# Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos

arXiv: https://arxiv.org/abs/2204.01696 · HTML: https://mlsanity.com/paper/2204.01696/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 94 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 30 of 61)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [Unsupervised Learning for Physical Interaction through Video Prediction](https://mlsanity.com/paper/1605.07157/) (2016)

## Built on by (most cited first, 30 of 111)

- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2409.16283/) (2024)
- [Structured World Models from Human Videos](https://mlsanity.com/paper/2308.10901/) (2023)
- [EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations](https://mlsanity.com/paper/2209.13064/) (2022)
- [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [Affordance Diffusion: Synthesizing Hand-Object Interactions](https://mlsanity.com/paper/2303.12538/) (2023)
- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [General Flow as Foundation Affordance for Scalable Robot Learning](https://mlsanity.com/paper/2401.11439/) (2024)
- [Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation](https://mlsanity.com/paper/2401.07487/) (2024)
- [EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning](https://mlsanity.com/paper/2312.06722/) (2023)
- [LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2303.09665/) (2023)
- [RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2407.04689/) (2024)
- [Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans](https://mlsanity.com/paper/2312.00775/) (2023)
- [Zero-Shot Robot Manipulation from Passive Human Videos](https://mlsanity.com/paper/2302.02011/) (2023)
- [Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment](https://mlsanity.com/paper/2306.05526/) (2023)
- [VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2503.07135/) (2025)
- [One-Shot Open Affordance Learning with Foundation Models](https://mlsanity.com/paper/2311.17776/) (2023)
- [HRP: Human Affordances for Robotic Pre-Training](https://mlsanity.com/paper/2407.18911/) (2024)
- [G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis](https://mlsanity.com/paper/2404.12383/) (2024)
- [Interaction Region Visual Transformer for Egocentric Action Anticipation](https://mlsanity.com/paper/2211.14154/) (2022)
- [Affordance Grounding from Demonstration Video to Target Image](https://mlsanity.com/paper/2303.14644/) (2023)
- [Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting](https://mlsanity.com/paper/2307.08243/) (2023)
- [Learning Precise Affordances from Egocentric Videos for Robotic Manipulation](https://mlsanity.com/paper/2408.10123/) (2024)
- [HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models](https://mlsanity.com/paper/2503.19157/) (2025)
- [EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding](https://mlsanity.com/paper/2301.02217/) (2023)

## Abstract (arXiv)

We propose to forecast future hand-object interactions given an egocentric video. Instead of predicting action labels or pixels, we directly predict the hand motion trajectory and the future contact points on the next active object (i.e., interaction hotspots). This relatively low-dimensional representation provides a concrete description of future interactions. To tackle this task, we first provide an automatic way to collect trajectory and hotspots labels on large-scale data. We then use this data to train an Object-Centric Transformer (OCT) model for prediction. Our model performs hand and object interaction reasoning via the self-attention mechanism in Transformers. OCT also provides a probabilistic framework to sample the future trajectory and hotspots to handle uncertainty in prediction. We perform experiments on the Epic-Kitchens-55, Epic-Kitchens-100, and EGTEA Gaze+ datasets, and show that OCT significantly outperforms state-of-the-art approaches by a large margin. Project page is available at https://stevenlsw.github.io/hoi-forecast .