Transformer-based methods have achieved great success in the field of human-object interaction (HOI) detection. However, these models tend to adopt semantically ambigu-ous queries, which lowers the transformer's representation learning power. Moreover, there are a very limited num-ber of labeled human-object pairs for most images in ex-isting datasets, which constrains the transformer's set pre-diction power. To handle the first problem, we propose an efficient knowledge distillation model, named Distillation using Oracle Queries (DOQ), which shares parameters be-tween teacher and student networks. The teacher network adopts oracle queries that are semantically clear and gener-ates high-quality decoder embeddings. By mimicking both the attention maps and decoder embeddings of the teacher network, the representation learning power of the student network is significantly promoted. To address the sec-ond problem, we introduce an efficient data augmentation method, named Context-Consistent Stitching (CCS), which generates complicated images online. Each new image is obtained by stitching labeled human-object pairs cropped from multiple training images. By selecting source images with similar context, the new synthesized image is made visually realistic. Our methods significantly promote both the accuracy and training efficiency of transformer-based HOI detection models. Experimental results show that our proposed approach consistently outperforms state-of-the-art methods on three benchmarks: HICO-DET, HOI-A, and V-COCO. Code is available at ht tps: / / gi thub. com/ SherlockHolmes221/DOQ.

Modern human-object interaction (HOI) detection approaches can be divided into one-stage methods and two-stage ones. One-stage models are more efficient due to their straightforward architectures, but the two-stage models are still advantageous in accuracy. Existing one-stage models usually begin by detecting predefined interaction areas or points, and then attend to these areas only for interaction prediction; therefore, they lack reasoning steps that dynamically search for discriminative cues. In this paper, we propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of action-aware points (ActPoints) via glance and gaze steps. The glance step quickly determines whether each pixel in the feature maps is an interaction point. The gaze step leverages feature maps produced by the glance step to adaptively infer ActPoints around each pixel in a progressive manner. Features of the refined ActPoints are aggregated for interaction prediction. Moreover, we design an action-aware approach that effectively matches each detected interaction with its associated human-object pair, along with a novel hard negative attentive loss to improve the optimization of GGNet. All the above operations are conducted simultaneously and efficiently for all pixels in the feature maps. Finally, GGNet outperforms state-of-the-art methods by significant margins on both V-COCO and HICO-DET benchmarks. Code of GGNet is available at https://github.com/SherlockHolmes221/GGNet.