# Grounded Human-Object Interaction Hotspots from Video

arXiv: https://arxiv.org/abs/1812.04558 · HTML: https://mlsanity.com/paper/1812.04558/

## Key facts

- Cited by 129 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 30 of 129)

- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)
- [Structured World Models from Human Videos](https://mlsanity.com/paper/2308.10901/) (2023)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Affordance Diffusion: Synthesizing Hand-Object Interactions](https://mlsanity.com/paper/2303.12538/) (2023)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [Learning Affordance Grounding from Exocentric Images](https://mlsanity.com/paper/2203.09905/) (2022)
- [VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects](https://mlsanity.com/paper/2106.14440/) (2021)
- [Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance](https://mlsanity.com/paper/2403.18036/) (2024)
- [Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks](https://mlsanity.com/paper/2110.03655/) (2021)
- [Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications](https://mlsanity.com/paper/2208.03826/) (2022)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation](https://mlsanity.com/paper/2401.07487/) (2024)
- [UMPNet: Universal Manipulation Policy Network for Articulated Objects](https://mlsanity.com/paper/2109.05668/) (2021)
- [LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding](https://mlsanity.com/paper/2303.09665/) (2023)
- [Grounded Question-Answering in Long Egocentric Videos](https://mlsanity.com/paper/2312.06505/) (2023)
- [Grounding 3D Object Affordance from 2D Interactions in Images](https://mlsanity.com/paper/2303.10437/) (2023)
- [End-to-End Affordance Learning for Robotic Manipulation](https://mlsanity.com/paper/2209.12941/) (2022)
- [AffordanceLLM: Grounding Affordance from Vision Language Models](https://mlsanity.com/paper/2401.06341/) (2024)
- [Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces](https://mlsanity.com/paper/2503.19199/) (2025)
- [Human Hands as Probes for Interactive Object Understanding](https://mlsanity.com/paper/2112.09120/) (2021)
- [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)
- [LEMON: Learning 3D Human-Object Interaction Relation from 2D Images](https://mlsanity.com/paper/2312.08963/) (2023)
- [Forecasting Action through Contact Representations from First Person Video](https://mlsanity.com/paper/2102.00649/) (2021)
- [O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning](https://mlsanity.com/paper/2106.15087/) (2021)

## Abstract (arXiv)

Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction "hotspots" directly from video. Rather than treat affordances as a manually supervised semantic segmentation task, our approach learns about interactions by watching videos of real human behavior and anticipating afforded actions. Given a novel image or video, our model infers a spatial hotspot map indicating how an object would be manipulated in a potential interaction-- even if the object is currently at rest. Through results with both first and third person video, we show the value of grounding affordances in real human-object interactions. Not only are our weakly supervised hotspots competitive with strongly supervised affordance methods, but they can also anticipate object interaction for novel object categories.