BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030536Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251218T104000
DTEND;TZID=Asia/Hong_Kong:20251218T114500
UID:siggraphasia_SIGGRAPH Asia 2025_sess153@linklings.com
SUMMARY:Human Motion Synthesis & Interaction
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nLearning Human Motion with Tempo
 rally Conditional Mamba\n\nLearning human motion based on a time-dependent
  input signal presents a challenging yet impactful task with various appli
 cations. The goal of this task is to generate or estimate human movement t
 hat consistently reflects the temporal patterns of conditioning inputs. Ex
 isting methods typically rely o...\n\n\nQuang Nguyen and Tri Le (FPT AI Ce
 nter); Baoru Huang (University of Liverpool, Imperial College London); Min
 h Nhat Vu (Vienna University of Technology); Ngan Le (University of Arkans
 as at Little Rock); Thieu Vo (National University of Singapore); and Anh N
 guyen (Department of Computer Science, University of Liverpool)\n---------
 ------------\nUni-Inter Unifying 3D Human Motion Synthesis Across Diverse 
 Interaction Contexts\n\nWe present Uni-Inter, a unified framework for huma
 n motion generation that supports a wide range of interaction scenarios—in
 cluding human-human, human-object, and human-scene—within a single, task-a
 gnostic architecture. In contrast to existing methods that rely on task-sp
 ecific designs a...\n\n\nSheng Liu (Nanjing University); Yuanzhi Liang and
  Jiepeng Wang (Institute of Artificial Intelligence, China Telecom (TeleAI
 )); Sidan Du (Nanjing University); and Chi Zhang and Xuelong Li (Institute
  of Artificial Intelligence, China Telecom (TeleAI))\n--------------------
 -\nPhysics-Based Motion Imitation with Adversarial Differential Discrimina
 tors\n\nMulti-objective optimization problems, which require the simultane
 ous optimization of multiple objectives, are prevalent across numerous app
 lications. Existing multi-objective optimization methods often rely on man
 ually-tuned aggregation functions to formulate a joint optimization object
 ive. The per...\n\n\nZiyu Zhang (Simon Fraser University); Sergey Bashkiro
 v (Sony Playstation); Dun Yang and Yi Shi (Simon Fraser University); Micha
 el Taylor (Sony Playstation); and Xue Bin Peng (Simon Fraser University, N
 VIDIA)\n---------------------\nSRBTrack: Terrain-Adaptive Tracking of a Si
 ngle-Rigid-Body Character Using Momentum-Mapped Space-Time Optimization\n\
 nGenerating realistic and robust motion for virtual characters under compl
 ex physical conditions, such as irregular terrain, real-time control scena
 rios, and external disturbances, remains a key challenge in computer graph
 ics.\nWhile deep reinforcement learning has enabled high-fidelity physics-
 based ...\n\n\nHanyang Cao (Hanyang University), Heyuan Yao and Libin Liu 
 (Peking University), and Taesoo Kwon (Hanyang University)\n---------------
 ------\nHOMA: Towards Generic Human-Object Interaction in Multimodal Drive
 n Human Animation with Weak Conditions\n\nWhile recent advances in human-o
 bject interaction (HOI) video generation showcase promising capabilities f
 or synthesizing coordinated human-object dynamics, existing methods remain
  constrained by their reliance on meticulously curated motion sequences an
 d actor-specific data, thereby limiting practi...\n\n\nZiyao Huang (Univer
 sity of Chinese Academy of Sciences); Zixiang Zhou (Tencent); Juan Cao (Un
 iversity of Chinese Academy of Sciences); Yifeng Ma and Yi Chen (Tencent);
  Zejing Rao (University of Chinese Academy of Sciences); Zhiyong Xu, Hongm
 ei Wang, Qin Lin, Yuan Zhou, and Qinglin Lu (Tencent); and Fan Tang (Unive
 rsity of Chinese Academy of Sciences)\n---------------------\nCHOICE: Coor
 dinated Human-Object Interaction in Cluttered Environments for Pick-and-Pl
 ace Actions\n\nAnimating human-scene interactions, such as picking and pla
 cing a wide range of objects with different geometries, is a challenging t
 ask, especially in a cluttered environment where interactions with complex
  articulated containers are involved. The main difficulty lies in the spar
 sity of the motion ...\n\n\nJintao Lu (The University of Hong Kong); He Zh
 ang (Tencent Robotics X); Yuting Ye, Takaaki Shiratori, and Sebastian Star
 ke (Meta Reality Labs); and Taku Komura (The University of Hong Kong)\n\nR
 egistration Category: Full Access, Full Access Supporter\n\nSession Chair:
  Kai Wang (Simon Fraser University)
END:VEVENT
END:VCALENDAR