# Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)

Source: [Grounded Human-Object Interaction Hotspots from Video (Extended Abstract)](<https://www.sota2.com/research/paper/68fa65d81e209131cea0cb26>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:36:37.771Z

Authors: Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

Published: 2019-06-03T19:12:55.000Z

## Abstract

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. Project page: http://vision.cs.utexas.edu/projects/interaction-hotspots/

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.01963>)

[PDF](<https://arxiv.org/pdf/1906.01963.pdf>)