GID-Net: Detecting human-object interaction with global and instance dependency

Publisher:
Elsevier BV
Publication Type:
Journal Article
Citation:
Neurocomputing, 2020
Issue Date:
2020-01-01
Filename Description Size
Neurocomputing-D-M-Yang.pdfPublished version3.8 MB
Adobe PDF
Full metadata record
© 2020 Elsevier B.V. Since detecting and recognizing individual human or object are not adequate to understand the visual world, learning how humans interact with surrounding objects becomes a core technology. However, convolution operations are weak in depicting visual interactions between the instances since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human perception in observing HOIs to introduce a two-stage trainable reasoning mechanism, referred to as GID block. GID block breaks through the local neighborhoods and captures long-range dependency of pixels both in global-level and instance-level from the scene to help detecting interactions between instances. Furthermore, we conduct a multi-stream network called GID-Net, which is a human-object interaction detection framework consisting of a human branch, an object branch and an interaction branch. Semantic information in global-level and local-level are efficiently reasoned and aggregated in each of the branches. We have compared our proposed GID-Net with existing state-of-the-art methods on two public benchmarks, including V-COCO and HICO-DET. The results have showed that GID-Net outperforms the existing best-performing methods on both the above two benchmarks, validating its efficacy in detecting human-object interactions.
Please use this identifier to cite or link to this item: