A toolkit developed to help analyzing existing Human-Object Interaction (HOI) detection methods, for research purpose. Not maintained but might still work for the majority of HOI methods..
-
Updated
Jul 11, 2023 - Python
A toolkit developed to help analyzing existing Human-Object Interaction (HOI) detection methods, for research purpose. Not maintained but might still work for the majority of HOI methods..
3D Human-Object Interaction in Video A New Approach to Object Tracking via Cross-Modal Attention
Learning Precise Affordances from Egocentric Videos for Robotic Manipulation (ICCV 2025)
CHAIR: 3D Human-Interaction Dataset. Human Object Interaction (HOI) dataset, focusing on interactions between humans and chairs.
[ICCV'25] Method for generating static human-object interactions
This is the official repository of the paper "Object size prediction from hand movement using a single RGB sensor". It contains the implementation, the dataset and the supplemental material of our work.
🚴♂️ ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection (MM 2020)
Official implementation for the CVPR'23 paper: Visibility Aware Human-Object Interaction Tracking from Single RGB Camera
[AAAI 2022] Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics.
Utilities for the dataset V-COCO in Python3
[ECCV 2022] SAGA: Stochastic Whole-Body Grasping with Contact
[ICCV 2023] RLIPv2: Fast Scaling of Relational Language-Image Pre-training
One-Stage HOI detection code: Visual Compositional Learning for Human-Object Interaction Detection (ECCV2020), Affordance Transfer Learning for Human-Object Interaction Detection (CVPR2021)
[CVPR'23] Method to infer objects from human interactions
Code for the ECCV'22 paper "Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos".
Code for our paper "Category Query Learning for Human-Object Interaction Classification" (CVPR2023)
[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation
The official code for Relational Context Learning for Human-Object Interaction Detection, CVPR2023.
Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human Interaction Motions in Scenes with Text Control".
Add a description, image, and links to the human-object-interaction topic page so that developers can more easily learn about it.
To associate your repository with the human-object-interaction topic, visit your repo's landing page and select "manage topics."