{"id":2661,"date":"2022-07-18T10:11:15","date_gmt":"2022-07-18T17:11:15","guid":{"rendered":"https:\/\/www.icpr2022.com\/?page_id=2661"},"modified":"2022-08-21T03:06:38","modified_gmt":"2022-08-21T10:06:38","slug":"keynote-abstracts","status":"publish","type":"page","link":"https:\/\/www.icpr2022.com\/keynote-abstracts\/","title":{"rendered":"Keynote Abstracts"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"2661\" class=\"elementor elementor-2661\" data-elementor-post-type=\"page\">\n\t\t\t\t\t\t\t\t\t<section data-kenburns=\"{&quot;fx&quot;:&quot;fade&quot;,&quot;speed&quot;:1500,&quot;fade&quot;:1900,&quot;slides&quot;:[{&quot;_id&quot;:&quot;bfcdc4c&quot;,&quot;premium_kenburns_images&quot;:{&quot;url&quot;:&quot;https:\\\/\\\/www.icpr2022.com\\\/wp-content\\\/uploads\\\/2021\\\/07\\\/paralaxBackground.png&quot;,&quot;id&quot;:29,&quot;size&quot;:&quot;&quot;,&quot;alt&quot;:&quot;&quot;,&quot;source&quot;:&quot;library&quot;},&quot;premium_kenburns_dir&quot;:&quot;tc&quot;,&quot;premium_kenburns_image_fit&quot;:&quot;pa-fill&quot;,&quot;premium_kenburns_zoom_dir&quot;:&quot;in&quot;}],&quot;infinite&quot;:&quot;&quot;}\" class=\"elementor-section elementor-top-section elementor-element elementor-element-4962740 premium-kenburns-yes elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"4962740\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-42657d5\" data-id=\"42657d5\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-14fdb06 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"14fdb06\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-7ed1a7c elementor-invisible\" data-id=\"7ed1a7c\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-eabe100 elementor-widget elementor-widget-image\" data-id=\"eabe100\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 17-10-2023 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"265\" height=\"300\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/c.v.jawahar-265x300.jpg\" class=\"attachment-medium size-medium wp-image-1370\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/c.v.jawahar-265x300.jpg 265w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/c.v.jawahar.jpg 300w\" sizes=\"(max-width: 265px) 100vw, 265px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5677962 elementor-widget elementor-widget-text-editor\" data-id=\"5677962\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 17-10-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<p><strong>C. V. Jawahar<br \/><\/strong><em>Professor at International Institute of Information Technology (IIIT), India.\u00a0<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-317efc3 elementor-invisible\" data-id=\"317efc3\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-3513fff elementor-widget elementor-widget-heading\" data-id=\"3513fff\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 17-10-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h4 class=\"elementor-heading-title elementor-size-default\">Towards Multimodality in Perception Tasks<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-db2c071 elementor-widget elementor-widget-text-editor\" data-id=\"db2c071\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: A number of perception tasks (especially in vision,<br \/>language and speech) are solved today with very high accuracy using<br \/>data-driven techniques. We are now seeing the emergence of a set<br \/>of more natural tasks that are inherently multimodal (eg. VQA).<br \/>They are closer to the way we interact with the world around us or<br \/>perceive our sensory inputs. As a result, today&#8217;s AI systems<br \/>(aka. deep learning architectures) are also becoming increasingly <br \/>capable of jointly processing inputs from different modalities.<br \/>In fact, they enjoy processing multiple modalities (eg. text, speech<br \/>and visual) together for superior solutions. Such algorithms<br \/>are also now discovering interesting correlations across the <br \/>modalities. In this talk, we especially focus on the interplay<br \/>between text, speech and visual content in talking face videos.<br \/>We present some of the recent results (including some from our<br \/>own research) and discuss ongoing trends and the challenges in<br \/>front of the community. For example, how many lip movements<br \/>can explain the speech that is produced and the reverse? How does<br \/>the multimodal nature of our inputs open up new avenues and<br \/>innovative solutions? Can we substitute or supplement one modality<br \/>for the other? Initial results hint at new possibilities in education, <br \/>healthcare and assistive technologies.\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-d37be17 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"d37be17\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-3dd650d elementor-invisible\" data-id=\"3dd650d\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-15be93f elementor-widget elementor-widget-image\" data-id=\"15be93f\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"267\" height=\"300\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/hatice-gunes-267x300.jpg\" class=\"attachment-medium size-medium wp-image-1371\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/hatice-gunes-267x300.jpg 267w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/hatice-gunes.jpg 327w\" sizes=\"(max-width: 267px) 100vw, 267px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0f351b8 elementor-widget elementor-widget-text-editor\" data-id=\"0f351b8\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Hatice Gunes<br \/><\/strong><em>Professor of Affective Intelligence and Robotics (AFAR) and the Head of the AFAR Lab at the University of Cambridge\u2019s Department of Computer Science and Technology, UK.\u00a0<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-e18a0d2 elementor-invisible\" data-id=\"e18a0d2\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-3a77a17 elementor-widget elementor-widget-heading\" data-id=\"3a77a17\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Artificial Emotional Intelligence: Quo Vadis?<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ba79d6c elementor-widget elementor-widget-text-editor\" data-id=\"ba79d6c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\tAbstract: Emotional intelligence for artificial systems is not a luxury but a necessity. It is paramount for many applications that require both short and long\u2013term engaging human\u2013technology interactions, including entertainment, hospitality, education, and healthcare. However, creating artificially intelligent systems and interfaces with social and emotional skills is a challenging task. Progress in industry and developments in academia provide us a positive outlook, however, the artificial emotional intelligence of the current technology is still quite limited. Creating technology with artificial emotional intelligence requires the development of perception, learning, action and adaptation capabilities, and the ability to execute these pipelines in real-time in human-AI interactions. Truly addressing these challenges relies on cross-fertilization of multiple research fields, including psychology, nonverbal behaviour understanding, psychiatry, vision, social signal processing, affective computing, and human-computer and human-robot interaction. My lab\u2019s research has been pushing the state of the art in a wide spectrum of research topics in this area, including the  design and creation of new datasets; novel feature representations and learning algorithms for sensing and understanding human nonverbal behaviours in solo, dyadic and group settings; designing short\/long-term human-robot interactions for wellbeing; and investigating the bias that creeps into these systems. In this talk, I will present some of my research team\u2019s explorations in these areas including modelling person-specific cognitive processes for personality recognition, continual learning for facial expression recognition, mitigating bias in affect recognition, learning social appropriateness of robot actions, and creating robotic wellbeing coaches with continual adaptation.\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-9637833 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"9637833\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-e66b2d5 elementor-invisible\" data-id=\"e66b2d5\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-9efa3fd elementor-widget elementor-widget-image\" data-id=\"9efa3fd\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"300\" height=\"300\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Kristen-Grauman-300x300.jpg\" class=\"attachment-medium size-medium wp-image-1493\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Kristen-Grauman.jpg 300w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Kristen-Grauman-150x150.jpg 150w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-026144f elementor-widget elementor-widget-text-editor\" data-id=\"026144f\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Kristen Grauman<br \/><\/strong><em>Professor in the Department of Computer Science at the University of Texas at Austin and a Research Director in Facebook AI Research (FAIR).<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-0cb3872 elementor-invisible\" data-id=\"0cb3872\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-f6d683f elementor-widget elementor-widget-heading\" data-id=\"f6d683f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Audio-visual learning<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-45ddeb7 elementor-widget elementor-widget-text-editor\" data-id=\"45ddeb7\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: Perception systems that can both see and hear have great potential to unlock problems in video understanding, augmented reality, and embodied AI.\u00a0 I will present our recent work in audio-visual (AV) perception.<br \/>First, we explore how audio\u2019s spatial signals can augment visual understanding of 3D environments.\u00a0 This includes ideas for self-supervised feature learning from echoes, AV floorplan reconstruction, and active source separation, where an agent intelligently moves to hear things better in a busy environment.\u00a0 Throughout this line of work, we leverage our open-source SoundSpaces platform, which allows state-of-the-art rendering of highly realistic audio in real-world scanned environments.\u00a0 <br \/>Next, building on these spatial AV ideas, we introduce new ways to enhance the audio stream &#8211; making it possible to transport a sound to a new physical environment observed in a photo, or to dereverberate speech so it is intelligible for machine and human ears alike.\u00a0 Finally, I will overview Ego4D, a massive new egocentric video dataset built via a multi-institution collaboration that supports an array of exciting multimodal tasks.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-839659c elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"839659c\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-644026b elementor-invisible\" data-id=\"644026b\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-304d8e6 elementor-widget elementor-widget-image\" data-id=\"304d8e6\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"300\" height=\"300\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/mbrujine-300x300.jpg\" class=\"attachment-medium size-medium wp-image-1369\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/mbrujine-300x300.jpg 300w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/mbrujine-150x150.jpg 150w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/mbrujine.jpg 332w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e8c9bb4 elementor-widget elementor-widget-text-editor\" data-id=\"e8c9bb4\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Marleen de Bruijne <br \/><\/strong><em>Professor of AI in medical image analysis at Erasmus MC, The Netherlands<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-6045c54 elementor-invisible\" data-id=\"6045c54\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-f24f72f elementor-widget elementor-widget-heading\" data-id=\"f24f72f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Learning with less in medical imaging<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e0d168e elementor-widget elementor-widget-text-editor\" data-id=\"e0d168e\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: Supervised learning approaches\u00a0 have had tremendous success in medical imaging in the past few years. Automated analysis using convolutional neural networks is now in many cases as accurate as the assessment of an expert observer. A major factor still hampering the adoption of these techniques in practice is that it can be very expensive, time-consuming, or even impossible to obtain sufficiently many representative and well-annotated training images to train reliable models. On the other hand, weaker labels are often readily available, for instance in the form of a radiologist\u2019s assessment of the presence or absence of certain abnormalities.\u00a0 In this talk, we will discuss various approaches to exploit such information and to make\u00a0 machine learning techniques work in real life situations, where (annotated) training data is limited, available annotations may be wrong, data is highly heterogeneous, and training data may not be representative for the target data to analyze. I will present examples in several medical imaging applications.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<div class=\"elementor-element elementor-element-76c4498 elementor-widget elementor-widget-spacer\" data-id=\"76c4498\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 17-10-2023 *\/\n.elementor-column .elementor-spacer-inner{height:var(--spacer-size)}.e-con{--container-widget-width:100%}.e-con-inner>.elementor-widget-spacer,.e-con>.elementor-widget-spacer{width:var(--container-widget-width,var(--spacer-size));--align-self:var(--container-widget-align-self,initial);--flex-shrink:0}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container,.e-con>.elementor-widget-spacer>.elementor-widget-container{height:100%;width:100%}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer,.e-con>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer{height:100%}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer>.elementor-spacer-inner,.e-con>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer>.elementor-spacer-inner{height:var(--container-widget-height,var(--spacer-size))}.e-con-inner>.elementor-widget-spacer.elementor-widget-empty,.e-con>.elementor-widget-spacer.elementor-widget-empty{position:relative;min-height:22px;min-width:22px}.e-con-inner>.elementor-widget-spacer.elementor-widget-empty .elementor-widget-empty-icon,.e-con>.elementor-widget-spacer.elementor-widget-empty .elementor-widget-empty-icon{position:absolute;top:0;bottom:0;left:0;right:0;margin:auto;padding:0;width:22px;height:22px}<\/style>\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-c07a149 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"c07a149\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-25a9deb elementor-invisible\" data-id=\"25a9deb\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-944466e elementor-widget elementor-widget-image\" data-id=\"944466e\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"150\" height=\"150\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Untitled-300-x-300-px-1-150x150.png\" class=\"attachment-thumbnail size-thumbnail wp-image-1436\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Untitled-300-x-300-px-1-150x150.png 150w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2021\/11\/Untitled-300-x-300-px-1.png 300w\" sizes=\"(max-width: 150px) 100vw, 150px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b0f6f79 elementor-widget elementor-widget-text-editor\" data-id=\"b0f6f79\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Dr. Xian-Sheng Hua<br \/><\/strong><em>Vice President of Alibaba Group, Head of City Brain Lab of DAMO Academy.\u00a0<\/em><\/p><p>\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-8001ae6 elementor-invisible\" data-id=\"8001ae6\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-be783a7 elementor-widget elementor-widget-heading\" data-id=\"be783a7\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Scalable Real-World Visual Intelligence System - from Algorithm to Platform to Application<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-14675a0 elementor-widget elementor-widget-text-editor\" data-id=\"14675a0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\tAbstract: Visual intelligence is one of the key aspects of Artificial Intelligence. Considerable technology progresses along this direction have been made in the past decade. However, how to incubate the right technologies to solve the real-world problems in scale and convert them into real business values remains a challenge. In this talk, we will analyze current challenges of visual intelligence and summarize a few key points that help us successfully develop and apply scalable technologies to solve the core problems. In particular, we will introduce a few key visual intelligence technologies that have been successfully applied in a few exemplar application areas, including smart city, industrial vision, visual design, and medical analysis, from problem discovery and definition, to key algorithms development, to scalable platform building, and to realizing core values in the related applications.\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<div class=\"elementor-element elementor-element-177e698 elementor-widget elementor-widget-spacer\" data-id=\"177e698\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c322fba elementor-widget elementor-widget-heading\" data-id=\"c322fba\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Award Winners <\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-5f76f69 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5f76f69\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-fa99eac elementor-invisible\" data-id=\"fa99eac\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-f05198a elementor-widget elementor-widget-image\" data-id=\"f05198a\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"214\" height=\"300\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/hrt-214x300.jpg\" class=\"attachment-medium size-medium wp-image-2707\" alt=\"\" srcset=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/hrt-214x300.jpg 214w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/hrt-731x1024.jpg 731w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/hrt-768x1076.jpg 768w, https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/hrt.jpg 914w\" sizes=\"(max-width: 214px) 100vw, 214px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c784e19 elementor-widget elementor-widget-text-editor\" data-id=\"c784e19\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Prof. Tieniu<br \/>Tan<br \/><\/strong><em>Institute of Automation Chinese Academy of Sciences (CASIA), <\/em><em>China<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-468744e elementor-invisible\" data-id=\"468744e\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-86bb45a elementor-widget elementor-widget-heading\" data-id=\"86bb45a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Iris Recognition: Progress and Challenges<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6252c7c elementor-widget elementor-widget-heading\" data-id=\"6252c7c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">King-Sun Fu Prize Lecture<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b540533 elementor-widget elementor-widget-text-editor\" data-id=\"b540533\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: Iris recognition has proven to be a most reliable biometric solution for personal identification and has received much attention from the pattern recognition community. However, it is far from being a solved problem as many open issues remain to be resolved to make iris recognition more user-friendly and robust. In this talk, I will present an overview of our decades\u2019 efforts on iris recognition, including iris image acquisition, iris image pre-processing, iris feature extraction and security issues of iris recognition systems. I will discuss our most recent work on light-field iris recognition and all-in-focus simultaneous iris recognition of multiple people at a distance. Examples will be given to demonstrate the successful routine use of our work in a wide range of fields such as mobile payment, banking, access control, welfare distribution, etc. I will also address some of the remaining challenges as well as promising future research directions before closing the talk.\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-742f624 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"742f624\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-91893ae elementor-invisible\" data-id=\"91893ae\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-fed53e3 elementor-widget elementor-widget-image\" data-id=\"fed53e3\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"150\" height=\"150\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/ge-150x150.jpg\" class=\"attachment-thumbnail size-thumbnail wp-image-2708\" alt=\"\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2e373c8 elementor-widget elementor-widget-text-editor\" data-id=\"2e373c8\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Jiliang Tang<br \/><\/strong><em>MSU Foundation Professor, Data Science and Engineering Lab, Michigan State University, USA<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-7db3a55 elementor-invisible\" data-id=\"7db3a55\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-1559602 elementor-widget elementor-widget-heading\" data-id=\"1559602\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Graph Neural Networks: Models, Trustworthiness, and Applications  <\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-46ad09b elementor-widget elementor-widget-heading\" data-id=\"46ad09b\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">J. K. Aggarwal Prize Lecture<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ae20033 elementor-widget elementor-widget-text-editor\" data-id=\"ae20033\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: Graph Neural Networks (GNNs) have shown their power in graph representation learning. They have advanced numerous recognition and learning tasks in many domains such as biology and healthcare. In this talk, I will first introduce a novel perspective to understand and unify existing GNNs that paves a principled and innovative way to design new GNN models. As GNNs become more pervasive, there is an ever-growing concern over how GNNs can be trusted. Then I will discuss how to build trustworthy GNNs. Given that graphs have been leveraged to denote data in real-world systems, I will finally demonstrate representative applications of GNNs.\u00a0\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-inner-section elementor-element elementor-element-0d93c83 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"0d93c83\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-31f2fbb elementor-invisible\" data-id=\"31f2fbb\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeInLeft&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-4de54ee elementor-widget elementor-widget-image\" data-id=\"4de54ee\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" loading=\"lazy\" width=\"150\" height=\"150\" src=\"https:\/\/www.icpr2022.com\/wp-content\/uploads\/2022\/07\/geeg-150x150.jpg\" class=\"attachment-thumbnail size-thumbnail wp-image-2709\" alt=\"\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0addd0e elementor-widget elementor-widget-text-editor\" data-id=\"0addd0e\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p><strong>Prof. Yunhong Wang<br \/><\/strong><em>School of Computer Science and Engineering, Beihang University, China<\/em><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-inner-column elementor-element elementor-element-f1381b6 elementor-invisible\" data-id=\"f1381b6\" data-element_type=\"column\" data-settings=\"{&quot;animation&quot;:&quot;fadeIn&quot;}\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-0c63875 elementor-widget elementor-widget-heading\" data-id=\"0c63875\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Towards Practical Biometrics: Face and Gait<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-258bdbb elementor-widget elementor-widget-heading\" data-id=\"258bdbb\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Maria Petrou Prize Lecture<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b0e1715 elementor-widget elementor-widget-text-editor\" data-id=\"b0e1715\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<p>Abstract: Biometrics are unique physical or behavioural characteristics that can be adopted for identification. In the last few years, substantial advancements have been made in this field with the development of deep learning theories and technologies. This is evidenced by not only the high results on large-scale benchmarks but also the attempts accounting for soft-biometrics, including gender, expression, age, etc. Meanwhile, recent studies show additional challenges in uncontrolled conditions, such as severe variations in scale, pose, illumination, occlusion and cluttered background, which should be well handled for real-world applications. This talk focuses on two typical representatives, face recogniiton and gait recognition, with dedicatedly designed deep learning based methodologies towards practical use, covering the tasks from identity recognition to attribute analysis, presenting the latest progress on the interpretability and robustness of deep neural networks. Finally, some perspectives are discussed to facilitate future research.\u00a0<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>C. V. JawaharProfessor at International Institute of Information Technology (IIIT), India.\u00a0 Towards Multimodality in Perception Tasks Abstract: A number of perception tasks (especially in vision,language and speech) are solved today with very high accuracy usingdata-driven techniques. We are now seeing the emergence of a setof more natural tasks that are inherently multimodal (eg. VQA).They are &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/www.icpr2022.com\/keynote-abstracts\/\"> <span class=\"screen-reader-text\">Keynote Abstracts<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"right-sidebar","site-content-layout":"plain-container","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"disabled","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"","footnotes":""},"_links":{"self":[{"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/pages\/2661"}],"collection":[{"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/comments?post=2661"}],"version-history":[{"count":62,"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/pages\/2661\/revisions"}],"predecessor-version":[{"id":3053,"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/pages\/2661\/revisions\/3053"}],"wp:attachment":[{"href":"https:\/\/www.icpr2022.com\/wp-json\/wp\/v2\/media?parent=2661"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}