Papers › Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D...
Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D Short Term Object Interaction Anticipation Challenge
Hyunjin Cho, Dong Un Kang, Se Young Chun
Short-term object interaction anticipation is an important task in egocentric video analysis, including precise predictions of future interactions and their timings as well as the categories and positions of the involved active objects. To alleviate the complexity of this task, our proposed method, SOIA-DOD, effectively decompose it into 1) detecting active object and 2) classifying interaction and predicting their timing. Our method first detects all potential active objects in the last frame of egocentric video by fine-tuning a pre-trained YOLOv9. Then, we combine these potential active objects as query with transformer encoder, thereby identifying the most promising next active object and predicting its future interaction and time-to-contact. Experimental results demonstrate that our method outperforms state-of-the-art models on the challenge test set, achieving the best performance in predicting next active objects and their interactions. Finally, our proposed ranked the third overall top-5 mAP when including time-to-contact predictions. The source code is available at https://github.com/KeenyJin/SOIA-DOD.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Short-term Object Interaction Anticipation | Ego4D | SOIA-DOD | Noun (Top5 mAP) | 34.886 | #2 of 4 | Archive leaderboard | report |
| Short-term Object Interaction Anticipation | Ego4D | SOIA-DOD | Noun+TTC (Top5 mAP) | 10.907 | #2 of 4 | Archive leaderboard | report |
| Short-term Object Interaction Anticipation | Ego4D | SOIA-DOD | Noun+Verb(Top5 mAP) | 17.614 | #2 of 4 | Archive leaderboard | report |
| Short-term Object Interaction Anticipation | Ego4D | SOIA-DOD | Overall (Top5 mAP) | 6.221 | #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