-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.html
executable file
·1041 lines (989 loc) · 46 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
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!doctype html>
<html lang="en">
<html xmlns="http://www.w3.org/1999/xhtml"><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"><link href="./Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation_files/chalkduster" rel="stylesheet">
<!-- <link rel="shortcut icon" href="data:image/svg+xml,<svg xmlns=%22http://www.w3.org/2000/svg%22 viewBox=%220 0 100 100%22><text y=%22.9em%22 font-size=%2290%22>🐼</text></svg>"> -->
<style>
@import url('https://fonts.cdnfonts.com/css/chalkduster');
</style>
<head>
<!-- Required meta tags -->
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<meta name="google-site-verification" content="eGDOZ_6azobM9Vcl7r072IFo1FJ-TfNvGkmz6YbLCLo" />
<!-- Bootstrap CSS -->
<link href="./html_pages/resources/bootstrap.min.css" rel="stylesheet">
<link href="./html_pages/resources/stylesheet.css" rel="stylesheet">
<script src="js/jquery-2.1.3.min.js"> </script>
<title>Video-MMMU</title>
</head>
<body data-new-gr-c-s-check-loaded="14.1110.0" data-gr-ext-installed="">
<header>
<nav>
<a class="h5 pt-1" style="margin-left: 10px; color: #fff !important;" href="#Video-MMMU">Video-MMMU</a>
</nav>
<nav>
<!-- Dropdown Menu -->
<div class="dropdown">
<a href="#Leaderboard">Leaderboard</a>
<a href="#Examples">VideoMMMU Examples</a>
<div class="dropdown-content">
<a href="#Art">Art</a>
<a href="#Business">Business</a>
<a href="#Humanities">Humanities</a>
<a href="#Science">Science</a>
<a href="#Medicine">Medicine</a>
<a href="#Engineering">Engineering</a>
</div>
</div>
</nav>
</header>
<section class="jumbotron text-center pb-2" id="Video-MMMU">
<div class="container">
<br><br><br>
<!-- Title with Icon -->
<h1 class="jumbotron-heading" style="font-size: 5.5rem; display: flex; align-items: center; justify-content: center; gap: 10px;">
<img src="./assets/figures/pyramid-chart.png" alt="Video-MMMU Icon" style="height: 5.5rem; width: auto;">
Video-MMMU
</h1>
<!-- Subtitle -->
<h5 class="pt-1" style="font-size: 2rem; font-weight: normal">
Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
</h5>
<br><br>
<!-- Paper Link -->
<a style="font-size: 1.2rem; color: white !important;">Paper under review</a>
<br><br>
<br><br><br>
</div>
</section>
<div style="display: flex; justify-content: space-around; flex-wrap: wrap; margin-top: -65px;">
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Business_Economics_1.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Business</span><br>
<span class="subtitle">Economics</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Business_Finance_2.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Business</span><br>
<span class="subtitle">Finance</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Business_Manage_3.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Business</span><br>
<span class="subtitle">Manage</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Business_Economics_4.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Business</span><br>
<span class="subtitle">Economics</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Engineering_Architecture_Engineering_5.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Engineering</span><br>
<span class="subtitle">Architecture</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Engineering_energy_6.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Engineering</span><br>
<span class="subtitle">Energy</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Engineering_electronics_8.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Engineering</span><br>
<span class="subtitle">Electronics</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Engineering_Computer_Science_1.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Engineering</span><br>
<span class="subtitle">Computer Science</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Art_Arthistory_13.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Art</span><br>
<span class="subtitle">Art Theory</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Art_Arttheory_14.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Art</span><br>
<span class="subtitle">Art Theory</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Humanities_psychology_15.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Humanities</span><br>
<span class="subtitle">Psychology</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Humainities_history_16.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Humanities</span><br>
<span class="subtitle">History</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Science_Physics_11.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Science</span><br>
<span class="subtitle">Physics</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Science_Chemistry_10.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Science</span><br>
<span class="subtitle">Chemistry</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/test_Clinical_medicine_173.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Medicine</span><br>
<span class="subtitle">Clinical Medicine</span>
</p>
</div>
</div>
<div class="video-teaser-container">
<video playsinline autoplay="autoplay" loop="loop" muted="muted" type="video/mp4" class="video-teaser" src="./assets/samples/Medicine_public_health_12.mp4"></video>
<div class="hover-overlay">
<p class="text-container">
<span class="title">Medicine</span><br>
<span class="subtitle">Public Health</span>
</p>
</div>
</div>
</div>
<section id="Abstract">
<hr class="mt-5">
<div class="container" style="margin-top: 30px">
<h1 class="text-center">Abstract</h1>
<br>
<p class="description text-left">
Humans acquire knowledge through three cognitive stages: perceiving information, comprehending knowledge, and adapting knowledge to solve novel problems. Videos serve as an effective medium for this learning process, facilitating a progression through these cognitive stages. However, existing video benchmarks fail to systematically evaluate the <i>knowledge acquisition</i> capabilities in Large Multimodal Models (LMMs). To address this gap, we introduce <strong>Video-MMMU</strong>, a multi-modal, multi-disciplinary benchmark designed to assess LMMs' ability to acquire and utilize knowledge from videos. Video-MMMU features a curated collection of 300 expert-level videos and 900 human-annotated questions across six disciplines, evaluating <i>knowledge acquisition</i> through stage-aligned question-answer pairs: Perception, Comprehension, and Adaptation. A proposed knowledge gain metric, Δ<sub>knowledge</sub>, quantifies improvement in performance after video viewing. Evaluation of LMMs reveals a steep decline in performance as cognitive demands increase and highlights a significant gap between human and model knowledge acquisition, underscoring the need for methods to enhance LMMs' capability to learn and adapt from videos.
</p>
<br>
<div class="image-viewer" style="margin-top: 20px; text-align: center;">
<img src="./assets/figures/figure_1.png" alt="Example PDF as Image" style="width: 80%; border-radius: 15px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);">
</div>
</div>
</section>
<section id="Overview">
<hr class="mt-5">
<div class="container" style="margin-top: 30px">
<h1 class="text-center">Overview</h1>
<br>
<p class="description text-left">
We introduce <strong>Video-MMMU</strong>, a massive, multi-modal, multi-disciplinary video benchmark that evaluates the knowledge acquisition capability from educational videos through three main features:
</p>
<p class="description text-left">
<strong>1) Knowledge-intensive Video Collection:</strong><br>
Our dataset comprises 300 expert-level videos spanning 6 professional disciplines: Art, Business, Science, Medicine, Humanities, and Engineering, with 30 subjects distributed among them.
</p>
<p class="description text-left">
<strong>2) Knowledge Acquisition-based Question Design:</strong><br>
Each video includes three question-answer pairs aligned with the three knowledge acquisition stages: Perception (identifying key information related to the knowledge), Comprehension (understanding the underlying concepts), and Adaptation (applying knowledge to new scenarios).
</p>
<p class="description text-left">
<strong>3) Quantitative Knowledge Acquisition Assessment:</strong><br>
We propose a knowledge acquisition metric, denoted as <i>Δ<sub>knowledge</sub></i>, to measure performance gains on practice exam questions after learning from videos. This metric enables us to quantitatively evaluate how effectively large multimodal models (LMMs) can assimilate and utilize the information presented in the videos to solve real-world, novel problems.
</p>
<br>
<div class="image-viewer" style="margin-top: 20px; text-align: center;">
<img src="./assets/figures/figure_2.png"
alt="Figure 2"
style="width: 80%; border-radius: 15px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);">
</div>
<p class="description text-left">
<br>
<strong>Key Insights:</strong>
</p>
<div class="insights" style="margin-top: 10px;">
<ul style="line-height: 1.8;">
<li>
<strong>1) Progressive Performance Decline:</strong><br>
Model performance decreases as cognitive demands increase. While models perform relatively better on perception tasks, their accuracy drops notably on comprehension tasks and declines further on adaptation tasks.
</li>
<li style="margin-top: 15px;">
<strong>2) Knowledge Acquisition from Videos is Challenging:</strong><br>
The knowledge acquisition metric <i>Δ<sub>knowledge</sub></i> reveals a significant gap between human and model performance. While humans achieve substantial improvement (<i>Δ<sub>knowledge</sub></i> = 33.1%) after watching the videos, even the top-performing models show smaller knowledge gains (<i>GPT-4o</i>: <i>Δ<sub>knowledge</sub></i> = 15.6%, <i>Claude-3.5-Sonnet</i>: <i>Δ<sub>knowledge</sub></i> = 11.4%).
</li>
</ul>
<p style="margin-top: 15px;">
This limitation underscores a potential challenge in current LMMs. While humans naturally acquire knowledge through video-based learning, having developed this capability through classroom learning and educational experiences throughout life, LMMs struggle to effectively learn from videos. These findings emphasize the need for further research to enhance how LMMs acquire and utilize video-based information, bringing them closer to human-level learning processes.
</p>
</div>
</section>
<section id="Statistics">
<hr class="mt-5">
<div class="container" style="margin-top: 30px">
<h1 class="text-center">Statistics</h1>
<!-- <div style="margin-top: 15px;">
<h3><strong>Perception Questions</strong></h3>
<ul style="line-height: 1.8;">
<li>
<strong>1) Optical Character Recognition (OCR):</strong> Questions that require extracting visual information, including formulas, data, charts, and handwritten content.
</li>
<li>
<strong>2) Automatic Speech Recognition (ASR):</strong> Questions that assess accurate transcription of spoken content.
</li>
</ul>
</div>
<div style="margin-top: 20px;">
<h3><strong>Comprehension Questions</strong></h3>
<ul style="line-height: 1.8;">
<li>
<strong>1) Concept Comprehension (CC):</strong> Questions that test conceptual understanding using multiple-answer multiple-choice (MAMC) format, presenting 4-10 statements with multiple possible correct answers.
</li>
<li>
<strong>2) Problem-solving Strategy Comprehension (PSC):</strong> Questions that assess understanding by presenting variants of video example questions with different values. These questions require applying the same reasoning process demonstrated in the video to new calculations.
</li>
</ul>
</div>
<div style="margin-top: 20px;">
<h3><strong>Adaptation Questions</strong></h3>
<ul style="line-height: 1.8;">
<li>
<strong>1) Case Study Analysis (CSA):</strong> Questions that test concept application to novel real-world scenarios.
</li>
<li>
<strong>2) Problem-solving Strategy Adaptation (PSA):</strong> Questions that assess the ability to modify learned solution methods for new problems by identifying key similarities and differences between examples and new scenarios.
</li>
</ul>
</div>
<p style="margin-top: 30px;">
We present 6 QA samples from Video-MMMU as follows:
</p> -->
<br>
<div class="image-viewer" style="margin-top: 20px; text-align: center;">
<img src="./assets/figures/figure_3.png"
alt="Figure 3"
style="width: 80%; border-radius: 15px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);">
</div>
</div>
</section>
<section id="Annotation Pipeline">
<hr class="mt-5">
<div class="container" style="margin-top: 30px">
<h1 class="text-center">Annotation Pipeline</h1>
<br>
<!-- Video Viewer -->
<div class="video-viewer" style="margin-top: 20px; text-align: center;">
<video controls autoplay muted="false" style="width: 80%; border-radius: 15px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);">
<source src="./assets/figures/pipeline_video.mp4" type="video/mp4">
</video>
</div>
</div>
</section>
<section id="Leaderboard">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<h1>Video-MMMU Leaderboard</h1>
<p class="description">We evaluate various open-source and proprietary LMMs. The table below provides a detailed comparison.</p>
<div class="legend">
<div class="legend-item">
<div class="legend-color human"></div>
<span>Human Expert</span>
</div>
<div class="legend-item">
<div class="legend-color opensource"></div>
<span>Open-Source</span>
</div>
<div class="legend-item">
<div class="legend-color proprietary"></div>
<span>Proprietary</span>
</div>
</div>
<table>
<thead>
<tr>
<th>Model</th>
<th>Overall</th>
<th>Perception</th>
<th>Comprehension</th>
<th>Adaptation</th>
</tr>
</thead>
<tbody>
<tr class="human-row">
<td>Human Expert</td>
<td>74.44</td>
<td>84.33</td>
<td>78.67</td>
<td>60.33</td>
</tr>
<tr class="proprietary-row">
<td>Claude-3.5-Sonnet</td>
<td>65.78</td>
<td>72.00</td>
<td>69.67</td>
<td>55.67</td>
</tr>
<tr class="proprietary-row">
<td>GPT-4o</td>
<td>61.22</td>
<td>66.00</td>
<td>62.00</td>
<td>55.67</td>
</tr>
<tr class="proprietary-row">
<td>Gemini 1.5 Pro</td>
<td>53.89</td>
<td>59.00</td>
<td>53.33</td>
<td>49.33</td>
</tr>
<tr class="opensource-row">
<td>Aria</td>
<td>50.78</td>
<td>65.67</td>
<td>46.67</td>
<td>40.00</td>
</tr>
<tr class="proprietary-row">
<td>Gemini 1.5 Flash</td>
<td>49.78</td>
<td>57.33</td>
<td>49.00</td>
<td>43.00</td>
</tr>
<tr class="opensource-row">
<td>LLaVA-Video-72B</td>
<td>49.67</td>
<td>59.67</td>
<td>46.00</td>
<td>43.33</td>
</tr>
<tr class="opensource-row">
<td>LLaVA-OneVision-72B</td>
<td>48.33</td>
<td>59.67</td>
<td>42.33</td>
<td>43.00</td>
</tr>
<tr class="opensource-row">
<td>MAmmoTH-VL-8B</td>
<td>41.78</td>
<td>51.67</td>
<td>40.00</td>
<td>33.67</td>
</tr>
<tr class="opensource-row">
<td>InternVL2-8B</td>
<td>37.44</td>
<td>47.33</td>
<td>33.33</td>
<td>31.67</td>
</tr>
<tr class="opensource-row">
<td>LLaVA-Video-7B</td>
<td>36.11</td>
<td>41.67</td>
<td>33.33</td>
<td>33.33</td>
</tr>
<tr class="opensource-row">
<td>VILA1.5-40B</td>
<td>34.00</td>
<td>38.67</td>
<td>30.67</td>
<td>32.67</td>
</tr>
<tr class="opensource-row">
<td>LLaVA-OneVision-7B</td>
<td>33.89</td>
<td>40.00</td>
<td>31.00</td>
<td>30.67</td>
</tr>
<tr class="opensource-row">
<td>Llama-3.2-11B</td>
<td>30.00</td>
<td>35.67</td>
<td>32.33</td>
<td>22.00</td>
</tr>
<tr class="opensource-row">
<td>LongVA-7B</td>
<td>23.98</td>
<td>24.00</td>
<td>24.33</td>
<td>23.67</td>
</tr>
<tr class="opensource-row">
<td>VILA1.5-8B</td>
<td>20.89</td>
<td>20.33</td>
<td>17.33</td>
<td>25.00</td>
</tr>
</tbody>
</table>
</div>
</section>
<section id="Art">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<h1>Video-MMMU Examples</h1>
<br>
<br>
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Art</h2>
<!-- YouTube Video -->
<div class="youtube-container" style="margin-top: 30px">
<iframe width="560" height="315" src="https://www.youtube.com/embed/Enej5kRTpW4?si=2nsQajSKBBtM-FFe" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> Which of the following does NOT appear in the video frame when the video introduces Painting?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Intense, warm colors</li>
<li>Strong contrasts of light and dark</li>
<li>Focus on movement, drama, and emotion</li>
<li>Abstraction</li>
<li>Allegory</li>
<li>Enhanced sense of movement</li>
<li>Deliberately set apart from Renaissance and Mannerism</li>
<li>Asymmetry</li>
<li>Renaissance</li>
<li>Mannerism</li>
</ol>
<p><strong>Ground truth: </strong>D. Abstraction</p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on your understanding of the video, which of the following statements about Baroque painting is/are correct?</p>
<ul>
<li>Statement 1. Baroque paintings focused on calm, balanced scenes with even lighting.</li>
<li>Statement 2. Baroque artists used strong contrasts of light and dark to highlight key figures.</li>
<li>Statement 3. Baroque painting was known for symmetrical compositions and a sense of stability.</li>
<li>Statement 4. Baroque artists avoided using allegory in their works.</li>
</ul>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Statement 1 is correct</li>
<li>Statement 1 and 2 are correct</li>
<li>Statement 1, 2, and 3 are correct</li>
<li>Statement 1, 3, and 4 are correct</li>
<li>Statement 2 and 4 are correct</li>
<li>Statement 3 is correct</li>
<li>Statements 1 and 4 are correct</li>
<li>Statements 1, 3, and 4 are correct</li>
<li>Statement 2 is correct</li>
<li>All are correct</li>
</ol>
<p><strong>Ground truth: </strong>I. Statement 2 is correct</p>
</div>
</div>
<!-- Adaptation Track -->
<div class="track">
<div class="track-title adaptation">Adaptation Track</div>
<div class="track-content">
<p><strong>Question:</strong> On the basis of style, this painting belongs to which of the following periods?</p>
<p>
<img src="./assets/samples/images_for_adaptation_track/new_Art_Theory_6.jpg" alt="Painting for Adaptation Question" style="max-width: 100%; height: auto; display: block; margin: 10px auto;" />
</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Rococo</li>
<li>Gothic</li>
<li>Renaissance</li>
<li>Baroque</li>
<li>Neoclassicism</li>
<li>Byzantine</li>
<li>Mannerism</li>
<li>Romanticism</li>
<li>Art Nouveau</li>
<li>Classical</li>
</ol>
<p><strong>Ground truth: </strong>I. Baroque</p>
</div>
</div>
</div>
</div>
</section>
<!-- <hr class="mt-5"> -->
<section id="Business">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Business</h2>
<!-- YouTube Video -->
<div class="youtube-container">
<iframe width="560" height="315" src="https://www.youtube.com/embed/ix03LGUQC7s?si=2eVRDUBESAGFeXfP" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> According to the video, a minimum price control for alcoholic drinks, the intention is to discourage consumption from Q1 to ____, due to the negative externalities, and the price is raised to ____ from the free market price of ____. Fill in the blanks based on the video content.</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>(Q*, Pmin, P1)</li>
<li>(Q*, P1, Pmin)</li>
<li>(Q1, Pmin, P2)</li>
<li>(Q2, P1, Pmin)</li>
<li>(Q*, P2, P1)</li>
<li>(Q1, P2, Pmin)</li>
<li>(Q2, Pmin, P1)</li>
<li>(Q*, Pmin, P2)</li>
<li>(Q2, P2, P1)</li>
<li>(Q1, P1, Pmin)</li>
</ol>
<p><strong>Ground truth: </strong>A. (Q*, Pmin, P1)</p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on your understanding, what is the correct sequence of consequences when a minimum price is imposed on a good with negative externalities in consumption?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Free market equilibrium at P1 and Q1 → Minimum price imposed above P1 → Consumption contracts to Q* → Externality internalized.</li>
<li>Minimum price imposed above P1 → Free market equilibrium at P1 and Q1 → Consumption contracts to Q* → Externality internalized.</li>
<li>Free market equilibrium at P1 and Q1 → Consumption contracts to Q* → Minimum price imposed above P1 → Externality internalized.</li>
<li>Externality internalized → Free market equilibrium at P1 and Q1 → Minimum price imposed above P1 → Consumption contracts to Q*.</li>
<li>Minimum price imposed above P1 → Consumption contracts to Q* → Externality internalized → Free market equilibrium at P1 and Q1.</li>
<li>Consumption contracts to Q* → Minimum price imposed above P1 → Free market equilibrium at P1 and Q1 → Externality internalized.</li>
<li>Free market equilibrium at P1 and Q1 → Minimum price imposed above P1 → Externality internalized → Consumption contracts to Q*.</li>
<li>Minimum price imposed above P1 → Free market equilibrium at P1 and Q1 → Externality internalized → Consumption contracts to Q*.</li>
<li>Externality internalized → Minimum price imposed above P1 → Free market equilibrium at P1 and Q1 → Consumption contracts to Q*.</li>
<li>Consumption contracts to Q* → Externality internalized → Minimum price imposed above P1 → Free market equilibrium at P1 and Q1.</li>
</ol>
<p><strong>Ground truth: </strong>A. Free market equilibrium at P1 and Q1 → Minimum price imposed above P1 → Consumption contracts to Q* → Externality internalized.</p>
</div>
</div>
<!-- Adaptation Track -->
<div class="track">
<div class="track-title adaptation">Adaptation Track</div>
<div class="track-content">
<p><strong>Question:</strong> Suppose the government decided that, since gasoline is a necessity, its price should be legally capped at $1.30 per gallon. What do you anticipate would be the outcome in the gasoline market?</p>
<p>
<img src="./assets/samples/images_for_adaptation_track/validation_Economics_2.png" alt="Gasoline Market Question" style="max-width: 100%; height: auto; display: block; margin: 10px auto;" />
</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>A price below that of $1.30 would cause a situation of excess demand and hence a surplus.</li>
<li>A price below that of $1.30 would cause a situation of excess demand and hence a shortage.</li>
<li>Not certain.</li>
<li>A price above that of $1.30 would cause a situation of excess demand and hence a shortage.</li>
<li>A price above that of $1.30 would cause a situation of excess supply and hence a shortage.</li>
<li>A price at $1.30 per gallon would result in an equilibrium where supply meets demand.</li>
<li>A price below that of $1.30 would cause a situation of excess supply and hence a surplus.</li>
<li>A price at $1.30 would eliminate any market shortages or surpluses.</li>
<li>A price of $1.30 would result in both excess demand and excess supply, depending on consumer preferences.</li>
<li>All situations are possible.</li>
</ol>
<p><strong>Ground truth: </strong>B. A price below that of $1.30 would cause a situation of excess demand and hence a shortage.</p>
</div>
</div>
</div>
</div>
</section>
<!-- <hr class="mt-5"> -->
<section id="Humanities">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Humanities</h2>
<!-- YouTube Video -->
<div class="youtube-container">
<iframe width="560" height="315" src="https://www.youtube.com/embed/1PnAVfnCG10?si=XDlObPB1DR54DQt8" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on the video, fill in the blanks about the Functionalist view of society’s culture:</p>
<p>"Functionalists take a ________ view on society’s culture and suggest it ________."</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Consensus, reflects the norms and values of the majority — a value consensus</li>
<li>Unified, represents shared practices and beliefs of a group</li>
<li>Conflict, reveals power struggles and competing interests within society</li>
<li>Critical, critiques the dominant traditions that maintain inequalities</li>
<li>Conservative, emphasizes the preservation of societal expectations</li>
<li>Agreement, highlights the shared opinions and moral agreements</li>
<li>Progressive, encourages the development of new cultural ideologies</li>
<li>Stratified, reflects the rules that structure society into classes</li>
<li>Divisive, showcases the competing customs and traditions in society</li>
<li>Analytical, breaks down societal structures into individual roles</li>
</ol>
<p><strong>Ground truth: </strong>A. Consensus, reflects the norms and values of the majority — a value consensus</p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on your understanding, which of the following statements about different sociological theories on culture is/are false?</p>
<p><strong>Statements:</strong></p>
<ul>
<li>Statement 1. Functionalists argue that society’s culture is fragmented, and individuals create their own norms based on personal preferences and life experiences.</li>
<li>Statement 2. Marxists suggest that culture is imposed by the ruling class (bourgeoisie) to maintain control over the working class and reinforce capitalist ideologies.</li>
<li>Statement 3. Feminists believe that culture is male-dominated and reflects patriarchal values, prioritizing men’s interests over women’s.</li>
<li>Statement 4. Postmodernists suggest that there is a single dominant culture, and individuals can choose their own cultural norms.</li>
</ul>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Statement 1 is false</li>
<li>Statement 2 is false</li>
<li>Statement 3 is false</li>
<li>Statement 4 is false</li>
<li>Statements 1 and 2 are false</li>
<li>Statements 3 and 4 are false</li>
<li>Statements 1 and 4 are false</li>
<li>Statements 1 and 3 are false</li>
<li>Statements 2 and 4 are false</li>
<li>None of the statements are false</li>
</ol>
<p><strong>Ground truth: </strong>G. Statements 1 and 4 are false</p>
</div>
</div>
<!-- Adaptation Track -->
<div class="track">
<div class="track-title adaptation">Adaptation Track</div>
<div class="track-content">
<p><strong>Question:</strong> Identify the theory that the following argument represents.</p>
<p>
<img src="./assets/samples/images_for_adaptation_track/sociology_4.png" alt="Gasoline Market Question" style="max-width: 100%; height: auto; display: block; margin: 10px auto;" />
</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Functionalism</li>
<li>Marxism</li>
<li>New Right</li>
<li>Postmodernism</li>
<li>Social action approaches</li>
<li>Interactionism</li>
<li>Feminism</li>
<li>Conflict Theory</li>
<li>Modernity</li>
<li>Positivists</li>
</ol>
<p><strong>Ground truth: </strong>Functionalism</p>
</div>
</div>
</div>
</div>
</section>
<!-- <hr class="mt-5"> -->
<section id="Science">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Science</h2>
<!-- YouTube Video -->
<div class="youtube-container">
<iframe width="560" height="315" src="https://www.youtube.com/embed/TQSvfrSJucI?si=xNUh5Ny5annIfdId" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> What is the equation used when solving the first question in the video?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>y = v<sub>0y</sub> t + 1/2 g t<sup>2</sup></li>
<li>y = y<sub>0</sub> + v<sub>0x</sub> t - 1/2 g t<sup>2</sup></li>
<li>y = v<sub>0x</sub> t + g t<sup>2</sup></li>
<li>y = y<sub>0</sub> + v<sub>0y</sub> t - 1/2 g t<sup>2</sup></li>
<li>y = v<sub>0y</sub> t - g t</li>
<li>y = y<sub>0</sub> + v<sub>0x</sub> t + 1/2 g t<sup>2</sup></li>
<li>y = y<sub>0</sub> + g t</li>
<li>y = y<sub>0</sub> + v<sub>0y</sub> t + g t<sup>2</sup></li>
<li>y = v<sub>0x</sub> t + 1/2 g t<sup>2</sup></li>
<li>y = y<sub>0</sub> + 1/2 g t<sup>2</sup></li>
</ol>
<p><strong>Ground truth: </strong>D. y = y<sub>0</sub> + v<sub>0y</sub> t - 1/2 g t<sup>2</sup></p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> If the angle theta is changed to 30 degrees, what is the result of the first question about the total time in the air?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>4.00 seconds</li>
<li>2.82 seconds</li>
<li>3.50 seconds</li>
<li>2.50 seconds</li>
<li>3.04 seconds</li>
<li>2.00 seconds</li>
<li>3.15 seconds</li>
<li>1.85 seconds</li>
<li>2.25 seconds</li>
<li>3.85 seconds</li>
</ol>
<p><strong>Ground truth: </strong>E. 3.04 seconds</p>
</div>
</div>
<!-- Adaptation Track -->
<div class="track">
<div class="track-title adaptation">Adaptation Track</div>
<div class="track-content">
<p><strong>Question:</strong> A rocket is shot from the top of a tower at an angle of 45° above the horizontal (Fig. 19-1). It hits the ground in 5 seconds at a horizontal distance from the foot of the tower equal to three times the height of the tower. Find the height of the tower.</p>
<p>
<img src="./assets/samples/images_for_adaptation_track/science_math_23.png" alt="Rocket Adaptation Question" style="max-width: 100%; height: auto; display: block; margin: 10px auto;" />
</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>h = 100 ft</li>
<li>h = 80 ft</li>
<li>h = 110 ft</li>
<li>h = 85 ft</li>
<li>h = 90 ft</li>
<li>h = 95 ft</li>
<li>h = 105 ft</li>
<li>h = 120 ft</li>
<li>h = 75 ft</li>
<li>h = 115 ft</li>
</ol>
<p><strong>Ground truth: </strong>A. h = 100 ft</p>
</div>
</div>
</div>
</div>
</section>
<!-- <hr class="mt-5"> -->
<section id="Medicine">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Medicine</h2>
<!-- YouTube Video -->
<div class="youtube-container">
<iframe width="560" height="315" src="https://www.youtube.com/embed/FI3-28tdovk?si=ckgiWJUK0speh1Ec" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> At the beginning of the video, what are the muscles in the lower left corner, upper left corner, and lower right corner, respectively?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Cardiac muscle, Smooth muscle, Skeletal muscle</li>
<li>Skeletal muscle, Cardiac muscle, Smooth muscle</li>
<li>Skeletal muscle, Smooth muscle, Cardiac muscle</li>
<li>Smooth muscle, Cardiac muscle, Skeletal muscle</li>
<li>Smooth muscle, Skeletal muscle, Cardiac muscle</li>
<li>Smooth muscle, Cardiac muscle, Cardiac muscle</li>
<li>Skeletal muscle, Skeletal muscle, Smooth muscle</li>
<li>Cardiac muscle, Smooth muscle, Smooth muscle</li>
<li>Skeletal muscle, Smooth muscle, Smooth muscle</li>
<li>Cardiac muscle, Skeletal muscle, Smooth muscle</li>
</ol>
<p><strong>Ground truth: </strong>J. Cardiac muscle, Skeletal muscle, Smooth muscle</p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on the video, how many of the following characteristics can be used to identify the different types of muscle tissue?</p>
<p>Characteristics:</p>
<ul>
<li>(c1). Presence of striations</li>
<li>(c2). Presence of intercalated discs</li>
<li>(c3). Voluntary control</li>
<li>(c4). Involuntary control</li>
<li>(c5). Branching appearance</li>
<li>(c6). Smooth, spindle-shaped cells</li>
<li>(c7). Long, cylindrical fibers</li>
<li>(c8). Multinucleated cells</li>
<li>(c9). Location</li>
</ul>
<p><strong>Options:</strong></p>
<ol type="A">
<li>0</li>
<li>1</li>
<li>2</li>
<li>3</li>
<li>4</li>
<li>5</li>
<li>6</li>
<li>7</li>
<li>8</li>
<li>9</li>
</ol>
<p><strong>Ground truth: </strong>H. 7</p>
</div>
</div>
<!-- Adaptation Track -->
<div class="track">
<div class="track-title adaptation">Adaptation Track</div>
<div class="track-content">
<p><strong>Question:</strong> What kind of tissue does this image depict?</p>
<p>
<img src="./assets/samples/images_for_adaptation_track/medicine_11.jpg" alt="Muscle Tissue Question" style="max-width: 100%; height: auto; display: block; margin: 10px auto;" />
</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Cardiac muscle</li>
<li>Skeletal muscle</li>
<li>Cartilage</li>
<li>Smooth muscle</li>
<li>Tendon</li>
<li>Ligament</li>
<li>Adipose tissue</li>
<li>Epithelium</li>
<li>Connective tissue</li>
<li>Nerve tissue</li>
</ol>
<p><strong>Ground truth: </strong>A. Cardiac muscle</p>
</div>
</div>
</div>
</div>
</section>
<!-- <hr class="mt-5"> -->
<section id="Engineering">
<hr class="mt-5">
<div class="container text-center" style="margin-top: 30px">
<!-- Section Title -->
<h2 class="section-title">Video-MMMU Examples - Engineering</h2>
<!-- YouTube Video -->
<div class="youtube-container">
<iframe width="560" height="315" src="https://www.youtube.com/embed/LnF-dYhi8JE?si=B5X6V7WeJOn0Dv6y" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
</div>
<!-- Question Tracks -->
<div class="tracks-row flex" style="margin-top: 20px;">
<!-- Perception Track -->
<div class="track">
<div class="track-title perception">Perception Track</div>
<div class="track-content">
<p><strong>Question:</strong> Identify the correct sequence of steps to construct the minimum spanning tree using Kruskal's algorithm from the graph described in the video.</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>Add CF, add AC, add EF, add BC, add FG.</li>
<li>Add BE, add EF, add CF, add BC, add FG.</li>
<li>Add BE, add EF, add FG, add BC, add CD.</li>
<li>Add BE, add AC, add EF, add FC, add CD.</li>
<li>Add BE, add BC, add AC, add EF, add FG.</li>
<li>Add BE, add AC, add DF, add BC, add CD.</li>
<li>Add BE, add AC, add EF, add BC, add FG.</li>
<li>Add BE, add AC, add DF, add FG, add BC.</li>
<li>Add BE, add EF, add BC, add FG, add CD.</li>
<li>Add BE, add AC, add FG, add EF, add BC.</li>
</ol>
<p><strong>Ground truth: </strong>G. Add BE, add AC, add EF, add BC, add FG.</p>
</div>
</div>
<!-- Comprehension Track -->
<div class="track">
<div class="track-title comprehension">Comprehension Track</div>
<div class="track-content">
<p><strong>Question:</strong> Based on the graph example in the video, if you apply Kruskal's algorithm and the weight of the first few edges changes slightly, which would be the resulting edge sequence if the edge BE now has a weight of 1 and EF a weight of 0.5?</p>
<p><strong>Options:</strong></p>
<ol type="A">
<li>EF, AC, BE, BC, FG</li>
<li>BE, EF, AC, FG, BC</li>
<li>BE, AC, BC, EF, FG</li>
<li>AC, BE, EF, BC, FG</li>
<li>EF, BE, FG, AC, BC</li>
<li>EF, BE, AC, BC, FG</li>
<li>BE, EF, FG, BC, AC</li>
<li>EF, AC, BC, BE, FG</li>