Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of egocentric (first-person) vision and related area resources
| Date | Stars |
|---|---|
| 2026-07-24 | 335 |
| 2026-07-25 | 335 |
| 2026-07-28 | 336 |
| 2026-07-30 | 336 |
| 2026-08-06 | 336 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Egocentric Vision [](https://awesome.re)
> A curated list of egocentric vision resources.
Egocentric (first-person) vision is a sub-field of computer vision that analyses image/video data obtained using a wearable camera simulating a person's visual field.
## Getting Started
New to egocentric vision? A few landmark resources already in this list are a good entry point:
- **Start here:** [An Outlook into the Future of Egocentric Vision](https://arxiv.org/abs/2308.07123) (IJCV 2024) is a broad survey of the field's tasks, datasets, and open challenges
- **Foundational datasets:** [Ego4D](https://ego4d-data.org), [EPIC-Kitchens 2020](https://epic-kitchens.github.io/2020-100), [Ego-Exo4D](https://ego-exo4d-data.org)
Papers below are grouped by task first (see [Papers](#papers)), then cross-listed by venue for browsing recent conference proceedings; each section is collapsed by default, click "Show papers" to expand. Datasets are listed separately in [Datasets](#datasets), with a highlights table of flagship datasets followed by the full index.
## Contents
- [Papers](#papers)
> Clustered into various problem statements.
- [Action/Activity Recognition](#ActionActivity-Recognition)
- [Object/Hand Recognition](#ObjectHand-Recognition)
- [Action/Gaze Anticipation](#ActionGaze-Anticipation)
- [Localization](#Localization)
- [Clustering](#Clustering)
- [Video Summarization](#Video-Summarization)
- [Social Interactions](#Social-Interactions)
- [Pose Estimation](#Pose-Estimation)
- [Human Object Interaction](#Human-Object-Interaction)
- [Temporal Boundary Detection](#Temporal-Boundary-Detection)
- [Privacy in Egocentric Videos](#Privacy-in-Egocentric-Videos)
- [Multiple Egocentric Tasks](#Multiple-Egocentric-Tasks)
- [Task Understanding](#Task-Understanding)
- [Ego-Exo Cross-View Learning](#ego-exo-cross-view-learning)
- [Egocentric Video-Language Models & Question Answering](#egocentric-video-language-models--question-answering)
- [Egocentric Video Generation & World Models](#egocentric-video-generation--world-models)
- [3D Scene Reconstruction & Mapping](#3d-scene-reconstruction--mapping)
- [Assistive & Navigation](#assistive--navigation)
- [Miscellaneous (New Tasks)](#Miscellaneous-New-Tasks)
> Clustered according to the conferences.
- [CVPR](#CVPR)
- [ECCV](#ECCV)
- [ICCV](#ICCV)
- [WACV](#WACV)
- [BMVC](#BMVC)
- [NeurIPS](#neurips)
- [Datasets](#datasets)
- [Workshops/Tutorials](#workshopstutorials)
## Papers
> Clustered in various problem statements.
### Action/Activity Recognition
<details>
<summary>Show papers (44)</summary>
- [ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition](https://arxiv.org/abs/2504.03948) - Sanjoy Kundu, Shanmukha Vellamcheti, and Sathyanarayanan N. Aakur. In ICCV 2025.
- [Understanding Multi-Task Activities from Single-Task Videos](https://openaccess.thecvf.com/content/CVPR2025/html/Shen_Understanding_Multi-Task_Activities_from_Single-Task_Videos_CVPR_2025_paper.html) - Yuhan Shen and Ehsan Elhamifar. In CVPR 2025.
- [Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos](https://arxiv.org/abs/2404.15161) - Merey Ramazanova, Alejandro Pardo, Bernard Ghanem, and Motasem Alfarra. In ICLR 2025.
- [On the Utility of 3D Hand Poses for Action Recognition](https://arxiv.org/abs/2403.09805) - Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, and Angela Yao. In ECCV 2024. [[project page]](https://s-shamil.github.io/HandFormer/)
- [SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos](https://arxiv.org/abs/2404.05206) - Changan Chen, Kumar Ashutosh, Rohit Girdhar, David Harwath, and Kristen Grauman. In CVPR 2024. [[project page]](https://vision.cs.utexas.edu/projects/soundingactions)
- [X-MIC: Cross-Modal Instance Conditioning for Egocentric Action GenExcerpt of 237,350 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e698375e17f6ff8d, topic:awesome, topic:awesome-list, desc:curated list
matched fp:e698375e17f6ff8d, topic:computer-vision, readme:computer vision, readme:pose estimation