BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Australia/Melbourne X-LIC-LOCATION:Australia/Melbourne BEGIN:DAYLIGHT TZOFFSETFROM:+1000 TZOFFSETTO:+1100 TZNAME:AEDT DTSTART:19721003T020000 RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU END:DAYLIGHT BEGIN:STANDARD DTSTART:19721003T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 TZNAME:AEST RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240214T070310Z LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre) DTSTART;TZID=Australia/Melbourne:20231213T123000 DTEND;TZID=Australia/Melbourne:20231213T133600 UID:siggraphasia_SIGGRAPH Asia 2023_sess163@linklings.com SUMMARY:Motion Synthesis with Awareness DESCRIPTION:Technical Papers\n\nDROP: Dynamics Responses from Human Motion Prior and Projective Dynamics\n\nSynthesizing realistic human movements, dynamically responsive to the environment, is a long-standing objective in character animation, with applications in computer vision, sports, and he althcare, for motion prediction and data augmentation. Recent kinematics-b ased generative motion models offer im...\n\n\nYifeng Jiang (Stanford Univ ersity), Jungdam Won (Seoul National University), Yuting Ye (Meta Reality Labs Research), and C. Karen Liu (Stanford University)\n------------------ ---\nObject Motion Guided Human Motion Synthesis\n\nModeling human behavio rs in contextual environments has a wide range of applications in characte r animation, embodied AI, VR/AR, and robotics. In real-world scenarios, hu mans frequently interact with the environment and manipulate various objec ts to complete daily tasks. In this work, we study the p...\n\n\nJiaman Li , Jiajun Wu, and Karen Liu (Stanford University)\n---------------------\nS ynthDa: Exploiting Existing Real-World Data for Usable and Accessible Synt hetic Data Generation\n\nSynthDa: Empowering computer vision with automate d synthetic data. Integrating 3 steps, it provides diverse synthetic data from real-world datasets for evaluations. Our experiments challenge data q uantity beliefs, challenging current beliefs.\n\n\nMegani Rajendran (NVIDI A), Chek Tien Tan and Indriyati Atmosukarto (Singapore Institute of Techno logy), Aik Beng Ng (NVIDIA), Zhihua Zhou (Singapore Institute of Technolog y), and Andrew Grant and Simon See (NVIDIA)\n---------------------\nMotion to Dance Music Generation using Latent Diffusion Model\n\nOur method is a motion-to-music generation model capable of producing dance music from 3D motion data and genre. It utilizes a latent diffusion-based architecture paired with a pre-trained VAE model.\n\n\nVanessa Tan, JungHyun Nam, Juhan Nam, and Junyong Noh (Korea Advanced Institute of Science and Technology (KAIST))\n---------------------\nCommonsense Knowledge-Driven Joint Reason ing Approach for Object Retrieval in Virtual Reality\n\nOut-of-reach objec t retrieval is an important task in virtual reality (VR). Gesture-based ap proach, one of the most commonly used approaches, enables bare-hand, eyes- free, and direct retrieval by using assigned gestures. However, it is diff icult to retrieve an object from plenty of objects accuratel...\n\n\nHaiya n Jiang (Beijing Institute of Technology; National Key Laboratory of Gener al Artificial Intelligence, Beijing Institute for General Artificial Intel ligence (BIGAI)); Dondong Weng (Beijing Institute of Technology); Xiaonuo Dongye (Beijing Institute of Technology; National Key Laboratory of Genera l Artificial Intelligence, Beijing Institute for General Artificial Intell igence (BIGAI)); Le Luo (Beijing Institute of Technology); and Zhenliang Z hang (National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI))\n------------------ ---\nComputational Design of Wiring Layout on Tight Suits with Minimal Mot ion Resistance\n\nAn increasing number of electronics are directly embedde d on the clothing to monitor human status (skeletal motion or electromyogr am activity) or provide haptic feedback.\nA specific challenge to prototyp e and fabricate such a clothing is to design the wiring layout, to minimiz e the intervention to h...\n\n\nKai Wang, Xiaoyu Xu, Yinping Zheng, Da Zho u, and Shihui Guo (Xiamen University); Yipeng Qin (School of Computer Scie nce and Informatic, Cardiff University); and Xiaohu Guo (University of Tex as at Dallas)\n\nRegistration Category: Full Access\n\nSession Chair: Chek Tien Tan (Singapore Institute of Technology) END:VEVENT END:VCALENDAR