paper-with-me

Video-to-image Affordance Grounding 벤치마크

Video-to-image Affordance Grounding on OPRA (28x28)

4개 결과 · ⬇ CSV · JSON

KLD

1.05 1.155 1.26 1.365 1.47 2018-06 2026-09 Demo2Vec — 1.2 (2018-06-01) Hotspot — 1.47 (2018-12-11) HAG-Net (+Hand Box) — 1.41 (2021-08-12) Afformer — 1.05 (2023-03-26) Demo2Vec — 1.2 (2018-06-01) Hotspot — 1.47 (2018-12-11)
RankModel KLDSIMAUC-J PaperCodeYear
1 Afformer 1.050.530.89 Affordance Grounding from Demonstration Video to Target Image showlab/afformer 2023
2 Demo2Vec 1.200.480.85 Demo2Vec: Reasoning Object Affordances From Online Videos 2018
3 HAG-Net (+Hand Box) 1.410.370.81 Learning Visual Affordance Grounding from Demonstration Videos 2021
4 Hotspot 1.470.360.81 Grounded Human-Object Interaction Hotspots from Video Tushar-N/interaction-hotspots 2018
1–4 / 4 페이지당 10 20 50 100