Research map / 3D vision / Depth and stereo
Moving Beyond More Views: Redundancy-Aware Ego–Exo Fusion for Proficiency Estimation
Xu Dong, Wanqing Li, Anthony Adeyemi-Ejeye, Andrew Gilbert
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 |
|---|---|---|---|
| add AdaMVS adaptive view selection (ablation) | EgoExo baseline · Ego-Exo4D Ego+Exos | accuracy: 45.5 -> 48.0 | Improved |
| add CORN ordinal loss (ablation) | AdaMVS · Ego-Exo4D Ego+Exos | accuracy: 48.0 -> 48.4 | Improved |
| add gradient blending (ablation) | AdaMVS+CORN · Ego-Exo4D Ego+Exos | accuracy: 48.4 -> 48.6 | Improved |
| add VIB with gradient blending (ablation) | AdaMVS+CORN+GB · Ego-Exo4D Ego+Exos | accuracy: 48.6 -> 51.0 | Improved |
| add AdaMVS to VIB-GB model (ablation) | VIB-GB model · Ego-Exo4D Ego+Exos | accuracy: 48.7 -> 51.0 | Improved |
| use Top-K=2 views instead of all 4 (ablation) | AdaMVS · Ego-Exo4D (K400) | accuracy: 49.89 -> 53.00 | Improved |
| use VIB-GB instead of standard dropout (p=0.5) | K400 baseline · Ego-Exo4D | accuracy: 48.8 -> 53.0 | Improved |
| use Feature-Mixup / dropout regularisers | K400 baseline · EgoExo-Fitness | accuracy: 44.0 -> 38.1 to 40.5 | Hurt |
| add more exocentric views to conventional fusion | Concat/summation fusion · Ego-Exo4D | accuracy: Concat (early) 47.7 (3 Exo) -> 45.5 (4 Exo) | Mixed |
| use AdaMVS-Small instead of Large | AdaMVS · Ego-Exo4D Ego+Exos | accuracy: 53.0 -> 50.1 | Mixed |
Closest papers by meaning
- Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations (CVPR 2025 · similarity 0.88)
- Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning (CVPR 2025 · similarity 0.87)
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (CVPR 2024 · similarity 0.87)
- EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs (NeurIPS 2025 · similarity 0.86)
- Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos (ICLR 2025 · similarity 0.86)
- Retrieval-Augmented Egocentric Video Captioning (CVPR 2024 · similarity 0.86)
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.
