# Challenges and Trends in Egocentric Vision: A Survey

arXiv: https://arxiv.org/abs/2503.15275 · HTML: https://mlsanity.com/paper/2503.15275/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 167 of its 238 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 30 of 167)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition](https://mlsanity.com/paper/1908.08498/) (2019)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields](https://mlsanity.com/paper/2210.13641/) (2022)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation](https://mlsanity.com/paper/2305.10874/) (2023)
- [Multiview Transformers for Video Recognition](https://mlsanity.com/paper/2201.04288/) (2022)

## Built on by (most cited first, 20 of 20)

- [FreeRet: MLLMs as Training-Free Retrievers](https://mlsanity.com/paper/2509.24621/) (2025)
- [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025)
- [LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks](https://mlsanity.com/paper/2603.00490/) (2026)
- [MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation](https://mlsanity.com/paper/2602.07082/) (2026)
- [EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR](https://mlsanity.com/paper/2603.04090/) (2026)
- [Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency](https://mlsanity.com/paper/2603.09798/) (2026)
- [Neuro-Symbolic Manipulation Understanding with Enriched Semantic Event Chains](https://mlsanity.com/paper/2604.21053/) (2026)
- [Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision](https://mlsanity.com/paper/2604.21461/) (2026)
- [Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models](https://mlsanity.com/paper/2606.09142/) (2026)
- [Evaluating the Impact of AI-Powered Audiovisual Personalization on Learner Emotion, Focus, and Learning Outcomes](https://mlsanity.com/paper/2505.03033/) (2025)
- [DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning](https://mlsanity.com/paper/2512.20409/) (2025)
- [Egocentric Gaze Estimation via Neck-Mounted Camera](https://mlsanity.com/paper/2602.11669/) (2026)
- [SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion](https://mlsanity.com/paper/2603.12764/) (2026)
- [FlatLands: Generative Floormap Completion From a Single Egocentric View](https://mlsanity.com/paper/2603.16016/) (2026)
- [Map-Mono-Ego: Map-Grounded Global Human Pose Estimation from Monocular Egocentric Video](https://mlsanity.com/paper/2605.20889/) (2026)
- [Impact of Hand Impairment and Occlusions on Hand Pose Estimation Accuracy in Augmented Reality Applications](https://mlsanity.com/paper/2606.17427/) (2026)
- [Understanding From Human Perspective: A Multi-agent System for Interactive Egocentric Medical Image Segmentation](https://mlsanity.com/paper/2607.17341/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)
- [PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance](https://mlsanity.com/paper/2609.14473/) (2026)
- [AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization](https://mlsanity.com/paper/2609.19793/) (2026)

## Abstract (arXiv)

With the rapid development of artificial intelligence technologies and wearable devices, egocentric vision understanding has emerged as a new and challenging research direction, gradually attracting widespread attention from both academia and industry. Egocentric vision captures visual and multimodal data through cameras or sensors worn on the human body, offering a unique perspective that simulates human visual experiences. This paper provides a comprehensive survey of the research on egocentric vision understanding, systematically analyzing the components of egocentric scenes and categorizing the tasks into four main areas: subject understanding, object understanding, environment understanding, and hybrid understanding. We explore in detail the sub-tasks within each category. We also summarize the main challenges and trends currently existing in the field. Furthermore, this paper presents an overview of high-quality egocentric vision datasets, offering valuable resources for future research. By summarizing the latest advancements, we anticipate the broad applications of egocentric vision technologies in fields such as augmented reality, virtual reality, and embodied intelligence, and propose future research directions based on the latest developments in the field.