mlsanityData to 7 Oct 2026

Egocentric and Exocentric Methods: A Short Survey

arXiv 2410.20621 ↗First posted 27 Oct 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The community has regained interest in the field of egocentric vision. While the third-person view and first-person have been thoroughly investigated, very few works aim to study both synchronously. Exocentric videos contain many relevant signals that are transferrable to egocentric videos. This paper provides a timely overview of works combining egocentric and exocentric visions, a very new but promising research topic. We describe in detail the datasets and present a survey of the key applications of ego-exo joint learning, where we identify the most recent advances. With the presentation of the current status of the progress, we believe this short but timely survey will be valuable to the broad video-understanding community, particularly when multi-view modeling is critical.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 75 of its 137 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

75 of 137 references.

References · 75

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2014Conditional Generative Adversarial Netscited by 2,152
  7. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  8. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  9. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  10. 2020Rescaling Egocentric Visioncited by 529
  11. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  12. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
38 more
  1. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  2. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  3. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
  4. 2019Cross-task weakly supervised learning from instructional videoscited by 199
  5. 2022Human-to-Robot Imitation in the Wildcited by 157
  6. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  7. 2018Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videoscited by 127
  8. 2021Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localizationcited by 112
  9. 2018Actor and Observer: Joint Modeling of First and Third-Person Videoscited by 102
  10. 2023Street-View Image Generation from a Bird's-Eye View Layoutcited by 102
  11. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 98
  12. 2019Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translationcited by 97
  13. 2020The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Posecited by 95
  14. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  15. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  16. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 79
  17. 2018Cross-View Image Synthesis using Conditional GANscited by 69
  18. 2023LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Groundingcited by 64
  19. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 55
  20. 2021Home Action Genome: Cooperative Compositional Action Understandingcited by 52
  21. 2022Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulationcited by 49
  22. 2020LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activitiescited by 46
  23. 2022Vision-Based Manipulators Need to Also See from Their Handscited by 46
  24. 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignmentcited by 46
  25. 2020MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detectioncited by 44
  26. 2024Retrieval-Augmented Egocentric Video Captioningcited by 42
  27. 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuningcited by 42
  28. 2018Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interactioncited by 40
  29. 2024EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understandingcited by 35
  30. 2023Affordance Grounding from Demonstration Video to Target Imagecited by 34
  31. 2024Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videoscited by 32
  32. 2024Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Modelscited by 32
  33. 2020Affordances in Robotic Tasks -- A Surveycited by 28
  34. 2020Multi-Channel Attention Selection GANs for Guided Image-to-Image Translationcited by 23
  35. 2022Grounded Affordance from Exocentric Viewcited by 21
  36. 2020Comprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluationcited by 20
  37. 2021Cross-View Exocentric to Egocentric Video Synthesiscited by 20
  38. 2023Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognitioncited by 20

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondencecited by 12
  2. 2025Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Visioncited by 8
  3. 2025EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Posescited by 7
  4. 2025Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challengescited by 5
  5. 2026BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Citiescited by 0
  6. 2026UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learningcited by 0