# Interaction Region Visual Transformer for Egocentric Action Anticipation

arXiv: https://arxiv.org/abs/2211.14154 · HTML: https://mlsanity.com/paper/2211.14154/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 64 references that are in the map.
- First posted on arXiv 25 Nov 2022.

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Learning to Detect Human-Object Interactions](https://mlsanity.com/paper/1702.05448/) (2017)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers](https://mlsanity.com/paper/2106.05392/) (2021)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [HOTR: End-to-End Human-Object Interaction Detection with Transformers](https://mlsanity.com/paper/2104.13682/) (2021)
- [PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection](https://mlsanity.com/paper/1912.12898/) (2019)
- [iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection](https://mlsanity.com/paper/1808.10437/) (2018)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)
- [DRG: Dual Relation Graph for Human-Object Interaction Detection](https://mlsanity.com/paper/2008.11714/) (2020)
- [Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks](https://mlsanity.com/paper/1912.09930/) (2019)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Mining the Benefits of Two-stage and One-stage HOI Detection](https://mlsanity.com/paper/2108.05077/) (2021)
- [Reformulating HOI Detection as Adaptive Set Prediction](https://mlsanity.com/paper/2103.05983/) (2021)
- [Object-Region Video Transformers](https://mlsanity.com/paper/2110.06915/) (2021)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [Target Adaptive Context Aggregation for Video Scene Graph Generation](https://mlsanity.com/paper/2108.08121/) (2021)
- [From Lifestyle Vlogs to Everyday Interactions](https://mlsanity.com/paper/1712.02310/) (2017)
- [Integrating Human Gaze into Attention for Egocentric Activity Recognition](https://mlsanity.com/paper/2011.03920/) (2020)
- [Predicting the Future: A Jointly Learnt Model for Action Anticipation](https://mlsanity.com/paper/1912.07148/) (2019)

## Built on by (most cited first, 30 of 37)

- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views](https://mlsanity.com/paper/2405.13659/) (2024)
- [Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos](https://mlsanity.com/paper/2406.01486/) (2024)
- [Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding](https://mlsanity.com/paper/2503.09143/) (2025)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos](https://mlsanity.com/paper/2409.02638/) (2024)
- [The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation](https://mlsanity.com/paper/2504.08654/) (2025)
- [AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2406.01194/) (2024)
- [A Survey on Deep Learning Techniques for Action Anticipation](https://mlsanity.com/paper/2309.17257/) (2023)
- [Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding](https://mlsanity.com/paper/2510.21356/) (2025)
- [Semantically Guided Representation Learning For Action Anticipation](https://mlsanity.com/paper/2407.02309/) (2024)
- [Human Action Anticipation: A Survey](https://mlsanity.com/paper/2410.14045/) (2024)
- [Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views](https://mlsanity.com/paper/2511.12878/) (2025)
- [VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation](https://mlsanity.com/paper/2307.03918/) (2023)
- [Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing](https://mlsanity.com/paper/2602.20597/) (2026)
- [MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation](https://mlsanity.com/paper/2501.08837/) (2025)
- [Action-Guided Attention for Video Action Anticipation](https://mlsanity.com/paper/2603.01743/) (2026)
- [Anticipating Object State Changes in Long Procedural Videos](https://mlsanity.com/paper/2405.12789/) (2024)
- [From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation](https://mlsanity.com/paper/2408.02769/) (2024)
- [RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation](https://mlsanity.com/paper/2603.27165/) (2026)
- [Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos](https://mlsanity.com/paper/2604.03667/) (2026)
- [EgoSelf: From Memory to Personalized Egocentric Assistant](https://mlsanity.com/paper/2604.19564/) (2026)
- [Modelling Spatio-Temporal Interactions For Compositional Action Recognition](https://mlsanity.com/paper/2305.02673/) (2023)
- [EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos](https://mlsanity.com/paper/2508.12349/) (2025)
- [EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction](https://mlsanity.com/paper/2510.21786/) (2025)
- [Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation](https://mlsanity.com/paper/2602.14837/) (2026)
- [How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction](https://mlsanity.com/paper/2605.20388/) (2026)
- [FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration](https://mlsanity.com/paper/2606.14778/) (2026)
- [Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding](https://mlsanity.com/paper/2510.10682/) (2025)

## Abstract (arXiv)

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.