PageSourceSearch

https://htcv-iccv2021.github.io/

html htcv-iccv2021.github.io collected 2026-10-03 09:18:27 UTC 51,172 bytes, 935 lines download raw bytes

1<!DOCTYPE html>
2<html lang="en">
3
4<head>
5    <title>HTCV</title>
6    <meta charset="utf-8">
7    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
8
9    <!-- <link rel="icon" type="image/x-ico" href="images/106point.jpg" /> -->
10    <link rel="icon" type="image/x-ico" href="imgs/logo.png" />
11    
12
13    <link href="https://fonts.googleapis.com/css?family=B612+Mono|Cabin:400,700&display=swap" rel="stylesheet">
14
15    <link rel="stylesheet" href="fonts/icomoon/style.css">
16    <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.4.1/css/bootstrap.min.css"
17          integrity="sha384-Vkoo8x4CGsO3+Hhxv8T/Q5PaXtkKtu6ug5TOeNV6gBiFeWPGFN9MuhOf23Q9Ifjh" crossorigin="anonymous">
18
19    <link rel="stylesheet" href="css/jquery-ui.css">
20    <link rel="stylesheet" href="css/owl.carousel.min.css">
21    <link rel="stylesheet" href="css/owl.theme.default.min.css">
22    <link rel="stylesheet" href="css/owl.theme.default.min.css">
23
24    <link rel="stylesheet" href="css/jquery.fancybox.min.css">
25
26    <link rel="stylesheet" href="fonts/flaticon/font/flaticon.css">
27
28    <link rel="stylesheet" href="css/aos.css">
29    <link href="css/jquery.mb.YTPlayer.min.css" media="all" rel="stylesheet" type="text/css">
30
31    <link rel="stylesheet" href="css/style.css">
32
33
34
35    
35<script>
vendor: 533 bytes, lines 35-48
35
36        (function (i, s, o, g, r, a, m) {
37            i['GoogleAnalyticsObject'] = r;
38            i[r] = i[r] || function () {
39                (i[r].q = i[r].q || []).push(arguments)
40            }, i[r].l = 1 * new Date();
41            a = s.createElement(o),
42                m = s.getElementsByTagName(o)[0];
43            a.async = 1;
44            a.src = g;
45            m.parentNode.insertBefore(a, m)
46        })(window, document, 'script', 'https://www.google-analytics.com/analytics.js', 'ga');
47
48        ga('create', '
48UA-88572407-1
vendor: 50 bytes, lines 48-50
48', 'auto');
49        ga('send', 'pageview');
50    
50</script>
50
51</head>
52
53<body data-spy="scroll" data-target=".site-navbar-target" data-offset="300">
54
55
56
57<div class="site-wrap">
58
59    <div class="site-mobile-menu site-navbar-target">
60        <div class="site-mobile-menu-header">
61
62            <div class="site-mobile-menu-close mt-3">
63                <span class="icon-close2 js-menu-toggle"></span>
64            </div>
65        </div>
66        <div class="site-mobile-menu-body"></div>
67    </div>
68
69<!---------------------------导航栏------------------------------->
70    <div class="site-navbar py-2 js-sticky-header site-navbar-target d-none pl-0 d-lg-block" role="banner" > 
71<!-- used:site-navbar py-2-->
72        <!-- <a href="http://iccv2021.thecvf.com/"> <img class='iccv' src="imgs/iccv2021.png" width=190px height=47px style="margin-top:6px;"></a> -->
73
74
75        <!-- <a href="index.html"><img src="imgs/logo.png" width=140px height=20px style="margin-left: 200px; margin-bottom: -60px;position:inherit;"></a> ->
76
77        <div class="container">
78          <a href="http://iccv2021.thecvf.com/"><img class="iccv" src="imgs/iccv2021.png" width=190px height=47px style="margin-top:30px;position:inherit;"></a>
79            <a href="index.html"><img src="imgs/logo.png" width=140px height=20px style="margin-left: 200px; margin-bottom: -60px;position:inherit;"></a> -->
80
81            <div class="d-flex align-items-center">
82                <!-- <a href="http://iccv2021.thecvf.com/"><img class="iccv" src="imgs/iccv2021.png" width=190px height=47px style="margin-top:30px;position:inherit;"></a>
83                <a href="index.html"><img src="imgs/logo.png" width=140px height=20px style="margin-left: 200px; margin-bottom: -60px;position:inherit;"></a> -->
84
85                <div class="mr-auto">
86
87                    <!-- <a href="http://iccv2021.thecvf.com/"><img class="iccv" src="imgs/iccv2021.png" width=190px height=47px style="margin-top:30px;position:inherit;"></a>
88                    <a href="index.html"><img src="imgs/logo.png" width=140px height=20px style="margin-left: 200px; margin-bottom: -60px;position:inherit;"></a> -->
89
90                    <nav class="site-navigation position-relative text-right" role="navigation">
91                     <a href="http://iccv2021.thecvf.com/"> <img class='iccv' src="imgs/iccv2021.png" width=190px height=47px style="margin-top:-1px;"></a>
92
93                        <!-- <a href="http://iccv2021.thecvf.com/"><img class="iccv" src="imgs/iccv2021.png" width=190px height=47px style="margin-top:30px;position:inherit;"></a>
94                        <a href="index.html"><img src="imgs/logo.png" width=140px height=20px style="margin-left: 200px; margin-bottom: -60px;position:inherit;"></a> -->
95
96                        <ul class="site-menu main-menu js-clone-nav mr-auto d-none pl-0 d-lg-block">
97                            <li>
98                                <!-- static/ -->
99                                <!-- <a href="http://iccv2021.thecvf.com/"><img class="iccv" src="imgs/iccv2021.png" width=190px height=47px style="margin-top:30px;position: sticky;"></a>  -->
100                                <a href="index.html"><img src="imgs/logo.png" width=280px height=42px style="margin-left: 200px; margin-top: -3.5px; position: sticky;"></a>
101                            </li>
102                            <li>
103                                <!-- <a href="index.html" class="nav-link text-left" style="font-size:15px; font-family:'Times New Roman', Times, serif;">Home</a> -->
104                                <a href="index.html" class="nav-link text-left" style="font-size:15px; font-family:Georgia, serif;">Home</a>
105                            </li>
106                            
107                            <li>
108                                <a href="index.html#call for papers" class="nav-link text-left" style="font-size:15px; font-family:Georgia, serif">Call for papers</a>
109                            </li>
110
111                            <li>
112                                <a href="index.html#dates" class="nav-link text-left" style="font-size:15px; font-family:Georgia, serif">important dates</a>
113                            </li>
114                            
115                            <li>
116                                <a href="index.html#invited speakers" class="nav-link text-left" style="font-size:15px; font-family:Georgia, serif">invited speakers</a>
117                            </li>
118
119                            <!-- <li>
120                                    <a href="index.html#schedule" class="nav-link text-left" style="font-size:15px; font-family:'Times New Roman', Times, serif">schedule</a>
121                            </li> -->
122
123                            <li>
124                                <a href="index.html#organizers" class="nav-link text-left" style="font-size:15px; font-family:Georgia, serif">organizers</a>
125                            </li>
126
127                            <!-- <li>
128                                <a href="evaluation.html" class="nav-link text-left">Accepted papers</a>
129                            </li> -->
130
131                            <!-- <li>
132                                <a href="leaderboard.html" class="nav-link text-left">leaderboard</a>
133                            </li> -->
134
135                            <!-- <li class="nav-item dropdown">
136                                <a class="nav-link dropdown-toggle" href="challenge.html" id="navbarDropdown"
137                                   role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
138                                    Previous
139                                </a>
140                                <div class="dropdown-menu" aria-labelledby="navbarDropdown">
141                                    <a class="dropdown-item" href="https://fllc-icpr2020.github.io/home/">FLLC2_ICPR2020</a>
142                                    <a class="dropdown-item" href="https://facial-landmarks-localization-challenge.github.io/#index">FLLC1_ICME2019</a>
143                                </div> -->
144                            </li>
145                        </ul>
146                    </nav>
147
148                </div>
149
150            </div>
151        </div>
152
153    </div>
154
155</div>
156
157<div class="site-blocks-cover overlay inner-page-cover" style="background-image: url('imgs/background.png');" 
158
159
160     data-stellar-background-ratio="0.5">
161    <div class="container">
162        <div class="row align-items-center justify-content-center">
163            <div class="col-md-10 text-center" data-aos="fade-up">
164<!--                <h3> The 2nd Learning from Imperfect Data (LID) Workshop</h3>-->
165                <br>
166                <!-- style="font-size:40px" -->
167                <!-- 1<sup>st</sup> -->
168                <h1 style="font-size:46px">Human-centric Trustworthy Computer Vision</h1>
169                <h1 style="font-size:46px">From Research to Applications</h1>
170
171                <br><br><br>
172                <h4> In Conjunction with ICCV 2021</h4>
173                <h4> October 17 2021, Virtually</h4>
174
175                <!-- <br> -->
176                <!-- <a class="btn" href="https://wj.qq.com/s2/8104361/7743">
176Click to sign up</a> -->
177
178            </div>
179        </div>
180    </div>
181</div>
182
183
184
185<div class="site-section">
186    <div class="container">
187
188<!------------------------------ news  ------------------------------------------>
189
190
191<div class="col-lg-12" id="news" style="padding-top:80px;margin-top:-150px;">
192        <h4><i>News</i> !</h4>
193
194        <ul>
195            <li> 
196                <p style="height: 10px">
197                    <strong style="font-size:20px;color:red;font-family:'Times New Roman';">July 23, 2021:&nbsp;</strong>&ensp;We have postponed the submission deadline by one week.
198                </p>
199            </li>
200
201            <li>
202                <p style="height: 10px">
203                    <strong style="font-size:20px;color:red;font-family:'Times New Roman';">July 23, 2021:&nbsp;</strong>&ensp;The top ranking papers will be recommended to ACM TOMM Special Issue.
204                </p>
205            </li>
206            <li>
207                <p style="height: 10px">
208                    <strong style="font-size:20px;color:red;font-family:'Times New Roman';">June 23, 2021:&nbsp </strong>The CMT submissions website: 
209                    <a href="https://cmt3.research.microsoft.com/HTCV2021/Submission/Index">https://cmt3.research.microsoft.com/HTCV2021</a>
210                </p>
211            </li>
212
213            <li>
214                <p style="height: 10px">
215                    <strong style="font-size:20px;color:red;font-family:'Times New Roman';">June 15, 2021:&nbsp </strong>The workshop date is presented.
216                </p>
217            </li>
218            <li>
219                <p style="height: 10px">
220                    <strong style="font-size:20px;color:red;font-family:'Times New Roman';"> May 10, 2021:&nbsp;&thinsp;&thinsp;</strong>The website is coming. Call for papers.
221                </p>
222                <!-- <p style="height: 10px">
223                <strong style="font-size:16px;color:red">Apr. 2, 2021: &emsp;</strong>
224                    The grand challenge track is open. Click <a href="https://cmt3.research.microsoft.com/ICMEW2021/Track/10/Submission/Create">here</a> to submit your paper.
225                    The deadline is April 7, 2021 [11:59 pm PST]
226                </p>
227
228                <p style="height: 10px">
229                <strong style="font-size:16px;color:red">Apr. 1, 2021: &emsp;</strong>
230                    The test phase begins. Please submit the model and paper following the <a href="evaluation.html#finalSubmission">submission guideline</a>.
231                </p>
232
233                <p style="height: 10px">
234                <strong style="font-size:16px;color:red">Mar. 4, 2021: &emsp;</strong>
235                    The 3rd Grand Challenge of 106-Point Facial Landmark Localization is opening now. Welcome to participate!
236                </p> -->
237
238            </li>
239        </ul>
240</div>
241<br><br><br><br>
242
243<!------------------------  overview  ----------------------->
244            <div class="col-lg-12">
245                <div class="section-title">
246                    <h2>Overview</h2>
247                    <br>
248                    <h4 style="font-size: 21px;"><i>How to define, pursue and evaluate trustworthy technologies for human-centric computer vision tasks?</i></h4>
249                </div>
250                <div class="trend-entry d-flex">
251                    <div class="trend-contents">
252                        <p>
253
254                            &emsp;&emsp; With the rapid technical progress in computer vision and the spread of vision-based applications over the past several years, the human-centric computer vision technologies, such as person re-identification, face recognition, action recognition, <i>etc</i>., are quickly becoming an essential enabler for many fields. Although, it brings great value to individuals and society, it is also encounters a variety of novel ethical, legal, social, and security challenges. Particularly, in recent years, the multiple multimedia sensing technologies as well as the large-scale computing and storage infrastru
254ctures are stimulating at a rapid velocity a wide variety of human-centric big data, which provides rich knowledge to help the development of these applications. Meanwhile, such data contains a large amount of personal private information, bringing concerns about the safety and trustworthiness of computer vision technologies. Consequently, trustworthy computer vision has been attracting an increasing attention from academia and industry. It focuses on human-oriented, fair, robust, interpretable, and responsible vision technologies, and is also at the core of the next-generation artificial intelligence (AI). The goal of this workshop is to: <font face="Times New Roman">1</font>) bring together the state-of-the-art research on human-centric vision analysis for trustworthy AI; <font face="Times New Roman">2</font>) call for a coordinated effort to understand the opportunities and challenges emerging in human-centric trustworthy vision technologies; <font face="Times New Roman">3</font>) explore the fairness, robustness, interpretability and accountability oriented to human; <font face="Times New Roman">4</font>) showcase innovative methodologies and ideas; <font face="Times New Roman">5</font>) introduce interesting real-world human-oriented trustworthy systems and applications; <font face="Times New Roman">6</font>) give insight into industry’s practice of trustworthy AI for human-centric vision and discuss future directions. We solicit original contributions in all fields of trustworthy human analysis to help us better understand the nature of vision algorithms for real-world applications. We hope the workshop offer a timely collection of research updates to benefit the researchers and practitioners working in the broad computer vision, pattern recognition, and trustworthy AI communities.
255                            <br>
256                        </p>
257                    </div>
258                </div>
259            </div>
260<!------------------------  Call for papers  --------------------->
261<div class="col-lg-12" id="call for papers" style="padding-top:80px;margin-top:-80px;">
262        <div class="section-title">
263
264            <br><br><br>
265            <h2>Call for papers</h2>
266        </div>
267
268        <div class="trend-entry d-flex">
269                <div class="trend-contents">
270                    <p style="margin: auto;">
271                        &emsp; &emsp;We invite submissions for ICCV <font face='Times New Roman'>2021</font> Workshop, Human-centric Trustworthy Computer Vision: From Research to Applications (HTCV<font face="Times New Roman">2021</font>), that brings researchers together to discuss human-oriented, fair, robust, interpretable, and responsible technologies for human-centric vision analysis. We solicit original research and survey papers from <font face="Times New Roman" size=5px>5</font> to <font face="Times New Roman" size=5px>8</font> pages (excluding references and appendices). Each submitted paper will be double-blind peer reviewed by at least three reviewers. All accepted papers will be presented as either oral or poster presentations, with a best paper award, and appear in the <a href="https://openaccess.thecvf.com/menu" style="font-family: 'Times New Roman', Times, serif; font-size:21px;">CVF open access archive.</a>
272                        Papers submission is through <a href="https://cmt3.research.microsoft.com/HTCV2021/Submission/Index" style="font-family: 'Times New Roman', Times, serif; font-size:21px;">HTCV<font face="Times New Roman">2021</font> CMT</a> and must follow the same policies and submission guidelines described in <a href="http://iccv2021.thecvf.com/node/4#submission-guidelines" style="font-family: 'Times New Roman', Times, serif; font-size:21px;">ICCV'<font face="Times New Roman">21</font> Author Guidelines</a>. Papers that violates the anonymity, do not use the ICCV submission template or have more than <font face="Times New Roman">8</font> pages (excluding references and appendices) will be rejected without review. In submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted to another workshop or conference during the review period.
273                        <br>
274                        &emsp;&emsp;The scope of this workshop includes, but is not limited to, the following topics:
275                    </p>
276                <ul class="set_ul" style="margin-bottom: 0px; margin-left:20px; display: inline-block;">
277                        <li>
278                            Adversarial attack and defense in face recognition and person re-identification
279                        </li>
280                        <li>
281                                Explainable face and body analysis, generation and edition
282                        </li>
283                        <li>
284                                Robust human body and face representation learning
285                        </li>
286                        <li>
287                                Face anti-spoofing and deep-fake detection
288                        </li>
289                        <li>
290                                Robust gait and action recognition
291                        </li>
292                        <li>
293                                Secured federated learning
294                        </li>
295                        <li>
296                                Robustness against evolving attacks in computer vision
297                        </li>
298                        <li>
299                                Fairness analysis for data and models of face or human recognition
300                        </li>
301                        <li>
302                                Trustworthy algorithms, frameworks, and tools for Human-centric Trustworthy Computer Vision
303                        </li>
304                    </ul>
305                    <p>
306                        &emsp;&emsp;The top ranking papers will be recommended to ACM TOMM Special Issue.
307                    </p>
308                </div>
309            </div>
310    </div>
311
312    
313<!------------------------  import dates  --------------------->
314
315<div class="col-lg-12" id="dates" style="padding-top:80px;margin-top:-80px;">
316        <div class="section-title">
317
318            <br><br><br>
319            <h2>Important Dates</h2>
320        </div>
321        <div class="trend-entry d-flex">
322            <table class="table table-striped" style="border-bottom:2px solid #C4C4C4;border-top:2px solid #C4C4C4;width:60%; line-height: 12px;" align="center">
323                <thead>
324                <!-- <tr style="background-color:#BFEFFF;"> -->
325                <tr>
326                    <th scope="col" style="text-align: center;"> Description</th>
327                    <th scope="col" style="text-align: center;"> Date (Pacific Time)</th>
328                </tr>
329                </thead>
330                <tbody>
331                <!-- <tr style="background-color:#8BB1D8;"> -->
332                <tr style="background-color:#B6CEE7;">    
333                    <td style="color: rgb(230, 33, 33); font-weight: bold;">Submission Deadline</td>
334                    <td style="color: rgb(230, 33, 33); font-weight: bold;">August 8, 2021 (11:59PM)</td>
335                </tr>
336                
337                <tr>
338                    <td>Decisions to Authors</td>
339                    <td> August 14, 2021 (11:59PM)</td>
340                </tr>
341
342                <!-- <tr style="background-color:#8BB1D8;"> -->
343                <tr style="background-color:#B6CEE7;">
344                    <td>Camera-ready Due</td>
345                    <td> August 18, 2021 (11:59PM)</td>
346                </tr>
347
348                <tr>
349                    <td>Workshop Date</td>
350                    <td> October 17, 2021 (Afternoon)</td>
351                </tr>
352
353                </tbody>
354                
355            </table> 
356        </div>
357        
358
359    </div>
360
361<!------------------------  Agenda  --------------------->
362
363<div class="col-lg-12" id="dates" style="padding-top:80px;margin-top:-80px;">
364        <div class="section-title">
365            <br><br><br>
366            <h2>Agenda</h2>
367        </div>
368        <div class="trend-entry d-flex">
369
370            <table class="table table-striped" style="border-bottom:2px solid #C4C4C4;border-top:2px solid #C4C4C4;width:100%; line-height: 20px;" align="center">
371            <!-- <table class="table table-striped" style="border-bottom:2px solid #C4C4C4;border-top:2px solid #C4C4C4;width:100%; line-height: 20px;" text-align="left"> -->
372                <thead>
373                <tr>
374                    <th scope="col" style="text-align: left;"> &nbsp;&thinsp;Time (EDT)</th>
375                    <th scope="col" style="text-align: left;"> Session</th>
376                    <th scope="col" style="text-align: left;"> Speaker</th>
377                </tr>
378                </thead>
379                <tbody>
380                <!-- <tr style="background-color:#8BB1D8;"> -->
381                <tr style="background-color:#B6CEE7;">    
382                   <td>1:00 PM-1:10 PM</td>
383                    <td style="text-align: left;">Opening</td>
384                    <td style="text-align: left;">Host</td>
385                </tr>
386                
387                <tr>
388                    <td>1:10 PM-1:55 PM</td>
389                    <td style="text-align: left;">Invited speak 1</td>
390                    <td style="text-align: left;">"Physical and digital fake face detection"&nbsp;&nbsp;Zhen Lei</td>
391                </tr>
392
393                <tr style="background-color:#B6CEE7;">
394                    <td>1:55 PM-2:40 PM</td>
395                    <td style="text-align: left;">Invited speak 2</td>
396                    <td style="text-align: left;">"Probabilistic Modeling for Human Mesh Recovery"&nbsp;&nbsp;Georgios Pavlakos</td>
397                </tr>
398
399                <tr>
400                    <td>2:40 PM-3:25 PM</td>
401                    <td style="text-align: left;">Invited speak 3</td>
402                    <td style="text-align: left;">"Pitfalls on the Road to Trust in Computer Vision"&nbsp;&nbsp;Karthik Nandakumar</td>                    
403                </tr>
404
405                <!-- <tr style="background-color:#8BB1D8;"> -->
406                <tr style="background-color:#B6CEE7;">    
407                   <td>3:25 PM-4:10 PM</td>
408                    <td style="text-align: left;">Invited speak 4</td>
409                    <td style="text-align: left;">"Challenges of Creating Affective Computational Tools for<br>Behavioral and Clinical Sciences"&nbsp;&nbsp;Albert Ali Salah</td>  
410                </tr>
411                
412                <tr>
413                    <td>4:10 PM-4:25 PM</td>
414                    <td style="text-align: left;">Oral presentation 1</td>
415                    <td style="text-align: left;">“Multi-Perspective Features Learning for Face Anti-Spoofing”</td>                     
416                </tr>
417
418                <tr style="background-color:#B6CEE7;">
419                    <td>4:25 PM-4:40 PM</td>
420                    <td style="text-align: left;">Oral presentation 2</td>
421                    <td style="text-align: left;">“Rethinking Common Assumptions to Mitigate Racial Bias in<br>Face Recognition Datasets”</td>
422                </tr>
423
424                <tr>
425                    <td>4:40 PM-4:55 PM</td>
426                    <td style="text-align: left;">Oral presentation 3</td>
427                    <td style="text-align: left;">“Transformer Meets Part Model: Adaptive Part Division for<br>Person Re-Identification”</td>
428                </tr>
429
430                <!-- <tr style="background-color:#8BB1D8;"> -->
431                <tr style="background-color:#B6CEE7;">    
432                   <td>4:55 PM-5:10 PM</td>
433                    <td style="text-align: left;">Oral presentation 4</td>
434                    <td style="text-align: left;">“SVEA: A Small-scale Benchmark for Validating the Usability of<br>Post-hoc Explainable AI Solutions in Image and Signal Recognition”</td>
435                </tr>
436                
437                <tr>
438                    <td>5:10 PM-5:20 PM</td>
439                    <td style="text-align: left;">Best Paper Announcement</td>
440                    <td style="text-align: left;">Host</td>
441                </tr>
442
443                <tr style="background-color:#B6CEE7;">
444                    <td>5:20 PM-5:55 PM</td>
445                    <td style="text-align: left;">Poster presentation</td>
446                    <td style="text-align: left;">Pre-recorded videos</td>
447                </tr>
448
449                <tr>
450                    <td>5:55 PM-6:00 PM</td>
451                    <td style="text-align: left;">Ending</td>
452                    <td style="text-align: left;">Host</td>
453                </tr>                
454
455                </tbody>
456                
457            </table> 
458        </div>
459        
460
461    </div>
462
463
464
465
466
467<!------------------------------ Invited speakers  ------------------------------------------>
468
469<div class="col-lg-12" id="invited speakers" style="padding-top:80px;margin-top:-80px;">
470    <div class="section-title">
471
472        <br><br><br>
473        <h2>Invited speakers</h2>
474        <br><br>
475     
476        <div align="left">
477
478    
479            <div class="instructor_fina" style="float: left; display: inline;
479 margin-top: 1px;">
480                <a href="http://www.cbsr.ia.ac.cn/users/zlei/">
481                    <div class="instructorphoto"><img src="imgs/ZhenLei.png"></div>
482                </a>
483                <div style="font-family:Helvetica, sans-serif; font-size: 17px;display: inline-block;">Prof.</div>
484                <a href="http://www.cbsr.ia.ac.cn/users/zlei/">
485                    <div style="font-size: 17px;display: inline-block;">&thinsp;Zhen Lei</div>
486                </a>
487                <div style="font-family:Helvetica, sans-serif; font-size: 17px">NLPR, CASIA, China</div>
488            </div>
489
490    		 <div style="font-family:Times New Roman, sans-serif; font-size: 20px; display: inline-block; width: 78%;text-align: justify;">
491             <strong>Title:</strong> Physical and digital fake face detection
492            <br>
493             <strong>Abstract:</strong> Physical and digital face attack are two common face attacks in reality. In many applications, we have to detect these two attacks to assure the security of the system. Physical fake face detection, also known as presentation attack detection or face anti-spoofing, is used to judge the genuine/fake face in front of a camera. The digital fake face detection is used to detect face forgery in the internet. In the first part, I will report recent progress on how to learn the optimal supervision signal so that the model can be better learned. In the second part, I’ll introduce a 3D decomposition based digital fake face detection method and show its effectiveness in face forgery detection task.
494            </div>
495
496            <br>
497            <br>
498            <br>
499            <br>
500
501            <!-- <div class="instructor_fina" style="float: left; display: inline;margin-top: 100px;"> -->
502            <div class="instructor_fina" style="float: left; display: inline; margin-top: 4px;">
503
504                <a href="https://geopavlakos.github.io/">
505                    <div class="instructorphoto"><img src="imgs/Georgios Pavlakos.png"></div>
506                </a>
507                <div style="font-family:Helvetica, sans-serif; font-size: 17px; display: inline-block;">Dr.</div>
508                <a href="https://geopavlakos.github.io/">
509                    <div style="font-size: 16px; display: inline-block;">&thinsp;Georgios Pavlakos</div>
510                </a>
511                <div style="font-family:Helvetica, sans-serif;font-size: 17px">UC Berkeley, USA</div>
512            </div>
513
514
515            <div style="font-family:Times New Roman, sans-serif; font-size: 20px; display: inline-block; width: 78%;text-align: justify;">
516             <strong>Title:</strong> Probabilistic Modeling for Human Mesh Recovery
517            <br>
518             <strong>Abstract:</strong> Reconstructing humans in 3D from a single image is an inherently ambiguous problem since multiple 3D poses can lead to the same reprojection. However, most related works only return one pose estimate for each input image. This fails to capture the multimodal aspect of the problem and results in systems with potentially non-interpretable or non-trustworthy behavior. In this talk, I will discuss our recent work that tries to embrace this multimodality and recasts the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery.
519            </div>
520
521            
522            <br>
523            <br>
524            <br>
525            <br>
526
527<!--             <div class="instructor_fina" style="float: left; display: inline;margin-top:100px;"> -->
528	            <div class="instructor_fina" style="float: left; display: inline;margin-top: -10px;">
529                <a href="https://www.sprintai.org/nkarthik">
530                    <div class="instructorphoto"><img src="imgs/KarthikNandakumar.png"></div>
531                </a>
532                <div style="font-family:Helvetica, sans-serif; font-size: 17px; display: inline-block;">Prof.</div>
533                <a href="https://www.sprintai.org/nkarthik">
534                    <div style="font-size: 16px; display: inline-block;">&thinsp;Karthik Nandakumar</div>
535                </a>
536                <div style="font-family:Helvetica, sans-serif;font-size: 17px">MUZUAI, Abu Dhabi</div>
537            </div>
538    		 <div style="font-family:Times New Roman, sans-serif; font-size: 20px; display: inline-block; width: 78%;text-align: justify;">
539             <strong>Title:</strong> Pitfalls on the Road to Trust in Computer Vision
540            <br>
541             <strong>Abstract:</strong>
541 Computer vision systems have had a profound positive impact on human lives in applications ranging from smartphone access control to self-driving vehicles and automated medical image diagnosis. While an exponential increase in data availability, combined with algorithmic advancements in machine learning such as deep neural network models and rapid improvements in computational capabilities have powered the growth in computer vision over the past two decades, the field is at a crossroad now due to a lack of trust among human users. Numerous concerns over the trustworthiness of computer vision systems have been raised by various stakeholders and these include: (i) safety and robustness of computer vision algorithms against adversarial attacks, (ii) potential for causing discriminatory harm against specific population groups, (iii) breach of data privacy and confidentiality, (iv) inability to provide explainable decisions, and (v) overall lack of accountability and auditability. In this talk, we will first review the above pitfalls on the road to trust and the interactions among them. Next, we discuss solutions that have been proposed in the literature to address these concerns. Finally, we identify possible research directions that can facilitate the safe navigation of these pitfalls and take us to the eventual destination of developing computer vision systems that can be trusted by human users.
542            </div>
543
544
545    		<br>
546    		<br>
547    		<br>
548            <br>
549
550            <!-- <div class="instructor_fina" style="float: left; display: inline;margin-top:40px"> -->
551            <div class="instructor_fina" style="float: left; display: inline;margin-top: 7px;">
552
553                <a href="https://webspace.science.uu.nl/~salah006/">
554                    <div class="instructorphoto"><img src="imgs/AlbertAliSalah.png"></div>
555                </a>
556                <div style="font-family:Helvetica, sans-serif; font-size: 17px;display: inline-block;">Prof.</div>
557                <a href="https://webspace.science.uu.nl/~salah006/">
558                    <div style="font-size: 17px;display: inline-block;">&thinsp;Albert Ali Salah</div>
559                </a>
560                <div style="font-family:Helvetica, sans-serif; font-size: 17px">Utrecht University, Netherlands</div>
561            </div>
562
563              <div style="font-family:Times New Roman, sans-serif; font-size: 20px; display: inline-block; width: 78%;text-align: justify;">
564             <strong>Title:</strong> Challenges of Creating Affective Computational Tools for Behavioral and Clinical Sciences
565            <br>
566             <strong>Abstract:</strong> Automatic analysis of human affective and social signals brought computer science closer to social sciences and, in particular, enabled collaborations between computer scientists and behavioral scientists.
567			In this talk, I highlight the main research areas in this burgeoning interdisciplinary area, and provide an overview of the opportunities and challenges. Drawing on examples from our recent research, such as automatic analysis of interactive play therapy sessions with children, and diagnosis of bipolar disorder from multimodal cues, as well as relying on recent examples from the growing literature, I will explore the potential of human-AI collaboration, where AI systems do not replace, but support monitoring and human decision making in behavioral and clinical sciences. I conclude with some controversial issues that may point out what "trustworthy AI" would mean for the technologies developed in this domain.
568
569            </div>
570
571
572
573    </div>
574
575</div>
576
577</div>
578
579
580
581                       
582<!----------------------------  organizers  ---------------------------------------->
583<div class="col-lg-12" id="organizers" style="padding-top:80px;margin-top:-80px;">
584
585    <!----------------------------  organizer  ---------------------------------------->
586        <div class="section-title">
587            <br><br><br>
588            <h2>organizers</h2>
589        </div>
590    
591        <div align="center">
592                <div class="instructor_mine">
593                    <a href="http://www.cs.ucf.edu/~liujg/">
594                        <div class="instructorphoto"><img src="imgs/JinggenLiu.png"></div>
595                        <div style="font-size: 18px">Jingen Liu</div>
596                    </a>
597                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">JD AI Research, USA
598                    </div>
599                </div>
600        
601                <div class="instructor_mine">
602                    <a href="https://www.sifeiliu.net/">
603                        <div class="instructorphoto"><img src="imgs/SifeiLiu.png"></div>
604                        <div style="font-size: 18px">Sifei Liu</div>
605                    </a>
606                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">Nvidia Research, USA</div>
607                </div>
608
609                <div class="instructor_mine">
610                    <a href="http://drliuwu.com/english.html">
611                        <div class="instructorphoto"><img src="imgs/WuLiu.png"></div>
612                        <div style="font-size: 18px">Wu Liu</div>
613                    </a>
614                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">JD AI Research, China</div>
615                </div>
616                    
617                <div class="instructor_mine">
618                    <a href="http://disi.unitn.it/~sebe/">
619                        <div class="instructorphoto"><img src="imgs/NicuSebe.png"></div>
620                        <div style="font-size: 18px">Nicu Sebe</div>
621                    </a>
622                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">UniTN, Italy</div>
623                </div>
624        
625                <div class="instructor_mine">
626                    <a href="https://sites.google.com/view/hailin-shi">
627                        <div class="instructorphoto"><img src="imgs/HailinShi.png"></div>
628                        <div style="font-size: 18px">Hailin Shi</div>
629                    </a>
630                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">JD AI Research, China</div>
631                </div>
632        </div>
633
634        <!----------------------------  Committe Chairs  ---------------------------------------->
635        <div class="section-title">
636            <br><br><br>
637            <h2>Committee Chairs</h2>
638        </div>
639 
640        <div align="center">
641
642            <div class="instructor">
643                <a href="https://scholar.google.com/citations?user=vhM_c14AAAAJ&hl=zh-CN">
644                    <div class="instructorphoto">
645                            <img src="imgs/QianBao.png">
646                    </div>
647                    <div style="font-size: 18px">Qian Bao</div>
648                </a>
649                <div style="font-family:Helvetica, sans-serif;font-size: 18px">JD AI Research, China</div>
650            </div>
651
652                <div class="instructor">
653                    <a href="https://aberhu.github.io/">
654                        <div class="instructorphoto">
655                                <img src="imgs/YiboHu.png">
656                        </div>
657                        <div style="font-size: 18px">Yibo Hu</div>
658                    </a>
659                    <div style="font-family:Helvetica, sans-serif;font-size: 18px">JD AI Research, China</div>
660                </div>
661                
662                <div class="instructor" style="width:240px;">
663                    <a href="https://www.aminer.cn/profile/junbo-guo/53f4652cdabfaeecd6a08551">
664                        <div class="instructorphoto">
665                                <img src="imgs/guojunbo.png">
666                        </div>
667                        <div style="font-size: 18px">Junbo Guo</div>
668                    </a>
669                    <div style="font-family:Helvetica, sans-serif;font-size: 18px;">People's Daily Online, China</div>
670                </div>
671        
672
673        </div>
674    </div>
675        <!----------------------------PC members---------------------------------------->
676        
677        <div class="section-title">
678                <br><br><br>
679                &emsp;&emsp;&emsp;&emsp;
680                <h2>PC members</h2>
681                &emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;
682                <h2>Advisory board</h2>
683        </div>
684
685        
686        <div class="set_ul"  style="font-family: Georgia, serif, Baskerville, monospace; font-size: 20px; margin-left: 180px; width: 35%; display: inline-block;">
687            <ul>
688                <li>
689                        <a href="https://research-repository.uwa.edu.au/e
689n/persons/naveed-akhtar">Naveed Akhtar</a> (<font face=Helvetica>UWA, Australia)</font>
690                        <!-- <a href="https://research-repository.uwa.edu.au/en/persons/naveed-akhtar">Naveed Akhtar</a> -->
691                </li>
692                
693                <li>
694                    <a href="https://sites.google.com/view/drjinghuang">Jing Huang</a> (<font face=Helvetica>JD AI Research, USA</font>)
695                </li>
696
697                <li>
698                    <div style="font-family: Helvetica;">Haoran Jiang (SHU, China)</div>
699                    <!-- Can Yang -->
700               </li>
701               
702                <li>
703                        <a href="https://sites.google.com/site/pingliu264/">Ping Liu</a> (<font face=Helvetica>A*STAR, Singapore</font>)
704                        <!-- <a href="https://sites.google.com/site/pingliu264/">Ping Liu</a> -->
705
706                </li>
707
708               <li>
709                <a href="http://prclibo.github.io/">Bo Li</a> (<font face=Helvetica>JD AI Research, China</font>)
710                <!-- <a href="http://prclibo.github.io/">Bo Li</a> -->
711                </li>
712
713                <li>
714                    <!-- <a href="https://www.facebook.com/public/Zheng-Sou/">Zheng Sou</a> (Facebook AI, USA) -->
715                    <div style="font-family: Helvetica;">Zheng Sou (Facebook AI, USA)</div>
716    
717                   </li>
718                
719                <li>
720                    <a href="http://wuziyan.com/">Ziyan Wu</a> (<font face=Helvetica>UII, USA</font>)
721                    <!-- <a href="http://wuziyan.com/">Ziyan Wu</a> -->
722                </li>
723                
724                <li>
725                    <a href="https://www.yf.io/">Fisher Yu</a> (<font face=Helvetica>ETH Zürich, Switzerland</font>)
726                    <!-- <a href="https://www.yf.io/">Fisher Yu</a> -->
727               </li>
728
729
730               <li>
731                <div style="font-family: Helvetica;">Can Yang (JD AI Research, China)</div>
732                  <!-- Can Yang -->
733               </li>
734
735               <li>
736                <a href="https://scie.shu.edu.cn/Prof/zengdan.htm">Dan Zeng</a> (<font face=Helvetica>SHU, China</font>)
737                <!-- <a href="https://sites.google.com/site/pingliu264/">Ping Liu</a> -->
738               </li>
739
740            </ul>
741            </div>
742
743            <div class="set_ul"  style="font-family: Georgia, serif, Baskerville, monospace; font-size: 20px;margin-left: -20px; width: 40%; display:block; float: right;">
744            <ul>
745                <li>
746                    <a href="https://ps.is.mpg.de/~black">Michael Black</a> (<font face=Helvetica>MPI-IS, Germany</font>)
747                </li>
748
749                <li>
750                    <a href="https://www.cs.umd.edu/people/lsdavis">Larry Davis</a> (<font face=Helvetica>UM, USA</font>)                   
751                </li>
752
753                <li>
754                    <a href="https://www.cse.msu.edu/~liuxm/index2.html">Xiaoming Liu</a> (<font face=Helvetica>MSU, USA</font>)
755                </li>
756                    
757                <li>
758                    <a href="https://taomei.me/">Tao Mei</a> (<font face=Helvetica>JD AI Research, China</font>)
759                </li>
760
761                <li>
762                    <a href="http://www.cs.cmu.edu/~yaser/">Yaser Sheikh</a> (<font face=Helvetica>CMU, USA</font>)
763                </li>
764            </ul>
765
766
767
768<!--     
769            <div class="section-title">
770                    <br><br><br>
771                    <h2>Advisors</h2>
772            </div>
773
774            <ul class="set_ul" style="margin-left: 300px;">
775                    <li>
776                        <div style="font-family: Helvetica;">Larry Davis (UM, USA)</div>
777                    </li>
778
779                    <li>
780                        <div style="font-family: Helvetica;">Micheal Black (MPI-IS, Germany)</div> 
781                    </li>
782
783                    <li>
784                        <div style="font-family: Helvetica;">Yaser Sheikh (CMU, USA)</div>
785                    </li>
786
787                    <li>
788                        <div style="font-family: Helvetica;">Xiaoming Liu (MSU, USA)</div>
789                    </li>
790                        
791                    <li>
792                        <div style="font-family: Helvetica;">Tao Mei (JD AI Research, China)</div>
793                    </li>
794                </ul> -->
795
796        <!-- <div align="center">
797
798                <div class="instructor">
799                    <a href="https://research-repository.uwa.edu.au/e
799n/persons/naveed-akhtar">
800                        <div class="instructorphoto">
801                                <img src="imgs/NaveedAkhtar.png">
802                        </div>
803                        <div>Naveed Akhtar</div>
804                    </a>
805                    <div>University of Western Australia, Australia</div>
806                </div>
807        
808                <div class="instructor">
809                    <a href="https://sites.google.com/site/pingliu264/">
810                        <div class="instructorphoto">
811                                <img src="imgs/PingLiu.png">
812                        </div>
813                        <div>Ping Liu</div>
814                    </a>
815                    <div>A*STAR, Singapore</div>
816                </div>
817
818                <div class="instructor">
819                    <a href="https://www.facebook.com/public/Zheng-Sou/">
820                        <div class="instructorphoto">
821                                <img src="imgs/YiboHu.png">
822                        </div>
823                        <div>Zheng Sou</div>
824                    </a>
825                    <div>Facebook AI, USA</div>
826                </div>
827
828                <div class="instructor">
829                    <a href="http://wuziyan.com/">
830                        <div class="instructorphoto">
831                                <img src="imgs/ZiyanWu.png">
832                        </div>
833                        <div>Ziyan Wu</div>
834                    </a>
835                    <div>United Imaging Intelligence, USA</div>
836                </div>
837
838                <div class="instructor">
839                    <a href="https://www.yf.io/">
840                        <div class="instructorphoto">
841                                <img src="imgs/FisherYu.png">
842                        </div>
843                        <div>Fisher Yu</div>
844                    </a>
845                    <div>ETH Z¨urich, Switzerland</div>
846                </div>
847        
848            </div>         -->
849    </div>
850
851
852
853<!------------------------------email-------------------------------->
854<br><br>
855 <p style="margin-top:30px;margin-bottom: 60px; text-align: center; font-family: 'Times New Roman', Times, serif; font-size: 24px;">If you have any questions, feel free to contact &lt [email protected] &gt </p>
856
857<!------------------------------ sponsor  ------------------------------------------>
858<div class="section-title">
859    <br>
860    <!-- <img src="images/logo.png" class="icon-align-center"> -->
861    <img src="imgs/JD AI Research.png" class="icon-align-center" style="margin-right: 60px;">
862    <img src="imgs/Nvidia-logo.jpg" class="icon-align-center" style="margin-right: 60px;">
863    <img src="imgs/University of Trento.png" class="icon-align-center"style="margin-right: 40px;">
864    <img src="imgs/People's Daily Online.png" class="icon-align-center">
865
866
867</div>
868<p style="margin-top:5px;margin-bottom: -30px; text-align: center; font-family: 'Times New Roman', Times, serif; font-size: 19px;">The workshop is organized in collaboration with JD AI Research, NVIDIA Research, University of Trento <br>and State Key Laboratory of Communication Content Cognition, People's Daily Online. </p>
869<!-------------------------------   boarder  ---------------------------------------->
870        <div class="col-lg-12">
871            <div style="display:inline-block;width:500px;">
872                
872<script type="text/javascript" src="//rc.rev
873            olvermaps.com/0/0/7.js?i=2hlmeh3dic1&amp;m=0&amp;c=ff0000&amp;cr1=ffffff&amp;br=19&amp;sx=0"
874                        async="async"></script>
874
875            </div>
876        </div>
877    </div>
878</div>
879</div>
880<!-- END section -->
881
882
883<div class="footer">
884    <div class="container">
885        <div class="row">
886            <div class="col-12">
887                <div class="copyright">
888                    <p>
889                        <!-- Link back to Colorlib can't be removed. Template is licensed under CC BY 3.0. -->
890                        Copyright &copy;
890<script>document.write(new Date().getFullYear());</script>
890
891                        All rights reserved | Powered by <a
892                            href="https://colorlib.com" target="_blank">Colorlib</a>
893                        <!-- Link back to Colorlib can't be removed. Template is licensed under CC BY 3.0. -->
894                    </p>
895                </div>
896            </div>
897        </div>
898    </div>
899</div>
900
901
902</div>
903<!-- .site-wrap -->
904
905
906<!-- loader -->
907<div id="loader" class="show fullscreen">
908    <svg class="circular" width="48px" height="48px">
909        <circle class="path-bg" cx="24" cy="24" r="22" fill="none" stroke-width="4" stroke="#eeeeee"/>
910        <circle class="path" cx="24" cy="24" r="22" fill="none" stroke-width="4" stroke-miterlimit="10"
911                stroke="#ff5e15"/>
912    </svg>
913</div>
914
915<script src="js/jquery-3.3.1.min.js"></script>
vendor: 2 bytes, line 915
915
916<script src="js/jquery-migrate-3.0.1.min.js"></script>
vendor: 2 bytes, line 916
916
917<script src="js/jquery-ui.js"></script>
vendor: 2 bytes, line 917
917
918<script src="js/popper.min.js"></script>
vendor: 2 bytes, line 918
918
919<script src="js/bootstrap.min.js"></script>
vendor: 2 bytes, line 919
919
920<script src="js/owl.carousel.min.js"></script>
vendor: 2 bytes, line 920
920
921<script src="js/jquery.stellar.min.js"></script>
vendor: 2 bytes, line 921
921
922<script src="js/jquery.countdown.min.js"></script>
vendor: 2 bytes, line 922
922
923<script src="js/bootstrap-datepicker.min.js"></script>
vendor: 2 bytes, line 923
923
924<script src="js/jquery.easing.1.3.js"></script>
vendor: 2 bytes, line 924
924
925<script src="js/aos.js"></script>
vendor: 2 bytes, line 925
925
926<script src="js/jquery.fancybox.min.js"></script>
vendor: 2 bytes, line 926
926
927<script src="js/jquery.sticky.js"></script>
vendor: 2 bytes, line 927
927
928<script src="js/jquery.mb.YTPlayer.min.js"></script>
928
929
930
931<script src="js/main.js"></script>
931
932
933</body>
934
935</html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.