# Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning

arXiv: https://arxiv.org/abs/2503.00986 · HTML: https://mlsanity.com/paper/2503.00986/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 71 references that are in the map.
- First posted on arXiv 2 Mar 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (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)
- [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)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception](https://mlsanity.com/paper/2306.06362/) (2023)
- [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021)
- [Language-Driven Representation Learning for Robotics](https://mlsanity.com/paper/2302.12766/) (2023)

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

- [A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning](https://mlsanity.com/paper/2509.15937/) (2025)
- [villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models](https://mlsanity.com/paper/2507.23682/) (2025)
- [What Do Latent Action Models Actually Learn?](https://mlsanity.com/paper/2506.15691/) (2025)
- [A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation](https://mlsanity.com/paper/2602.01067/) (2026)
- [EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT](https://mlsanity.com/paper/2510.23569/) (2025)
- [Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation](https://mlsanity.com/paper/2606.17030/) (2026)
- [Learning Additively Compositional Latent Actions for Embodied AI](https://mlsanity.com/paper/2604.03340/) (2026)
- [Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance](https://mlsanity.com/paper/2505.14346/) (2025)
- [HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics](https://mlsanity.com/paper/2512.00885/) (2025)
- [SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting](https://mlsanity.com/paper/2511.18127/) (2025)
- [CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild](https://mlsanity.com/paper/2602.17770/) (2026)
- [VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2605.31351/) (2026)
- [Show, Don't Tell: Detecting Novel Objects by Watching Human Videos](https://mlsanity.com/paper/2603.12751/) (2026)
- [Hand Trajectory Fusion for Egocentric Natural Language Query Grounding](https://mlsanity.com/paper/2606.02962/) (2026)
- [From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language Models](https://mlsanity.com/paper/2606.15417/) (2026)
- [SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding](https://mlsanity.com/paper/2607.04017/) (2026)
- [Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?](https://mlsanity.com/paper/2607.08514/) (2026)
- [Semantic Anchoring for Robotic Action Representations](https://mlsanity.com/paper/2607.13597/) (2026)
- [Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition](https://mlsanity.com/paper/2607.19889/) (2026)
- [G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding](https://mlsanity.com/paper/2608.20157/) (2026)

## Abstract (arXiv)

In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature. However, existing egocentric video representation learning methods mainly focus on aligning video representation with high-level narrations, overlooking the intricate dynamics between hands and objects. In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process. Since no suitable data is available, we introduce HOD, a novel pipeline employing a hand-object detector and a large language model to generate high-quality narrations with detailed descriptions of hand-object dynamics. To learn these fine-grained dynamics, we propose EgoVideo, a model with a new lightweight motion adapter to capture fine-grained hand-object motion information. Through our co-training strategy, EgoVideo effectively and efficiently leverages the fine-grained hand-object dynamics in the HOD data. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple egocentric downstream tasks, including improvements of 6.3% in EK-100 multi-instance retrieval, 5.7% in EK-100 classification, and 16.3% in EGTEA classification in zero-shot settings. Furthermore, our model exhibits robust generalization capabilities in hand-object interaction and robot manipulation tasks. Code and data are available at https://github.com/OpenRobotLab/EgoHOD/.