Category Query Learning for Human-Object Interaction Classification

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 humanobject interaction classification task. Our method is simple, general and effective. It is validated on three representative HOI baselines and achieves new state-of-theart results on two benchmarks. Code will be available at https://github.com/charles-xie/CQL .