2 papers
cs.CV2026
DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing
Zhengjie Xu, Ruihao Gong, Xianglong Liu
Human mesh recovery (HMR) provides a geometric foundation for understanding human motion, but accurately reconstructing both body motion and fine hand articulation from videos rema…
cs.CV2026
Order Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language Reasoning
Haihan Li, Haihao Li, Zhenfei Xu +2
Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact case of this problem: their pu…