End-to-End Human Object Interaction Detection with HOI Transformer

Abstract

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% AP role 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.

Towards Tokenized Human Dynamics Representation

“…For encoding the representation network f (•) of pose sequences in our task, we adopt the Transformer encoder network [54] for its superior performance on recent vision applications [7,16,34,42,60].…”