arXiv:2603.24106v2 Announce Type: replace
Abstract: Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit…
arXiv:2603.29967v1 Announce Type: new
Abstract: Understanding how brain structure and function interact is key to explaining intelligence yet modeling them jointly is challenging as the structural and functional connectome capture complementary aspect…
arXiv:2603.21482v2 Announce Type: replace
Abstract: Recent vision-language models such as CLIP provide strong cross-modal alignment, but current CLIP-guided ReID pipelines rely on global features and fixed prompts. This limits their ability to capture…
arXiv:2603.29966v1 Announce Type: new
Abstract: Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent eva…
arXiv:2603.19979v2 Announce Type: replace
Abstract: Scalable and reliable evaluation is increasingly critical in the end-to-end era of autonomous driving, where vision–language–action (VLA) policies directly map raw sensor streams to driving actions…
arXiv:2603.29962v1 Announce Type: new
Abstract: Surgical procedures are inherently complex and risky, requiring extensive expertise and constant focus to well navigate evolving intraoperative scenes. Computer-assisted systems such as surgical visual q…
arXiv:2603.18782v3 Announce Type: replace
Abstract: Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-regi…
arXiv:2603.29960v1 Announce Type: new
Abstract: Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-sectional and miss how brain networks chang…
arXiv:2603.14794v2 Announce Type: replace
Abstract: Modeling the reactive tempo of human conversation remains difficult because most audio-visual datasets portray isolated speakers delivering short monologues. We introduce \textbf{Face-to-Face with Ji…
arXiv:2603.29954v1 Announce Type: new
Abstract: In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to classify known objects without forgetting while identi…