TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Human-Object Interaction Detection	HICO-DET	GPNN	mAP	13.11	# 52
Human-Object Interaction Detection	V-COCO	GPNN	AP(S1)	44.0	# 32

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-human-object-interactions-by-graph/human-object-interaction-detection-on-v-coco)](https://paperswithcode.com/sota/human-object-interaction-detection-on-v-coco?p=learning-human-object-interactions-by-graph)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-human-object-interactions-by-graph/human-object-interaction-detection-on-hico)](https://paperswithcode.com/sota/human-object-interaction-detection-on-hico?p=learning-human-object-interactions-by-graph)`

Learning Human-Object Interactions by Graph Parsing Neural Networks

ECCV 2018 · Siyuan Qi, Wenguan Wang, Baoxiong Jia, Jianbing Shen, Song-Chun Zhu ·

This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end. For a given scene, GPNN infers a parse graph that includes i) the HOI graph structure represented by an adjacency matrix, and ii) the node labels. Within a message passing inference framework, GPNN iteratively computes the adjacency matrices and node labels. We extensively evaluate our model on three HOI detection benchmarks on images and videos: HICO-DET, V-COCO, and CAD-120 datasets. Our approach significantly outperforms state-of-art methods, verifying that GPNN is scalable to large datasets and applies to spatial-temporal settings. The code is available at https://github.com/SiyuanQi/gpnn.