390 citations
- Carnegie Mellon UniversityUS7 papers
- University of Illinois Urbana-ChampaignUS7 papers
- University of WashingtonUS7 papers
- Adobe Systems (United States)US6 papers
- Google (United States)US6 papers
- University of GroningenNL5 papers
- University of Southern CaliforniaUS5 papers
- Meta (United States)US4 papers
- Microsoft (United States)US4 papers
- Columbia UniversityUS3 papers
- National University of SingaporeSG3 papers
- Northwestern UniversityUS3 papers
84 papers
Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
Li Wang, Yiyu Zhuang, Yanwen Wang +4
3D human pose estimation from sketches has broad applications in computer animation and film production. Unlike traditional human pose estimation, this task presents unique challen…
A Survey on Human Interaction Motion Generation
Kewei Sui, Anindita Ghosh, Inwoo Hwang +3
Humans inhabit a world defined by interactions -- with other humans, objects, and environments. These interactive movements not only convey our relationships with our surroundings…
Stable Flow: Vital Layers for Training-Free Image Editing
Omri Avrahami, Or Patashnik, Ohad Fried +4
Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT),…
Matting by Generation
Zhixiang Wang, Baiang Li, Jian Wang +4
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge. Our method harnesses the cap…
Spectral 2-actions, foams, and frames in the spectrification of Khovanov arc algebras
Anne Dranowski, Meng Guo, Aaron Lauda +1
Leveraging skew Howe duality, we show that Lawson-Lipshitz-Sarkar's spectrification of Khovanov's arc algebra gives rise to 2-representations of categorified quantum groups over $\…
General-Purpose User Modeling with Behavioral Logs: A Snapchat Case Study
Qixiang Fang, Zhihan Zhou, Francesco Barbieri +6
Learning general-purpose user representations based on user behavioral logs is an increasingly popular user modeling approach. It benefits from easily available, privacy-friendly y…