Papers › Interaction Region Visual Transformer for Egocentric Action Anticipation

Interaction Region Visual Transformer for Egocentric Action Anticipation

25 Nov 2022IEEE WACV 2024 1arXiv:2211.14154archive 2025-07-28

Debaditya Roy, Ramanathan Rajendiran, Basura Fernando

Human-object interaction is one of the most important visual cues and we propose a novel way to represent human-object interactions for egocentric action anticipation. We propose a novel transformer variant to model interactions by computing the change in the appearance of objects and human hands due to the execution of the actions and use those changes to refine the video representation. Specifically, we model interactions between hands and objects using Spatial Cross-Attention (SCA) and further infuse contextual information using Trajectory Cross-Attention to obtain environment-refined interaction tokens. Using these tokens, we construct an interaction-centric video representation for action anticipation. We term our model InAViT which achieves state-of-the-art action anticipation performance on large-scale egocentric datasets EPICKTICHENS100 (EK100) and EGTEA Gaze+. InAViT outperforms other visual transformer-based methods including object-centric video representation. On the EK100 evaluation server, InAViT is the top-performing method on the public leaderboard (at the time of submission) where it outperforms the second-best model by 3.3% on mean-top5 recall.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lahaproject/inavit mentioned on GitHubpytorch report

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

Action AnticipationHuman-Object Interaction DetectionObject

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Anticipation EGTEA InAViT Top-1 Accuracy 67.8 #2 of 3 Archive leaderboard report
Action Anticipation EPIC-KITCHENS-100 InAViT Recall@5 25.89 #2 of 9 Archive leaderboard report
Action Anticipation EPIC-KITCHENS-100 (test) InAViT recall@5 23.75 #1 of 8 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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