BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T130000
DTEND;TZID=Asia/Tokyo:20241205T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess132@linklings.com
SUMMARY:Characters and Crowds
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nPDP: Physics-Based Character Animation via Diffusion Policy\n\nGenerat
 ing diverse and realistic human motion that can physically interact with a
 n environment remains a challenging research area in character animation. 
 Meanwhile, diffusion-based methods, as proposed by the robotics community,
  have demonstrated the ability to capture highly diverse and multi-moda...
 \n\n\nTakara Truong, Michael Piseno, Zhaoming Xie, and Karen Liu (Stanford
  University)\n---------------------\nCBIL: Collective Behavior Imitation L
 earning for Fish from Real Videos\n\nReproducing realistic collective beha
 viors presents a captivating yet formidable challenge. Traditional rule-ba
 sed methods rely on hand-crafted principles, limiting motion diversity and
  realism in generated collective behaviors. Recent imitation learning meth
 ods learn from data but often require gro...\n\n\nYifan Wu (University of 
 Hong Kong); Zhiyang Dou (University of Hong Kong, University of Pennsylvan
 ia); Yuko Ishiwaka and Shun Ogawa (SoftBank); Yuke Lou (University of Hong
  Kong); Wenping Wang (Texas A&M University); Lingjie Liu (University of Pe
 nnsylvania); and Taku Komura (University of Hong Kong)\n------------------
 ---\nResolving Collisions in Dense 3D Crowd Animations\n\nWe propose a con
 tact-aware method for synthesizing dense 3D crowds of animated characters.
  Unlike existing methods, our approach prevents character intersections by
  modeling contacts using physics-based techniques. This results in real-ti
 me, collision-free animations with enhanced realism and geomet...\n\n\nGon
 zalo Gomez-Nogales, Melania Prieto-Martin, Cristian Romero, Marc Comino-Tr
 inidad, and Pablo Ramon-Prieto (Universidad Rey Juan Carlos); Anne-Hélène 
 Olivier (INRIA, Université de Rennes, CNRS, IRISA,  M2S Centre de Rennes);
  Ludovic Hoyet (Institut national de recherche en informatique et en autom
 atique (INRIA)); Miguel Otaduy (Universidad Rey Juan Carlos); Julien Pettr
 e (Institut national de recherche en informatique et en automatique (INRIA
 )); and Dan Casas (Universidad Rey Juan Carlos)\n---------------------\nBo
 dy Gesture Generation for Multimodal Conversational Agents\n\nCreating int
 elligent virtual agents with realistic conversational abilities necessitat
 es a multimodal communication approach extending beyond text. Body gesture
 s, in particular, play a pivotal role in delivering a lifelike user experi
 ence by providing additional context, such as agreement, confusion...\n\n\
 nSunwoo Kim, Minwook Chang, and Yoonhee Kim (NCSOFT) and Jehee Lee (Seoul 
 National University)\n---------------------\nMonkey See, Monkey Do: Harnes
 sing Self-attention in Motion Diffusion for Zero-shot Motion Transfer\n\nG
 iven the remarkable results of motion synthesis with diffusion models, a n
 atural question arises: how can we effectively leverage these models for m
 otion editing? Existing diffusion-based motion editing methods overlook th
 e profound potential of the prior embedded within the weights of pre-train
 ed ...\n\n\nSigal Raab, Inbar Gat, Nathan Sala, Guy Tevet, and Rotem Shale
 v-Arkushin (Tel Aviv University); Ohad Fried (Reichman University); and Am
 it Haim Bermano and Daniel Cohen-Or (Tel Aviv University)\n\nRegistration 
 Category: Full Access, Full Access Supporter\n\nLanguage Format: English L
 anguage\n\nSession Chair: Yi Zhou (Adobe)
END:VEVENT
END:VCALENDAR