# Egocentric zone-aware action recognition across environments

arXiv: https://arxiv.org/abs/2409.14205 · HTML: https://mlsanity.com/paper/2409.14205/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [Grounded Human-Object Interaction Hotspots from Video](https://mlsanity.com/paper/1812.04558/) (2018)
- [AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection](https://mlsanity.com/paper/1709.07326/) (2017)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [Multi-Modal Domain Adaptation for Fine-Grained Action Recognition](https://mlsanity.com/paper/2001.09691/) (2020)
- [EGO-TOPO: Environment Affordances from Egocentric Video](https://mlsanity.com/paper/2001.04583/) (2020)
- [Heterogeneous Domain Generalization via Domain Mixup](https://mlsanity.com/paper/2009.05448/) (2020)
- [Temporal Attentive Alignment for Large-Scale Video Domain Adaptation](https://mlsanity.com/paper/1907.12743/) (2019)
- [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020)
- [Learning Dexterous Grasping with Object-Centric Visual Affordances](https://mlsanity.com/paper/2009.01439/) (2020)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [Slow-Fast Auditory Streams For Audio Recognition](https://mlsanity.com/paper/2103.03516/) (2021)
- [Prompt Vision Transformer for Domain Generalization](https://mlsanity.com/paper/2208.08914/) (2022)

## Built on by (most cited first, 6 of 6)

- [Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing](https://mlsanity.com/paper/2602.20597/) (2026)
- [Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videos](https://mlsanity.com/paper/2506.02167/) (2025)
- [Domain Generalization using Action Sequences for Egocentric Action Recognition](https://mlsanity.com/paper/2506.17685/) (2025)
- [Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention](https://mlsanity.com/paper/2512.24323/) (2025)
- [TRec: Learning Hand-Object Interactions through 2D Point Track Motion](https://mlsanity.com/paper/2601.03667/) (2026)
- [Ego4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoring](https://mlsanity.com/paper/2601.17056/) (2026)

## Abstract (arXiv)

Human activities exhibit a strong correlation between actions and the places where these are performed, such as washing something at a sink. More specifically, in daily living environments we may identify particular locations, hereinafter named activity-centric zones, which may afford a set of homogeneous actions. Their knowledge can serve as a prior to favor vision models to recognize human activities. However, the appearance of these zones is scene-specific, limiting the transferability of this prior information to unfamiliar areas and domains. This problem is particularly relevant in egocentric vision, where the environment takes up most of the image, making it even more difficult to separate the action from the context. In this paper, we discuss the importance of decoupling the domain-specific appearance of activity-centric zones from their universal, domain-agnostic representations, and show how the latter can improve the cross-domain transferability of Egocentric Action Recognition (EAR) models. We validate our solution on the EPIC-Kitchens-100 and Argo1M datasets