generated from eliahuhorwitz/Academic-project-page-template
-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathindex.html
More file actions
executable file
·669 lines (612 loc) · 28.6 KB
/
index.html
File metadata and controls
executable file
·669 lines (612 loc) · 28.6 KB
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
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<!-- Meta tags for social media banners, these should be filled in appropriatly as they are your "business card" -->
<!-- Replace the content tag with appropriate information -->
<meta name="description" content="DESCRIPTION META TAG">
<meta property="og:title" content="SOCIAL MEDIA TITLE TAG" />
<meta property="og:description" content="SOCIAL MEDIA DESCRIPTION TAG TAG" />
<meta property="og:url" content="URL OF THE WEBSITE" />
<!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X630-->
<meta property="og:image" content="static/image/your_banner_image.png" />
<meta property="og:image:width" content="1200" />
<meta property="og:image:height" content="630" />
<meta name="twitter:title" content="TWITTER BANNER TITLE META TAG">
<meta name="twitter:description" content="TWITTER BANNER DESCRIPTION META TAG">
<!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600-->
<meta name="twitter:image" content="static/images/your_twitter_banner_image.png">
<meta name="twitter:card" content="summary_large_image">
<!-- Keywords for your paper to be indexed by-->
<meta name="keywords" content="KEYWORDS SHOULD BE PLACED HERE">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>LAMM</title>
<link rel="icon" type="image/x-icon" href="static/images/lamm.ico">
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
<link rel="stylesheet" href="static/css/bulma.min.css">
<link rel="stylesheet" href="static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="static/css/bulma-slider.min.css">
<link rel="stylesheet" href="static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="static/css/index.css">
<link rel="stylesheet" href="static/css/style.css" type="text/css">
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script src="https://documentcloud.adobe.com/view-sdk/main.js"></script>
<script defer src="static/js/fontawesome.all.min.js"></script>
<script src="static/js/bulma-carousel.min.js"></script>
<script src="static/js/bulma-slider.min.js"></script>
<script src="static/js/index.js"></script>
</head>
<body>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">
<img src="static/images/lamm.png" align="left" width="150px" hspace="15"/>
LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark</h1>
<div class="is-size-5 publication-authors">
<!-- Paper authors -->
<span class="author-block">
<a href="https://scholar.google.com.hk/citations?user=ngPR1dIAAAAJ&hl=zh-CN" target="_blank">Zhenfei Yin</a><sup>1*</sup>,</span>
<span class="author-block">
<a href="https://github.com/wangjiongw" target="_blank">Jiong Wang</a><sup>1, 3*</sup>,</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=S25Lr3oAAAAJ&hl=zh-CN" target="_blank">Jianjian Cao</a><sup>1, 4*</sup>,</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=EDLcoVkAAAAJ&hl=zh-CN" target="_blank">Zhelun Shi</a><sup>1, 2*</sup>,</span>
<span class="author-block">
<a href="https://github.com/lnbxldn" target="_blank">Dingning Liu</a><sup>1, 5</sup>,</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=BizedOAAAAAJ" target="_blank">Mukai Li</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://xiaoshuihuang.github.io/" target="_blank">Xiaoshui Huang</a><sup>1</sup>,<br></span>
<span class="author-block">
<a href="https://lucassheng.github.io/" target="_blank">Lu Sheng</a><sup></sup><sup>2</sup>,</span>
<span class="author-block">
<a href="http://leibai.site/" target="_blank">Lei Bai</a><sup></sup><sup>1, †</sup>,</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=Sqou_P0AAAAJ&hl=en" target="_blank">Zhiyong Wang</a><sup>6</sup>,</span>
<span class="author-block">
<a href="https://amandajshao.github.io/" target="_blank">Jing Shao</a><sup>1, †</sup>,</span>
<span class="author-block">
<a href="https://wlouyang.github.io/" target="_blank">Wanli Ouyang</a><sup>1</sup></span>
</div>
<div class="is-size-5 publication-authors">
<span class="author-block">
<sup>1</sup>Shanghai Artificial Intelligence Lab,
<sup>2</sup>Beihang University, <sup>3</sup>The Chinese University of Hong Kong (Shenzhen),
<sup>4</sup>Fudan University, <sup>5</sup>Dalian University of Technology, <sup>6</sup>The University of Sydney<br>
<span class="eql-cntrb"><small><br><sup>*</sup>Indicates Equal Contribution; </small><small><sup>†</sup>Indicates Corresponding Authors</small></span>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<!-- Arxiv PDF link -->
<span class="link-block">
<a href="https://arxiv.org/pdf/2306.06687.pdf" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span>
<!-- Supplementary PDF link -->
<!-- <span class="link-block">
<a href="static/pdfs/supplementary_material.pdf" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Supplementary</span>
</a>
</span> -->
<!-- Github link -->
<span class="link-block">
<a href="https://github.com/OpenLAMM/LAMM" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Github</span>
</a>
</span>
<!-- Data Link -->
<span class="link-block">
<a href="https://opendatalab.com/LAMM/download" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-database"></i>
</span>
<span>Data</span>
</a>
</span>
<!-- Demo Link -->
<span class="link-block">
<a href="https://huggingface.co/spaces/openlamm/LAMM" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-gamepad"></i>
</span>
<span>Demo</span>
</a>
</span>
<!-- Model Link -->
<span class="link-block">
<a href="https://huggingface.co/openlamm" target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-box"></i>
</span>
<span>Models</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- Teaser Video -->
<section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/M7XlIe8hhPk" frameborder="0" allow="autoplay; encrypted-media"
allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- End teaser video -->
<!-- Teaser Poster -->
<!-- <section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<img src="static/images/imagewall.png" alt="MY ALT TEXT" width="900px" height="auto"/>
</div>
</div>
</section> -->
<!-- End teaser poster -->
<!-- Paper abstract -->
<section class="section hero is-light">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
Large language models have become a potential pathway toward achieving artificial general intelligence.
Recent works on multi-modal large language models have demonstrated their effectiveness in handling visual
modalities. In this work, we extend the research of MLLMs to point clouds and present the LAMM-Dataset and
LAMM-Benchmark for 2D image and 3D point cloud understanding. We also establish an extensible framework to
facilitate the extension of MLLMs to additional modalities.
Our main contribution is three-fold: 1) We present the LAMM-Dataset and LAMM-Benchmark, which cover almost
all high-level vision tasks for 2D and 3D vision. Extensive experiments validate the effectiveness of our
dataset and benchmark. 2) We demonstrate the detailed methods of constructing instruction-tuning datasets
and benchmarks for MLLMs, which will enable future research on MLLMs to scale up and extend to other
domains, tasks, and modalities faster. 3) We provide a primary but potential MLLM training framework
optimized for modalities' extension. We also provide baseline models, comprehensive experimental
observations, and analysis to accelerate future research.
</p>
</div>
</div>
</div>
</div>
</section>
<!-- End paper abstract -->
<!-- Image carousel -->
<section class="hero is-small">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="column is-centered has-text-centered">
<h2 class="title is-3">LAMM-Dataset</h2>
<img src="static/images/dataset.png" alt="MY ALT TEXT" width="900px" height="auto"/>
<h2 class="subtitle has-text-centered">
LAMM-Dataset
</h2>
<p style="font-size: 16px; text-align: left;">
<strong>LAMM-Dataset</strong> is a comprehensive multi-modal instruction tuning dataset, which contains <strong>186,098</strong> language-image instruction-response pairs, and <strong> 10,262</strong> lanuage-3D instruction-response pairs. We collect images and point clouds from publicly available datasets and use the GPT API and self-instruction methods to generate instructions and responses based on the original labels from these datasets. In LAMM-Dataset, the instruction-response pairs are gathered from 8 image datasets and 4 point cloud datasets. Here we design four type of multi-modal instruction-response pairs,
</p>
<ul style="font-size: 16px; text-align: left;">
<li>
<strong>C1:</strong> n-round daily dialogue focuses on multi-modal daily conversations.
</li>
<li>
<strong>C2:</strong> n-round factual knowledge dialogue aims at factual knowledge reasoning.
</li>
<li>
<strong>C3:</strong> 1-round detailed description aims to elaborate images and 3D scenes in texts.
</li>
<li>
<strong>C4:</strong> 1-round visual task dialogue transfers various vision tasks into instruction-response pairs, aiming at enhancing generalizability towards domain tasks in other modalities.
</li>
</ul>
</div>
</div>
</div>
</section>
<!-- End image carousel -->
<!-- Image carousel -->
<section class="hero is-small">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="column is-centered has-text-centered">
<h2 class="title is-3">LAMM-Benchmark</h2>
<img src="static/images/benchmark.png" alt="MY ALT TEXT" width="900px" height="auto"/>
<h2 class="subtitle has-text-centered">
LAMM-Benchmark
</h2>
<p style="font-size: 16px; text-align: left;">
<strong> LAMM-Benchmark </strong> evaluates 9 common image tasks, using a total of 11 datasets with over <strong>62,439</strong> samples, and 3 common point cloud tasks, by utilizing 3 datasets with over <strong>12,788</strong> data samples, while existing works only provide quantitative results on fine-tuning and evaluating specific datasets such as ScienceQA, and most works only conduct demonstration or user studies.
</p>
<ul style="font-size: 16px; text-align: left;">
<li>
We are the very first attempt to establish a benchmark for MLLMs. We conducted a comprehensive benchmark to quantify the zero-shot and fine-tuning performance of existing multi-modal language models on various computer vision tasks and compare them against state-of-the-art methods of these tasks, including classification, object detection, pose estimation, visual question answering, facial classification, optical character recognition, object counting.
</li>
<li>
We also attempted two novel evaluation strategies designed explicitly for MLLMs. Specifically, as for text generation, we established a scoring logic based on the GPT API. As for tasks involving interactions between points and images, such as object detection and pose estimation, we proposed an object-locating evaluation method.
</li>
</ul>
</div>
</div>
</div>
</section>
<!-- End image carousel -->
<!-- Image carousel -->
<section class="hero is-small">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="column is-centered has-text-centered">
<h2 class="title is-3">Examples</h2>
<img src="static/images/daily_dialogue.png" alt="MY ALT TEXT" width="900px" height="auto"/>
<img src="static/images/detail_description.png" alt="MY ALT TEXT" width="1000px" height="auto"/>
<img src="static/images/factual_knowledge.png" alt="MY ALT TEXT" width="900px" height="auto"/>
<img src="static/images/visual_task.png" alt="MY ALT TEXT" width="900px" height="auto"/>
</div>
</div>
</div>
</section>
<!-- Leaderboard -->
<section class="section hero is-light">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-centered has-text-centered">
<h2 class="title is-3">Leaderboard</h2>
<table class="lamm" style="text-align: center;">
<caption><b>Comparison of Multimodal Large Language Models on 2D computer vision tasks</b></caption>
<thead>
<tr>
<th>Task</th>
<th>Dataset</th>
<th>Metric</th>
<th>SOTA</th>
<th>LLaVA</th>
<th>MiniGPT4</th>
<th>mPLUG-owl</th>
<th>LAMM</th>
</tr>
</thead>
<tbody>
<tr>
<td>Classification</td>
<td>CIFAR10</td>
<td>Acc ↑</td>
<td>99.5</td>
<td><b><u>60.83</u></b></td>
<td>46.22</td>
<td>42.5</td>
<td>34.5</td>
</tr>
<tr>
<td>Detection</td>
<td>VOC2012</td>
<td>mAP ↑</td>
<td>97.2</td>
<td>1.42</td>
<td>0.92</td>
<td>0.158</td>
<td><b><u>4.82</u></b></td>
</tr>
<tr>
<td>VQA</td>
<td>SQAimage</td>
<td>Acc ↑</td>
<td>92.53<br>N/A</td>
<td>40.5<br>18.13</td>
<td>43.43<br>Failed</td>
<td>36.39<br>19.31</td>
<td><b><u>47.15</u></b></td>
</tr>
<tr>
<td>VQA</td>
<td>AI2D</td>
<td>Acc ↑</td>
<td>N/A</td>
<td>18.13</td>
<td>Failed</td>
<td>19.31</td>
<td>19.5</td>
</tr>
<tr>
<td>Image Caption</td>
<td>flickr30k</td>
<td>BLEU4 ↑</td>
<td>30.1</td>
<td><b><u>6.65</u></b></td>
<td>5.1</td>
<td>2.74</td>
<td>0.70</td>
</tr>
<tr>
<td>F-g clasification</td>
<td>UCMerced</td>
<td>Acc ↑</td>
<td>100</td>
<td><b><u>47</u></b></td>
<td>33.6</td>
<td>32.5</td>
<td>13</td>
</tr>
<tr>
<td>Counting</td>
<td>FSC147</td>
<td>MAE ↓</td>
<td>10.79</td>
<td>56.2</td>
<td>Failed</td>
<td>60.67</td>
<td><b><u>53.97</u></b></td>
</tr>
<tr>
<td>OCR</td>
<td>SVT</td>
<td>Word Acc ↑</td>
<td>97.9</td>
<td><b><u>37.78</u></b></td>
<td>16.97</td>
<td>30.39</td>
<td>4.2</td>
</tr>
<tr>
<td>Facial Classification</td>
<td>CelebA(Smile)</td>
<td>Acc ↑</td>
<td>N/A</td>
<td>Failed</td>
<td><b><u>66.36</u></b></td>
<td>Failed</td>
<td>51.3</td>
</tr>
<tr>
<td>Facial Classification</td>
<td>CelebA(Hair)</td>
<td>Acc ↑</td>
<td>N/A</td>
<td><b><u>46.42</u></b></td>
<td>43.47</td>
<td>40.93</td>
<td>30.48</td>
</tr>
<tr>
<td>Keypoints Detection</td>
<td>LSP</td>
<td>PCK ↑</td>
<td>99.5</td>
<td>Failed</td>
<td>Failed</td>
<td>Failed</td>
<td>Failed</td>
</tr>
</tbody>
</table>
<table class="lamm" style="text-align: center;">
<caption><b>Results of LAMM model on selected 2D vision tasks</b></caption>
<thead>
<tr>
<th>Task</th>
<th>Dataset</th>
<th>LAMM(Zero-Shot)</th>
<th>LAMM(Finetune)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Classification (Acc)</td>
<td>CIFAR10</td>
<td>34.5</td>
<td>91.2</td>
</tr>
<tr>
<td>Object Detection (Acc)</td>
<td>VOC2012</td>
<td>4.82</td>
<td>13.48</td>
</tr>
<tr>
<td>VQA (mAP@0.5)</td>
<td>SQAimage</td>
<td>47.15</td>
<td>74.27</td>
</tr>
</tbody>
</table>
<table class="lamm" align="center">
<caption><b>Results of 3D tasks by LAMM</b></caption>
<thead>
<tr>
<th>Task</th>
<th>Dataset</th>
<th>SOTA</th>
<th>LAMM(Zero-Shot)</th>
<th>LAMM(Finetune)</th>
</tr>
</thead>
<tbody>
<tr>
<td>3D Object Detection <b>(mAP@0.5)</b></td>
<td>ScanNet</td>
<td>63.2</td>
<td>9.3</td>
<td>11.89</td>
</tr>
<tr>
<td>Visual Grounding <b>(mAP@0.5)</b></td>
<td>ScanRefer</td>
<td>54.59</td>
<td>Failed</td>
<td>3.38</td>
</tr>
<tr>
<td>3D VQA <b>(Acc of multiple choice prolblem)</b></td>
<td>ScanQA</td>
<td>N/A</td>
<td>26.54</td>
<td>99.89</td>
</tr>
</tbody>
</table>
<table class="lamm" align="center">
<caption><b>Comparison of results of Binary Locating Metric and GPT Metric of existing MLLMs</b></caption>
<thead>
<tr>
<th></th>
<th>LLaVA</th>
<th>MiniGPT4</th>
<th>mPLUG-owl</th>
<th>LAMM</th>
</tr>
</thead>
<tbody>
<tr>
<td>Binary-Loc Metric</td>
<td>14.73</td>
<td>13.12</td>
<td>4.42</td>
<td><b><u>31.2</u></b></td>
</tr>
<tr>
<td>GPT Metric</td>
<td>11</td>
<td>-</td>
<td>-</td>
<td><b><u>89</u></b></td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</section>
<!-- End Leaderboard -->
<!-- Youtube video -->
<!-- <section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<h2 class="title is-3">Video Presentation</h2>
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/M7XlIe8hhPk" frameborder="0" allow="autoplay; encrypted-media"
allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</div>
</section> -->
<!-- End youtube video -->
<!-- Video carousel -->
<!-- <section class="hero is-small">
<div class="hero-body">
<div class="container">
<h2 class="title is-3">Another Carousel</h2>
<div id="results-carousel" class="carousel results-carousel">
<div class="item item-video1">
<video poster="" id="video1" autoplay controls muted loop height="100%">
<source src="static/videos/carousel1.mp4" type="video/mp4">
</video>
</div>
<div class="item item-video2">
<video poster="" id="video2" autoplay controls muted loop height="100%">
<source src="static/videos/carousel2.mp4" type="video/mp4">
</video>
</div>
<div class="item item-video3">
<video poster="" id="video3" autoplay controls muted loop height="100%">\
<source src="static/videos/carousel3.mp4" type="video/mp4">
</video>
</div>
</div>
</div>
</div>
</section> -->
<!-- End video carousel -->
<!-- Paper poster -->
<!-- <section class="hero is-small is-light">
<div class="hero-body">
<div class="container">
<h2 class="title">Poster</h2>
<iframe src="static/pdfs/LAMM.pdf" width="100%" height="550">
</iframe>
</div>
</div>
</section> -->
<!--End paper poster -->
<!--BibTex citation -->
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article{yin2023lamm,
title={LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark},
author={Yin, Zhenfei and Wang, Jiong and Cao, Jianjian and Shi, Zhelun and Liu, Dingning and Li, Mukai and Sheng, Lu and Bai, Lei and Huang, Xiaoshui and Wang, Zhiyong and others},
journal={arXiv preprint arXiv:2306.06687},
year={2023}
}
</code></pre>
</div>
</section>
<!--End BibTex citation -->
<footer class="footer">
<div class="container">
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<h2 class="title">Acknowledgement</h2>
<p>
- Thanks Mr. Hongxing Fan and Mr. Zeren Chen for support of LAMM project. <br>
- This page was built using the <a href="https://github.com/eliahuhorwitz/Academic-project-page-template"
target="_blank">Academic Project Page Template</a>.
<!-- You are free to borrow the of this website, we just ask that you link back to this page in the footer. <br> This website is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/" target="_blank">Creative -->
<!-- Commons Attribution-ShareAlike 4.0 International License</a>. -->
</p>
</div>
</div>
</div>
</div>
</footer>
<!-- Statcounter tracking code -->
<!-- Default Statcounter code for LAMM Page https://openlamm.github.io/ -->
<script type="text/javascript">
var sc_project=12890989;
var sc_invisible=0;
var sc_security="2b9c183b";
var scJsHost = "https://";
document.write("<sc"+"ript type='text/javascript' src='" + scJsHost+
"statcounter.com/counter/counter.js'></"+"script>");
</script>
<noscript><div class="statcounter"><a title="Web Analytics Made Easy -
Statcounter" href="https://statcounter.com/" target="_blank"><img
class="statcounter" src="https://c.statcounter.com/12890989/0/2b9c183b/0/"
alt="Web Analytics Made Easy - Statcounter"
referrerPolicy="no-referrer-when-downgrade"></a></div></noscript>
<!-- You can add a tracker to track page visits by creating an account at statcounter.com -->
<!-- End of Statcounter Code -->
</body>
</html>