arXiv:2606. 28083v1 Announce Type: cross Abstract: Micro-expression recognition is challenging due to subtle and short-lived facial muscle movements.
By Nandani Sharma, Varun Sharma, Dinesh Singh
Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories.
arXiv:2607. 00716v1 Announce Type: cross Abstract: Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs.
By Yingjie Dai, Tianyang Xu, Yanglin Deng, Xiao-Jun Wu, Josef Kittler
Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In real-world deployments, such as egocentric vision, crowded surveillance, wearable devices, or edge robotics, limited field-of-view (FoV) frequently causes substantial joint visibility dropout, leading to severe performance degradation that existing models are largely unprepared to handle.
arXiv:2607. 23077v1 Announce Type: new Abstract: Modeling multi-entity temporal data requires capturing dependencies across entities, time, and their interactions.
By Narthana Sivalingam, Santhirarajah Sivasthigan, Buddhi Wijenayake, Roshan Godaliyadda, Vijitha Herath, Parakrama Ekanayake
arXiv:2604. 08435v2 Announce Type: replace-cross Abstract: It remains challenging to assess driver fatigue from untrimmed videos under constrained computational budgets, due to the difficulty of modeling long-range temporal dependencies in subtle facial expressions.
By Changdao Chen, Qinqiuhong Ye, Hao Chen, Jinyu Wang