Research map / Label-efficient and robust learning / Test-time adaptation
Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
Zhaofeng Shi, Heqian Qiu, Lanxiao Wang, Qingbo Wu, Fanman Meng, Lili Pan, Hongliang Li
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 dual-clue consistency loss L_C (ablation) | DCPGN · EgoExoLearn Exo2Ego | Noun Top-5 recall: 44.80 -> 46.26 | Improved |
| add visual clue (ablation) | DCPGN (w/o L_C) · EgoExoLearn Exo2Ego | Noun Top-5 recall: 41.32 -> 44.80 | Improved |
| add textual clue (ablation) | DCPGN (w/o L_C) · EgoExoLearn Ego2Exo | Verb Top-5 recall: 43.72 -> 45.84 | Improved |
| add whole DCCM module (ablation) | DCPGN · EgoMe-anti Exo2Ego | Verb Top-5 recall: 40.84 -> 43.84 | Improved |
| add confidence-based reweighting (ablation) | ML-PGM · EgoExoLearn Exo2Ego | Noun Top-5 recall: 37.76 -> 38.43 | Improved |
| multi-label Top-K assignment instead of Top-1 (ablation) | ML-PGM · EgoMe-anti Exo2Ego | Verb Top-5 recall: 35.47 -> 39.87 | Improved |
| increase K from 1 to 3 (ablation) | DCPGN · EgoMe-anti Exo2Ego | Verb Top-5 recall: 39.89 -> 43.84 | Improved |
| increase K from 3 to 5 (ablation) | DCPGN · EgoMe-anti Exo2Ego | Verb Top-5 recall: 43.84 -> 42.98 | Mixed |
| add test-time adaptation DCPGN vs no adaptation (ablation) | DCPGN · EgoMe-anti Exo2Ego | Verb Top-5 recall: 32.46 -> 43.84 | Improved |
| DCPGN vs ML-TTA | DCPGN · EgoExoLearn Exo2Ego | Noun Top-5 recall: 36.35 -> 46.26 | Improved |
Closest papers by meaning
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.86)
- Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs (NeurIPS 2026 · similarity 0.86)
- Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling (ICLR 2025 · similarity 0.85)
- EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World (CVPR 2024 · similarity 0.85)
- Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos (ICLR 2025 · similarity 0.85)
- EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs (NeurIPS 2025 · 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.
