End-to-End Human Object Interaction Detection with HOI Transformer
By Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qianyu Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Yichen Wei. 2021
268 citations recorded by the source corpus.
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner. Current approaches either decouple HOI task into separated stages of object detection and interaction classification or introduce surrogate interaction problem. In contrast, our method, named HOI Transformer, streamlines the HOI pipeline by eliminating the need for many hand-designed components. HOI Transformer reasons about the relations of objects and humans from global image context and directly predicts HOI instances in parallel. A quintuple matching loss is introduced to force HOI predictions in a unified way. Our method is conceptually much simpler and demonstrates improved accuracy. Without bells and whistles, HOI Transformer achieves 26.61% AP on HICO-DET and 52.9% AProle on V-COCO, surpassing previous methods with the advantage of being much simpler. We hope our approach will serve as a simple and effective alternative for HOI tasks. Code is available at https://github.com/bbepoch/HoiTransformer.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Jitendra Malik
- Li Fei-Fei
- Abhinav Kumar Gupta
- Xiaogang Wang
- Trevor Darrell
Citations in the corpus
- EDTER: Edge Detection with Transformer (2022, methodology): “Recently, it is applied in conjunction with CNN in DETR [7] and the other variants [10, 27, 31, 58, 73].”
- Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models (2022, methodology): “By adapting TPT to context-dependent visual reasoning, we outperform the state-of-the-art method [17] by 4.1% Bongard-HOI benchamrk [16].”
- Webly Supervised Concept Expansion for General Purpose Vision Models (2022, result): “Although recent models [33,84,80] show results up to 32.”