# Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment

arXiv: https://arxiv.org/abs/2306.05526 · HTML: https://mlsanity.com/paper/2306.05526/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 87 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA](https://mlsanity.com/paper/1605.06336/) (2016)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Cross-task weakly supervised learning from instructional videos](https://mlsanity.com/paper/1903.08225/) (2019)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations](https://mlsanity.com/paper/2209.13064/) (2022)
- [VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors](https://mlsanity.com/paper/2210.11339/) (2022)
- [Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos](https://mlsanity.com/paper/1804.09626/) (2018)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)

## Built on by (most cited first, 30 of 46)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [EgoLife: Towards Egocentric Life Assistant](https://mlsanity.com/paper/2503.03803/) (2025)
- [Retrieval-Augmented Egocentric Video Captioning](https://mlsanity.com/paper/2401.00789/) (2024)
- [Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation](https://mlsanity.com/paper/2410.00263/) (2024)
- [Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos](https://mlsanity.com/paper/2403.06351/) (2024)
- [Seeing the Arrow of Time in Large Multimodal Models](https://mlsanity.com/paper/2506.03340/) (2025)
- [Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding](https://mlsanity.com/paper/2503.09143/) (2025)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos](https://mlsanity.com/paper/2504.11732/) (2025)
- [Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs](https://mlsanity.com/paper/2312.02638/) (2023)
- [Intention-driven Ego-to-Exo Video Generation](https://mlsanity.com/paper/2403.09194/) (2024)
- [IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos](https://mlsanity.com/paper/2411.11409/) (2024)
- [Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos](https://mlsanity.com/paper/2311.16444/) (2023)
- [Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?](https://mlsanity.com/paper/2405.17719/) (2024)
- [On-Robot Reinforcement Learning with Goal-Contrastive Rewards](https://mlsanity.com/paper/2410.19989/) (2024)
- [EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World](https://mlsanity.com/paper/2501.19061/) (2025)
- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly](https://mlsanity.com/paper/2604.10409/) (2026)
- [O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views](https://mlsanity.com/paper/2506.06026/) (2025)
- [Egocentric and Exocentric Methods: A Short Survey](https://mlsanity.com/paper/2410.20621/) (2024)
- [Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations](https://mlsanity.com/paper/2503.19706/) (2025)
- [What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning](https://mlsanity.com/paper/2503.21055/) (2025)
- [Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs](https://mlsanity.com/paper/2505.21955/) (2025)
- [Spherical World-Locking for Audio-Visual Localization in Egocentric Videos](https://mlsanity.com/paper/2408.05364/) (2024)
- [EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2503.15470/) (2025)
- [EgoExo-Con: Exploring View-Invariant Video Temporal Understanding](https://mlsanity.com/paper/2510.26113/) (2025)
- [Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos](https://mlsanity.com/paper/2403.05535/) (2024)
- [FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition](https://mlsanity.com/paper/2409.01448/) (2024)
- [ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition](https://mlsanity.com/paper/2504.03948/) (2025)

## Abstract (arXiv)

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to learning view-invariant features from paired synchronized viewpoints. We relax that strong data assumption and propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time, even when not captured simultaneously or in the same environment. To this end, we propose AE2, a self-supervised embedding approach with two key designs: (1) an object-centric encoder that explicitly focuses on regions corresponding to hands and active objects; and (2) a contrastive-based alignment objective that leverages temporally reversed frames as negative samples. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context, comprising four datasets -- including an ego tennis forehand dataset we collected, along with dense per-frame labels we annotated for each dataset. On the four datasets, our AE2 method strongly outperforms prior work in a variety of fine-grained downstream tasks, both in regular and cross-view settings.