arXiv 2610.20091 · cs.CV · 2026-10-14
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Jaeyeon Heo, Geuntaek Lim, Yukyung Choi
机构待核实
在最新榜 #364 本站收录于 2026-10-26
一句话要点
RTAformer 针对视频场景图生成中的「关系语义惯性」（关系已变但预测不变），分别建模实体持续性和关系变化，把相邻帧关系查询的差异注入谓词更新。
RTAformer tackles "relational semantic inertia" in video scene graph generation by separately modeling entity persistence and relation changes, injecting calibrated adjacent-frame query differences to guide predicate updates.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：视觉理解与 3D
- Spectral-Spatial Interpretation ▲753
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲189
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲172
- DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations ▲161
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。