HCVRD: A Benchmark for Large-Scale Human-Centered Visual Relationship Detection

Authors

  • Bohan Zhuang The University of Adelaide
  • Qi Wu The University of Adelaide
  • Chunhua Shen The University of Adelaide
  • Ian Reid The University of Adelaide
  • Anton van den Hengel The University of Adelaide

Abstract

Visual relationship detection aims to capture interactions between pairs of objects in images. Relationships between objects and humans represent a particularly important subset of this problem, with implications for challenges such as understanding human behavior, and identifying affordances, amongst others. In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotations (nearly 10K categories) than the previous released datasets. This large label space better reflects the reality of human-object interactions, but gives rise to a long-tail distribution problem, which in turn demands a zero-shot approach to labels appearing only in the test set. This is the first time this issue has been addressed. We propose a webly-supervised approach to these problems and demonstrate that the proposed model provides a strong baseline on our HCVRD dataset.

Downloads

Published

2018-04-27

How to Cite

Zhuang, B., Wu, Q., Shen, C., Reid, I., & van den Hengel, A. (2018). HCVRD: A Benchmark for Large-Scale Human-Centered Visual Relationship Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12260