mlsanityData to 7 Oct 2026

Rescaling Egocentric Vision

arXiv 2006.13256 ↗First posted 23 Jun 2020cs.CV cs.LGcited by 529

Not on the map. Why?

Cited by 36 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics

Key facts. Cited by 529 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 54; 2023: 101; 2024: 122; 2025: 115; 2026: 130.

529 papers.

Sort:

By area:

  1. 2023Segment Anythingcited by 8,158
  2. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  3. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  4. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  5. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Modelscited by 310
  6. 2024Latent Action Pretraining from Videoscited by 302
  7. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 301
  8. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 276
  9. 2022Masked Visual Pre-training for Motor Controlcited by 246
  10. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  11. 2022Egocentric Video-Language Pretrainingcited by 231
  12. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
38 more
  1. 2024VideoLLM-online: Online Video Large Language Model for Streaming Videocited by 216
  2. 2022Learning Video Representations from Large Language Modelscited by 204
  3. 2023Video Understanding with Large Language Models: A Surveycited by 203
  4. 2022ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learningcited by 192
  5. 2022MERLOT Reserve: Neural Script Knowledge through Vision and Language and Soundcited by 184
  6. 2023Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perceptioncited by 166
  7. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  8. 2023HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real Worldcited by 159
  9. 2022Multiview Transformers for Video Recognitioncited by 148
  10. 2023TriDet: Temporal Action Detection with Relative Boundary Modelingcited by 141
  11. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  12. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  13. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  14. 2023EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbonecited by 130
  15. 2024LITA: Language Instructed Temporal-Localization Assistantcited by 124
  16. 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 122
  17. 2023VideoLLM: Modeling Video Sequence with Large Language Modelscited by 116
  18. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  19. 2022EgoTaskQA: Understanding Human Tasks in Egocentric Videoscited by 112
  20. 2022Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videoscited by 110
  21. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  22. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 106
  23. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 104
  24. 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 103
  25. 2024VideoPrism: A Foundational Visual Encoder for Video Understandingcited by 103
  26. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  27. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  28. 2024Deep Multimodal Learning with Missing Modality: A Surveycited by 89
  29. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  30. 2023An Outlook into the Future of Egocentric Visioncited by 84
  31. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  32. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 78
  33. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 69
  34. 2025Large Video Planner Enables Generalizable Robot Controlcited by 67
  35. 2023HierVL: Learning Hierarchical Video-Language Embeddingscited by 66
  36. 2023EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planningcited by 66
  37. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 61
  38. 2024Real-World Robot Applications of Foundation Models: A Reviewcited by 60

50 most cited of 529 All 529 (JSON)