Research map / Detection and segmentation / Open-set and few-shot detection
Grounded Affordance from Exocentric View
Hongchen Luo, Wei Zhai, Jing Zhang, Yang Hua Cao, Dacheng Tao
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 AIM module (ablation) | baseline · AGD20K mixed test (Seen) | KLD: 1.765 -> 1.680 | Improved |
| add AIM module (ablation) | baseline · AGD20K mixed test (Unseen) | KLD: 2.003 -> 1.973 | Improved |
| add ACP strategy (ablation) | baseline · AGD20K mixed test (Seen) | KLD: 1.765 -> 1.659 | Improved |
| add ACP strategy (ablation) | baseline · AGD20K mixed test (Unseen) | NSS: 0.725 -> 0.828 | Improved |
| add CFT module on top of AIM (ablation) | AIM · AGD20K mixed test (Seen) | KLD: 1.680 -> 1.602 | Improved |
| add ACP on top of AIM+CFT (ablation) | AIM+CFT · AGD20K mixed test (Seen) | KLD: 1.602 -> 1.555 | Improved |
| add ACP on top of AIM+CFT (ablation) | AIM+CFT · AGD20K mixed test (Unseen) | NSS: 0.912 -> 1.017 | Improved |
| add CFT on top of AIM+ACP (ablation) | AIM+ACP · AGD20K mixed test (Seen) | KLD: 1.641 -> 1.555 | Improved |
| train WSOL baseline with both exo and ego images | BAS · AGD20K mixed test (Seen) | KLD: 1.945 -> 2.188 | Hurt |
| train WSOL baseline with both exo and ego images | BAS · AGD20K mixed test (Unseen) | KLD: 2.223 -> 2.002 | Improved |
| train WSOL baseline with both exo and ego images | EIL · AGD20K mixed test (Seen) | KLD: 1.914 -> 1.983 | Hurt |
| train WSOL baseline with both exo and ego images | SPA · AGD20K mixed test (Seen) | KLD: 5.719 -> 5.057 | Improved |
Closest papers by meaning
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.93)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.90)
- Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors (ICLR 2025 · similarity 0.89)
- Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models (CVPR 2026 · similarity 0.89)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.89)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.88)
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.
