mlsanityData to 14 Oct 2026

EGO-TOPO: Environment Affordances from Egocentric Video

arXiv 2001.04583 ↗First posted 14 Jan 2020cs.CVcited by 111

Not on the map. Why?

Abstract (arXiv)

First-person video naturally brings the use of a physical environment to the forefront, since it shows the camera wearer interacting fluidly in a space based on his intentions. However, current methods largely separate the observed actions from the persistent space itself. We introduce a model for environment affordances that is learned directly from egocentric video. The main idea is to gain a human-centric model of a physical space (such as a kitchen) that captures (1) the primary spatial zones of interaction and (2) the likely activities they support. Our approach decomposes a space into a topological map derived from first-person activity, organizing an ego-video into a series of visits to the different zones. Further, we show how to link zones across multiple related environments (e.g., from videos of multiple kitchens) to obtain a consolidated representation of environment functionality. On EPIC-Kitchens and EGTEA+, we demonstrate our approach for learning scene affordances and anticipating future actions in long-form video.

Key facts. Cited by 111 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 16; 2023: 25; 2024: 26; 2025: 14; 2026: 13.

111 papers.

Sort:

By area:

  1. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 226
  2. 2021Anticipative Video Transformercited by 200
  3. 2021Towards Long-Form Video Understandingcited by 146
  4. 2022EgoTaskQA: Understanding Human Tasks in Egocentric Videoscited by 115
  5. 2022Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videoscited by 111
  6. 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
  7. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 99
  8. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 95
  9. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  10. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 81
  11. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 80
  12. 2022Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applicationscited by 78
38 more
  1. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 65
  2. 2022Real-time Online Video Detection with Temporal Smoothing Transformerscited by 58
  3. 2021Human Hands as Probes for Interactive Object Understandingcited by 52
  4. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  5. 2023EPIC Fields: Marrying 3D Geometry and Video Understandingcited by 49
  6. 2021Activity Graph Transformer for Temporal Action Localizationcited by 48
  7. 2021Forecasting Action through Contact Representations from First Person Videocited by 46
  8. 2024Retrieval-Augmented Egocentric Video Captioningcited by 42
  9. 2021Learning to Anticipate Egocentric Actions by Imaginationcited by 40
  10. 2023Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphscited by 39
  11. 2021Predicting the Future from First Person (Egocentric) Vision: A Surveycited by 36
  12. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 36
  13. 2022MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domaincited by 36
  14. 2024AMEGO: Active Memory from long EGOcentric videoscited by 36
  15. 2023Video-Mined Task Graphs for Keystep Recognition in Instructional Videoscited by 35
  16. 2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 34
  17. 2022Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detectioncited by 30
  18. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  19. 2023PALM: Predicting Actions through Language Modelscited by 29
  20. 2023Pretrained Language Models as Visual Planners for Human Assistancecited by 28
  21. 2024Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mindcited by 28
  22. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  23. 2023Learning Foresightful Dense Visual Affordance for Deformable Object Manipulationcited by 25
  24. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  25. 2023Object-centric Video Representation for Long-term Action Anticipationcited by 24
  26. 2022EgoEnv: Human-centric environment representations from egocentric videocited by 22
  27. 2023Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognitioncited by 20
  28. 2025Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMscited by 19
  29. 2023Multi-label affordance mapping from egocentric visioncited by 18
  30. 2021Shaping embodied agent behavior with activity-context priors from egocentric videocited by 17
  31. 2023SpotEM: Efficient Video Search for Episodic Memorycited by 17
  32. 2023Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videoscited by 15
  33. 2021UnweaveNet: Unweaving Activity Storiescited by 14
  34. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  35. 2023Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspectivecited by 14
  36. 2024AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipationcited by 14
  37. 2023Chop & Learn: Recognizing and Generating Object-State Compositionscited by 13
  38. 2024LLM-enhanced Scene Graph Learning for Household Rearrangementcited by 12

50 most cited of 111 All 111 (JSON)