BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Shanghai BEGIN:STANDARD DTSTART:19910915T010000 TZOFFSETFROM:+0900 TZOFFSETTO:+0800 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250115T033928Z UID:1271F9BD-2C6D-48CB-858F-1D28CE99F689 DTSTART;TZID=Asia/Shanghai:20240703T143000 DTEND;TZID=Asia/Shanghai:20240703T153000 DESCRIPTION:Lecture Title: Theory and Technology of Multimodal Fusion for L ow-Quality Data\nSpeaker: Prof. Zhang Changqing\nVenue: Room 9322\, Xipu C ampus\, Southwest Jiaotong University\n----------------------------------- ----------------------------\n\nAbstract:\nMultimodal data often exhibit c omplex interrelationships\, and in real-world scenarios\, the quality of d ata from different information sources can vary dynamically across time\, space\, and samples. This dynamic nature significantly impacts the ability to support tasks effectively. For instance\, multimodal data may be affec ted by adverse weather conditions or sensor malfunctions\, where radar sig nals are often more reliable than RGB camera signals during nighttime or i n rainy and foggy weather. Based on this context\, this lecture will intro duce machine learning methods and applications designed for low-quality mu ltimodal data and analyze the theoretical foundations behind them.\n------ ---------------------------------------------------------\n\nSpeaker Biogr aphy:\nProf. Zhang Changqing is a professor and doctoral advisor at the Co llege of Intelligence and Computing\, Tianjin University\, and Vice Dean o f the School of Artificial Intelligence. He is a recipient of a national-l evel youth talent award. His research focuses on machine learning and comp uter vision\, with multiple papers selected for oral presentations or spot light papers at ICML\, CVPR\, and NeurIPS. His work has been cited over 10 \,000 times on Google Scholar. Prof. Zhang’s achievements include the Fi rst Prize of the Natural Science Award from the China Society of Image and Graphics\, the Best Paper Award at ICME\, and recognition in Baidu's list of Global High-Potential Chinese AI Scholars\, as well as Stanford Univer sity's Global Top 2% Scientists list.\n\nChengdu\, Sichuan\, China LOCATION:Chengdu\, Sichuan\, China ORGANIZER:zhengyubang@163.com SEQUENCE:37 SUMMARY: Invited talk given by Prof. Changqing Zhang of Tianjin University URL;VALUE=URI:https://events.vtools.ieee.org/m/462103 X-ALT-DESC:Description: <br /><div class="flex-shrink-0 flex flex-col relat ive items-end">\n<div>\n<div class="pt-0">\n<div class="gizmo-bot-avatar f lex h-8 w-8 items-center justify-center overflow-hidden rounded-full">\n<d iv class="relative p-1 rounded-sm flex items-center justify-center bg-toke n-main-surface-primary text-token-text-primary h-8 w-8">&nbsp\;</div>\n</d iv>\n</div>\n</div>\n</div>\n<div class="group/conversation-turn relative flex w-full min-w-0 flex-col agent-turn">\n<div class="flex-col gap-1 md:g ap-3">\n<div class="flex max-w-full flex-col flex-grow">\n<div class="min- h-8 text-message flex w-full flex-col items-end gap-2 whitespace-normal br eak-words text-start [.text-message+&amp\;]:mt-5" dir="auto" data-message- author-role="assistant" data-message-id="b7e84108-2ae7-4cf7-89ee-2cb9cc21e 9ca" data-message-model-slug="gpt-4o">\n<div class="flex w-full flex-col g ap-1 empty:hidden first:pt-[3px]">\n<div class="markdown prose w-full brea k-words dark:prose-invert light">\n<p><strong>Lecture Title:</strong> Theo ry and Technology of Multimodal Fusion for Low-Quality Data<br><strong>Spe aker:</strong> Prof. Zhang Changqing<br><strong>Venue:</strong> Room 9322\ , Xipu Campus\, Southwest Jiaotong University</p>\n<hr>\n<p><strong>Abstra ct:</strong><br>Multimodal data often exhibit complex interrelationships\, and in real-world scenarios\, the quality of data from different informat ion sources can vary dynamically across time\, space\, and samples. This d ynamic nature significantly impacts the ability to support tasks effective ly. For instance\, multimodal data may be affected by adverse weather cond itions or sensor malfunctions\, where radar signals are often more reliabl e than RGB camera signals during nighttime or in rainy and foggy weather. Based on this context\, this lecture will introduce machine learning metho ds and applications designed for low-quality multimodal data and analyze t he theoretical foundations behind them.</p>\n<hr>\n<p><strong>Speaker Biog raphy:</strong><br>Prof. Zhang Changqing is a professor and doctoral advis or at the College of Intelligence and Computing\, Tianjin University\, and Vice Dean of the School of Artificial Intelligence. He is a recipient of a national-level youth talent award. His research focuses on machine learn ing and computer vision\, with multiple papers selected for oral presentat ions or spotlight papers at ICML\, CVPR\, and NeurIPS. His work has been c ited over 10\,000 times on Google Scholar. Prof. Zhang&rsquo\;s achievemen ts include the First Prize of the Natural Science Award from the China Soc iety of Image and Graphics\, the Best Paper Award at ICME\, and recognitio n in Baidu's list of Global High-Potential Chinese AI Scholars\, as well a s Stanford University's Global Top 2% Scientists list.</p>\n</div>\n</div> \n</div>\n</div>\n</div>\n</div> END:VEVENT END:VCALENDAR