-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.html
172 lines (155 loc) · 7.57 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
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="description" content="Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation">
<meta name="keywords"
content="egocentric,video understanding,vision language models">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model</title>
<!-- Google tag (gtag.js) -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-B5BEN25S50"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-B5BEN25S50');
</script>
<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="icon" href="./static/images/favicon.svg"> -->
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.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-2 publication-title">HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model</h1>
<h2 class="title is-6 publlication-title">🎉 Accepted to NeurIPS 2024 🎉</h2>
<div class="is-size-6 publication-authors">
<span class="author-block">
<a href="https://vhvkhoa.github.io/">Khoa Vo</a>,
</span>
<span class="author-block">
<a href="https://uark-aicv.github.io/team/thinh_phan">Thinh Phan</a>,
</span>
<span class="author-block">
<a href="https://kashu7100.github.io/">Kashu Yamazaki</a>,
</span>
<span class="author-block">
<a href="https://trqminh.github.io/">Minh Tran</a>,
</span>
<span class="author-block">
<a href="https://uark-aicv.github.io/team/ngan_le">Ngan Le</a>,
</span>
</div>
<div class="is-size-6 publication-authors">
<span class="author-block">University of Arkansas</span>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<span class="link-block">
<a href="https://openreview.net/forum?id=7uWzoGn4kv&referrer=%5Bthe%20profile%20of%20Khoa%20Vo%5D(%2Fprofile%3Fid%3D~Khoa_Vo1)"
class="external-link button is-normal is-rounded">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Open Review</span>
</a>
</span>
<span class="link-block">
<a href="https://arxiv.org/abs/2406.00307"
class="external-link button is-normal is-rounded">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>
<span class="link-block">
<a
class="button is-normal disabled is-rounded" aria-disabled="true">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code (coming soon)</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<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>Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities,
which presents two major limitations: (1) visual reasoning disobeys the natural perception that humans do in first-person perspective, leading to a lack of reasoning interpretation; and (2) learning is limited in capturing inherent fine-grained relationships between two modalities.
</p>
<p>
In this paper, we take an inspiration from human perception and explore a compositional approach for egocentric video representation.
We introduce HENASY (Hierarchical ENtities ASsemblY), which includes a spatiotemporal token grouping mechanism to explicitly assemble dynamically evolving scene entities through time and model their relationship for video representation.
By leveraging compositional structure understanding, HENASY possesses strong interpretability via visual grounding with free-form text queries.
We further explore a suite of multi-grained contrastive losses to facilitate entity-centric understandings.
This comprises three alignment types: video-narration, noun-entity, verb-entities alignments.
</p>
<p> Our method demonstrates strong interpretability in both quantitative and qualitative experiments;
while maintaining competitive performances on five downstream tasks via zero-shot transfer or as video/text representation, including video/text retrieval, action recognition, multi-choice query, natural language query, and moments query.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
</div>
</section>
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@InProceedings{khoavo2024henasy,
author = {Khoa Vo and Thinh Phan and Kashu Yamazaki and Ngan Le},
title = {HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model},
booktitle = {Thirty-eighth Conference on Neural Information Processing Systems},
year = {2024}
}</code></pre>
</div>
</section>
<footer class="footer">
<div class="container">
<div class="content has-text-centered">
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">
<img alt="Creative Commons License" style="border-width:0"
src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" />
</a>
</div>
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This website adapted from the Nerfies templates, which is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0
International License</a>.
</p>
</div>
</div>
</div>
</div>
</footer>
</body>
</html>