mlsanityData to 14 Oct 2026

Egocentric zone-aware action recognition across environments

arXiv 2409.14205 ↗First posted 21 Sep 2024cs.CVcited by 6

Not on the map. Why?

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

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

43 of 53 references.

References · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2018SlowFast Networks for Video Recognitioncited by 1,867
  6. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  7. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  9. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  10. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  11. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  12. 2020Rescaling Egocentric Visioncited by 540
31 more
  1. 2019What Makes Training Multi-Modal Classification Networks Hard?cited by 344
  2. 2017Temporal Relational Reasoning in Videoscited by 324
  3. 2019EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognitioncited by 226
  4. 2018Grounded Human-Object Interaction Hotspots from Videocited by 129
  5. 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 128
  6. 2020Rolling-Unrolling LSTMs for Action Anticipation from First-Person Videocited by 120
  7. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  8. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  9. 2020EGO-TOPO: Environment Affordances from Egocentric Videocited by 111
  10. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  11. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  12. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  13. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 85
  14. 2023An Outlook into the Future of Egocentric Visioncited by 84
  15. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  16. 2020Towards Universal Representation Learning for Deep Face Recognitioncited by 78
  17. 2021Slow-Fast Auditory Streams For Audio Recognitioncited by 56
  18. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  19. 2021E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognitioncited by 50
  20. 2019Dance with Flow: Two-in-One Stream Action Detectioncited by 30
  21. 2023What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locationscited by 25
  22. 2019Learning Grasp Affordance Reasoning through Semantic Relationscited by 23
  23. 2018Visual Affordance and Function Understanding: A Surveycited by 20
  24. 2016Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensorscited by 18
  25. 2019Affordance Learning for End-to-End Visuomotor Robot Controlcited by 18
  26. 2023Multi-label affordance mapping from egocentric visioncited by 18
  27. 2023Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videoscited by 15
  28. 2019VideoDG: Generalizing Temporal Relations in Videos to Novel Domainscited by 14
  29. 2017Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactionscited by 8
  30. 2021Affordance-Based Mobile Robot Navigation Among Movable Obstaclescited by 7
  31. 2022Bringing Online Egocentric Action Recognition into the wildcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2026Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsingcited by 4
  2. 2025Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videoscited by 2
  3. 2025Domain Generalization using Action Sequences for Egocentric Action Recognitioncited by 1
  4. 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Interventioncited by 1
  5. 2026TRec: Learning Hand-Object Interactions through 2D Point Track Motioncited by 1
  6. 2026Ego4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoringcited by 0