www.bilibili.com/video/BV1Br4y1q7YN/">[Bilibili]</a>
<a href="https://github.com/GeWu-Lab/MUSIC-AVQA">[Code]</a>
</p>
</div>
</div>
</div>
<br>
<!-- publication 05 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/LooktoHearOurPlanet.png" />
</div>
<div class="publication-right">
<div class="text-muted publication-content">
<h5 class="pub-title">Self-supervised Audiovisual Representation Learning for Remote Sensing Data</h5>
<div class="pub-authors">
Konrad Heidler, Lichao Mou, Di Hu, Pu Jin, <b>Guangyao Li</b>, Chuang Gan, Ji-Rong Wen, Xiao Xiang Zhu
</div>
<div class="pub-publication">
<i>International Journal of Applied Earth Observation and Geoinformation (IJAEOG)</i>, 2023.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://www.sciencedirect.com/science/article/pii/S1569843222003181">[Paper]</a>
<a href="https://arxiv.org/abs/2108.00688">[arXiv]</a>
<a href="https://www.youtube.com/watch?v=gD_fNJPBWhs">[Demo](YouTube)</a>
</p>
</div>
</div>
</div>
<br>
<p class="text-muted" style="text-align:left">
<br>
Before 2020, my research interests mainly focus on agricultural artificial intelligence and agricultural informatization.
</p>
<!-- publication 04 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2020_CompAgri_review.png" />
</div>
<div class="publication-right">
<div class="text-muted publication-content">
<h5 class="pub-title">A review of computer vision technologies for plant phenotyping</h5>
<div class="pub-authors">
Zhenbo Li, Ruohao Guo, Meng Li, Yaru Chen, <b>Guangyao Li</b>
</div>
<div class="pub-publication">
<i>Computers and Electronics in Agriculture (COMPAG)</i>, 2020.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<!-- <a href="{{ site.baseurl }}/static/files/publications/A_review_of_computer_vision_technologies_for_plant_phenotyping.pdf">[Pdf] </a> -->
<a href="https://www.sciencedirect.com/science/article/abs/pii/S0168169920307511">[Paper]</a>
<!-- <a href="hhttps://www.youtube.com/watch?v=gD_fNJPBWhs" style="color:#ffc107">[Demo]</a> -->
</p>
</div>
</div>
</div>
<br>
<!-- publication 03 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2019_prcv_shellfish.png" />
</div>
<div class="publication-right">
<div class="text-muted publication-content">
<h5 class="pub-title">Shellfish Detection based on Fusion Attention Mechanism in End-to-End Network</h5>
<div class="pub-authors">
<b>Guangyao Li</b>, Zhenbo Li, Chuyue Zhang, Yaodong Li, Jun Yue
</div>
<div class="pub-publication">
<!-- <i>Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 2022. -->
<i>Proc. Conference on Pattern Recognition and Computer Vision (PRCV)</i>. 2019.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://dl.acm.org/doi/abs/10.1007/978-3-030-31726-3_44">[Paper]</a>
<!-- <a href="https://link.springer.com/chapter/10.1007/978-3-030-31726-3_44">[Springer]</a> -->
<!-- <a href="hhttps://www.youtube.com/watch?v=gD_fNJPBWhs" style="color:#ffc107">[Demo]</a> -->
</p>
</div>
</div>
</div>
<br>
<!-- publication 02 -->
<div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2018_ifac_cucumber.png" />
</div>
<div class="publication-right">
<div class="text-muted publication-content">
<h5 class="pub-title">Sea cucumber image dehazing method by fusion of Retinex and dark channel</h5>
<div class="pub-authors">
Zhenbo Li, <b>Guangyao Li</b>, Bingshan Niu, Fang Peng
</div>
<div class="pub-publication">
<i>IFAC PapersOnLine</i>, 2018.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://www.sciencedirect.com/science/article/pii/S240589631831214X?via%3Dihub">[Paper]</a>
<!-- <a href="hhttps://www.youtube.com/watch?v=gD_fNJPBWhs" style="color:#ffc107">[Demo]</a> -->
</p>
</div>
</div>
</div>
<br>
<!-- publication 01 -->
<!-- <div class="publication">
<div class="publication-left">
<img src="{{ site.baseurl }}/static/files/publications/2018_ifac_waterquality.png" />
</div>
<div class="publication-right">
<div class="text-muted publication-content">
<h5 class="pub-title">Water Quality Prediction Model Combining Sparse Auto-encoder and LSTM Network</h5>
<div class="pub-authors">
Zhenbo Li, Fang Peng, Bingshan Niu, <b>Guangyao Li</b>, Jing Wu, Zheng Miao
</div>
<div class="pub-publication">
<i>IFAC PapersOnLine</i>, 2018.
</div>
<p class="text-muted" style="color:#00F; margin-bottom:0rem; line-height: 1.5">
<a href="https://www.sciencedirect.com/science/article/pii/S2405896318312072">[Paper]</a>
</p>
</div>
</div>
</div> -->
</div>
</div>
</div>
</section>
<!-- Service -->
<section id="service" style="clear:both;">
<div class="container">
<!-- <div class="row justify-content-md-center text-center"> -->
<!-- <div class="row text-center"> -->
<div class="row">
<div class="col-md-12" style="text-align:left">
<h1 class="section-subheading" style="text-align:left; margin-left:-14px">Service</h1>
<h1 class="section-subheading" style="text-align:left; margin-left:-14px"><hr/></h1>
</div>
<br>
<br>
<!-- <ul> -->
<!-- <b>PC Member:</b> IJCAI 2023, AAAI 2024 -->
<!-- <ul>
<li>IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2024,</li>
<li>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, 2024,</li>
<li>International Joint Conference on Artificial Intelligence (IJCAI) 2023.</li>
<li>Asian Conference on Computer Vision (ACCV) 2022,</li>
</ul> -->
<!-- </ul> -->
<ul>
<b>Conference Reviewer:</b>
<ul>
<li>IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2024,</li>
<li>ACM International Conference on Multimedia (ACMMM) 2024,</li>
<li>Annual Conference on Neural Information Processing Systems (NeurIPS) 2024,</li>
<li>IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, 2024,</li>
<li>International Joint Conference on Artificial Intelligence (IJCAI) 2023, 2024,</li>
<li>Asian Conference on Computer Vision (ACCV) 2022.</li>
</ul>
</ul>
<ul>
<b>Journal Reviewer:</b>
<ul>
<li>IEEE Transactions on Multimedia (TMM),</li>
<li>IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).</li>
</ul>
</ul>
</div>
</div>
</section>
<!-- Contact -->
<section id="contact">
<!-- <section class="bg-light" id="contact"> -->
<div class="container">
<br>
<h2 class="section-heading text-uppercase">Contact</h2>
<div class="text-muted">
Email: guangyaoli@ruc.edu.cn
<br>
Address: Lide Building
</div>
</div>
</section>
<script type="application/ld+json">
{
"@context":"http://schema.org/",
"@type":"Dataset",
"name":"MUSIC-AVQA dataset",
"description":"First-person (egocentric) video dataset; multi-faceted non-scripted recordings in the wearers' homes, capturing all daily activities in the kitchen over multiple days. Annotations are collected using a novel live audio commentary approach.",
"url":"https://github.com/epic-kitchens/annotations",
"sameAs":"https://data.bris.ac.uk/data/dataset/3h91syskeag572hl6tvuovwv4d",
"citation":"Damen, Dima et al. 'Scaling Egocentric Vision: The EPIC-KITCHENS Dataset', European Conference on Computer Vision, 2018",
"identifier": "10.5523/bris.3h91syskeag572hl6tvuovwv4d",
"keywords":[
"Egocentric vision",
"Human actions",
"Object interactions",
"actions",
"video",
"kitchens",
"cooking",
"dataset",
"epic kitchens",
"epic",
"eccv",
"2022"
],
"creator":{
"@type":"Organization",
"url": "https://epic-kitchens.github.io/",
"name":"EPIC Team",
"contactPoint":{
"@type":"ContactPoint",
"contactType": "technical support",
"email":"uob-epic-kitchens@bristol.ac.uk",
"url":"https://github.com/epic-kitchens/annotations/issues"
}
},
"distribution":[
{
"@type":"DataDownload",
"encodingFormat":"video/mp4",
"contentUrl":"https://data.bris.ac.uk/data/dataset/3h91syskeag572hl6tvuovwv4d"
},
{
"@type":"DataDownload",
"encodingFormat":"image/jpeg",
"contentUrl":"https://data.bris.ac.uk/data/dataset/3h91syskeag572hl6tvuovwv4d"
},
{
"@type":"DataDownload",
"encodingFormat":"text/csv",
"contentUrl":"https://github.com/epic-kitchens/annotations"
},
{
"@type":"DataDownload",
"encodingFormat":"application/octet-stream",
"contentUrl":"https://github.com/epic-kitchens/annotations"
}
],
"license": "https://creativecommons.org/licenses/by-nc/4.0/"
}
</script>