Category Query Learning for Human-Object Interaction Classification
This addresses the problem of improving classification accuracy in human-object interaction tasks for computer vision applications, representing an incremental advancement.
The paper tackles human-object interaction classification by introducing category query learning, a method that associates queries with interaction categories and converts them to image-specific representations via a transformer decoder, achieving new state-of-the-art results on two benchmarks.
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.