Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification
Wanke Xia, Ruiding Zhu, Xingguo Xu +6
Multi-modal object re-identification exploits complementary RGB, near-infrared (NIR), and thermal-infrared (TIR) observations to retrieve target objects. However, existing methods…
cs.CV2026
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal
Feier Wu, Wanke Xia, Xu He +8
Video object removal must eliminate not only the target object but also its induced effects while maintaining high-fidelity and spatiotemporally coherent restoration. Existing meth…
cs.CV2026
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
Yuan Zeng, Yujia Shi, Yuhao Yang +4
Human image animation aims to generate a video from a static reference image, guided by pose information extracted from a driving video. Existing approaches often rely on pose esti…