Category Query Learning for Human-Object Interaction Classification

CVPR 2023  ·  Chi Xie, Fangao Zeng, Yue Hu, Shuang Liang, Yichen Wei ·

Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning. Such queries are explicitly associated to interaction categories, converted to image specific category representation via a transformer decoder, and learnt via an auxiliary image-level classification task. This idea is motivated by an earlier multi-label image classification method, but is for the first time applied for the challenging human-object interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-the-art results on two benchmarks.

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human-Object Interaction Detection HICO-DET CQL+GEN-VLKT-L mAP 36.03 # 8
Human-Object Interaction Detection HICO-DET CQL+GEN-VLKT-B mAP 35.36 # 10

Methods


No methods listed for this paper. Add relevant methods here