Papers › Demo2Vec: Reasoning Object Affordances From Online Videos
Demo2Vec: Reasoning Object Affordances From Online Videos
Kuan Fang, Te-Lin Wu, Daniel Yang, Silvio Savarese, Joseph J. Lim
Watching expert demonstrations is an important way for humans and robots to reason about affordances of unseen objects. In this paper, we consider the problem of reasoning object affordances through the feature embedding of demonstration videos. We design the Demo2Vec model which learns to extract embedded vectors of demonstration videos and predicts the interaction region and the action label on a target image of the same object. We introduce the Online Product Review dataset for Affordance (OPRA) by collecting and labeling diverse YouTube product review videos. Our Demo2Vec model outperforms various recurrent neural network baselines on the collected dataset.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video-to-image Affordance Grounding | OPRA | Demo2Vec | KLD | 2.34 | #3 of 3 | Archive leaderboard | report |
| Video-to-image Affordance Grounding | OPRA | Demo2Vec | Top-1 Action Accuracy | 40.79 | #3 of 3 | Archive leaderboard | report |
| Video-to-image Affordance Grounding | OPRA (28x28) | Demo2Vec | AUC-J | 0.85 | #2 of 4 | Archive leaderboard | report |
| Video-to-image Affordance Grounding | OPRA (28x28) | Demo2Vec | KLD | 1.20 | #2 of 4 | Archive leaderboard | report |
| Video-to-image Affordance Grounding | OPRA (28x28) | Demo2Vec | SIM | 0.48 | #2 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections