Not every moment in a video is equally useful for recognizing an action. A few decisive moments often carry the evidence: the instant an object moves, the peak of a dive, or one object placed on another. Existing video datasets rarely provide large-scale, action-conditioned labels for which short segments carry that ev...
CRYSTAL is introduced, a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning through verifiable intermediate steps, and the Causal Process Reward (CPR), a multiplicative reward that couples answer correctness with step-level alignment, and CPR-Curriculum, which progressively increases reasonin...
This work proposes StoryTeller, a training-free framework for story-aware long-form AD that consistently improves narrative coherence, factual grounding, and story comprehension over strong baselines in automatic, QA-based, and human evaluations.
Seung-Yeon Hahm, M. T. Dinh, SouYoung Jin· 0 citations
Inspired by recent progress in 3D reconstruction with 3D Gaussian Splatting, PredGS, a lightweight and plug-and-play adapter based on 2D Gaussian representation, which could be seamlessly integrated with existing pixel space predictors, significantly improving spatial detail preservation with negligible computational o...
Yujin Tang, Tian Zhou, Xin Lin et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
