This work proposes CLIPtrase, a novel training-free semantic segmentation strategy, which enhances local cognition through recalibrated self-correlation among patches and quadrant mask ensemble strategy, which demonstrates significant improvements in segmentation accuracy and the ability to maintain semantic coherence...
Tong Shao, Zhuo-Tao Tian, Yun-Yang Mo et al.· IEEE Transactions on Pattern...· 0 citations
PlayWorld is introduced, a benchmark providing 171 scenarios, each with a specified objective, to assess models along four core dimensions: geometry consistency, interaction fidelity, out-of-sight evolution, and insight evolution, and basic ability metrics for video quality and controllability.
Kai Ding, Xi Chen, Ming-Hong Cai et al.· 3 citations
This work proposes VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning, showing that representation-centric continued pre-training can deliver highly competitive performance under a modest compute budget and is an important independent axis of...
Sen-Qiao Yang, Cheng-Yao Wang, Yu-Xin Chen et al.· 8 citations
The OmniEdit-Bench provides a comprehensive and reliable testbed for evaluating instruction-based video editing and offers insights into future research directions, including an accuracy-aware penalty mechanism that conditions other scores on accuracy, preventing visually plausible but incorrect edits from receiving in...
Chenxuan Miao, Yutong Feng, Yi Lu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
