Research map / Video / Video segmentation and tracking
Egocentric Video Search via Physical Interactions
Taiki Miyanishi, Jun-ichiro Hirayama, Quan Kong, Takuya Maekawa, Hiroki Moriya, Takayuki Suyama
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| retrieve in PCCA latent space fusing motion and video instead of raw motion space | gesture-based video retrieval · inner-subject | AP: 0.2699 -> 0.3557 | Improved |
| retrieve in PCCA latent space fusing motion and video instead of raw motion space | gesture-based video retrieval · cross-subject | AP: 0.1477 -> 0.2087 | Improved |
| use probabilistic CCA instead of standard CCA for initial retrieval (ablation) | gesture-based video retrieval · inner-subject | AP: 0.3253 -> 0.3557 | Improved |
| use probabilistic CCA instead of standard CCA for initial retrieval (ablation) | gesture-based video retrieval · cross-subject | AP: 0.1856 -> 0.2087 | Improved |
| add single-modality KDE re-ranking on motion (ablation) | MR + PCCA · inner-subject | AP: 0.3557 -> 0.3554 | No clear effect |
| add multimodal PCCA-based KDE re-ranking (ablation) | MR + PCCA · inner-subject | AP: 0.3557 -> 0.3822 | Improved |
| add multimodal PCCA-based KDE re-ranking (ablation) | MR + PCCA · cross-subject | AP: 0.2087 -> 0.2238 | Improved |
| use PCCA kernel instead of CCA kernel in KDE re-ranking (ablation) | MR + PCCA re-ranking · inner-subject | AP: 0.3697 -> 0.3822 | Improved |
Closest papers by meaning
- Retrieval-Augmented Egocentric Video Captioning (CVPR 2024 · similarity 0.88)
- Egocentric Action Recognition by Automatic Relation Modeling (TPAMI 2022 · similarity 0.87)
- EgoLife: Towards Egocentric Life Assistant (CVPR 2025 · similarity 0.86)
- Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning (ICLR 2025 · similarity 0.86)
- Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? (ICLR 2025 · similarity 0.85)
- Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
