BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Hong_Kong BEGIN:STANDARD DTSTART:19791021T023000 TZOFFSETFROM:+0900 TZOFFSETTO:+0800 TZNAME:HKT END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20261020T010510Z UID:5B15EA77-16DB-47F8-9E99-865AFC71D01D DTSTART;TZID=Asia/Hong_Kong:20261120T103000 DTEND;TZID=Asia/Hong_Kong:20261120T113000 DESCRIPTION:Prof. Josiane Zerubia from INRIA\, France will give a talk enti tled "Probabilistic Graphical Models and Deep Learning for Remote SensingI mage Analysis" at CUHKSZ.\n\nAbstract: Deep learning offers powerful non-p arametric feature extraction\, while probabilistic graphical models such a s Markov random fields and conditional random fields provide a principled framework for structured prediction. This lecture examines their connectio ns\, from simple integration to end-to-end and intrinsically integrated fo rmulations\, and shows how they support remote sensing image analysis. Res ults on multimodal satellite and aerial imagery demonstrate applications i n structured prediction\, image fusion and segmentation\, and image genera tion.\n\nSpeaker Bio: Professor Josiane Zerubia has been a permanent resea rch scientist at INRIA since 1989 and Director of Research since 1995. She leads INRIA's AYANA exploratory research group\, an interdisciplinary pro ject spanning stochastic modeling\, image processing\, artificial intellig ence\, remote sensing and embedded computing. Her research focuses on imag e processing using probabilistic models\, parameter estimation\, statistic al learning\, optimization and artificial intelligence. She is an IEEE Lif e Fellow\, EURASIP Fellow and IAPR Fellow\, and an IEEE Geoscience and Rem ote Sensing Society Distinguished Lecturer (2025-2027).\n\nRoom: RM 207\, Bldg: Chengdao Building\, 2001 Longxiang Blvd\, Shenzhen\, Guangdong\, Chi na LOCATION:Room: RM 207\, Bldg: Chengdao Building\, 2001 Longxiang Blvd\, She nzhen\, Guangdong\, China ORGANIZER:SimonPun@cuhk.edu.cn SEQUENCE:16 SUMMARY:Seminar by Prof. Josiane Zerubia from INRIA\, France URL;VALUE=URI:https://events.vtools.ieee.org/m/587360 X-ALT-DESC:Description: <br /><p>Prof. Josiane Zerubia from INRIA\, France will give a talk entitled "Probabilistic Graphical Models and Deep Learnin g for Remote SensingImage Analysis" at CUHKSZ.</p>\n<p>Abstract: Deep lear ning offers powerful non-parametric feature extraction\, while probabilist ic graphical models such as Markov random fields and conditional random fi elds provide a principled framework for structured prediction. This lectur e examines their connections\, from simple integration to end-to-end and i ntrinsically integrated formulations\, and shows how they support remote s ensing image analysis. Results on multimodal satellite and aerial imagery demonstrate applications in structured prediction\, image fusion and segme ntation\, and image generation.</p>\n<p>Speaker Bio: Professor Josiane Zer ubia has been a permanent research scientist at INRIA since 1989 and Direc tor of Research since 1995. She leads INRIA's AYANA exploratory research g roup\, an interdisciplinary project spanning stochastic modeling\, image p rocessing\, artificial intelligence\, remote sensing and embedded computin g. Her research focuses on image processing using probabilistic models\, p arameter estimation\, statistical learning\, optimization and artificial i ntelligence. She is an IEEE Life Fellow\, EURASIP Fellow and IAPR Fellow\, and an IEEE Geoscience and Remote Sensing Society Distinguished Lecturer (2025-2027).</p> END:VEVENT END:VCALENDAR