arXiv 2610.20091 · cs.CV · 2026-10-14
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Jaeyeon Heo, Geuntaek Lim, Yukyung Choi
Affiliation unverified
In latest · #364 Added on 2026-10-26
One-line takeaway
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.
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。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Vision & 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.