AI Paper Atlas

Research map / Video / Video segmentation and tracking

Integrating Affordances and Attention Models for Short-Term Object Interaction Anticipation

Lorenzo Mur-Labadia, Rubén Martínez-Cantín, J.J. Guerrero, Giovanni Maria Farinella, Antonino Furnari

TPAMI 2026 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add learned environment affordancesSTAformer++ · Ego4D-STA v1 valAll mAP: 4.31 -> 4.66Improved
add fixed environment affordances and interaction hotspotsSTAformer · Ego4D-STA v1 valAll mAP: 3.53 -> 3.77Improved
replace Faster R-CNN head with DETR head (ablation)DINOv2 image-only model · Ego4D-STA v1 valNoun mAP: 17.48 -> 29.33Improved
frame-guided attention temporal pooling instead of temporal convolution (ablation)STAformer · Ego4D-STA v1 valAll mAP: 2.94 -> 3.39Improved
compute temporal pooling per scale (ablation)STAformer++ · Ego4D-STA v1 valAll mAP: 4.07 -> 4.31Improved
dual image-video attention instead of sum fusion (ablation)STAformer · Ego4D-STA v1 valAll mAP: 3.39 -> 3.47Improved
use both-direction dual attention rather than one direction (ablation)STAformer · Ego4D-STA v1 valAll mAP: 3.01 -> 3.53Improved
EgoVideo (fine-tuned) instead of TimeSformer video encoder (ablation)STAformer++ · Ego4D-STA v1 valAll mAP: 2.89 -> 3.65Improved
fine-tune last blocks of Swin-T image encoder (ablation)STAformer++ image-only · Ego4D-STA v1 valAll mAP: 2.71 -> 2.85Improved
center prior to re-weight scores (ablation)STAformer · Ego4D-STA v1 valNoun mAP: 21.71 -> 17.70Hurt
hands proximity prior to re-weight scores (ablation)STAformer · Ego4D-STA v1 valNoun mAP: 21.71 -> 16.35Hurt
add interaction hotspots (ablation)STAformer++ · Ego4D-STA v1 valNoun mAP and N+V mAP: 32.07 -> 32.84 N mAP and 15.00 -> 15.67 N+V mAPImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy