paper-with-me

Papers

Grounded Human-Object Interaction Hotspots from Video

2018-12-11 · ICCV 2019 10 · Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

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.

📄 PDF Abstract BibTeX arXiv:1812.04558

Code (1)

Tushar-N/interaction-hotspots pytorch

Tasks

Human-Object Interaction DetectionObjectObject RecognitionSemantic SegmentationVideo-to-image Affordance Grounding

Similar Papers 제목 키워드 기반

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

2019-06-03 · Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman

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…

Human-Object Interaction DetectionObjectSemantic Segmentation

Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos

2022-04-04 · CVPR 2022 1 · Shaowei Liu, Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang

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 ac…

Object

Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video

2019-11-25 · ECCV 2020 8 · Miao Liu, Siyu Tang, Yin Li, James Rehg

We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate…

Action AnticipationHuman-Object Interaction Detection

Bidirectional Progressive Transformer for Interaction Intention Anticipation

2024-05-09 · Zichen Zhang, Hongchen Luo, Wei Zhai, Yang Cao 외

Interaction intention anticipation aims to jointly predict future hand trajectories and interaction hotspots. Existing research often treated trajectory forecasting and interaction hotspots prediction as separate tasks o…

PredictionTrajectory Forecasting

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

2026-02-02 · Youliang Zhang, Zhengguang Zhou, Zhentao Yu, Ziyao Huang 외 arxiv

Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task to grounded human-object interaction (G…

Video Generation