Exploiting Scene Graphs for Human-Object Interaction Detection

Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 15984-15993


Human-Object Interaction (HOI) detection is a fundamental visual task aiming at localizing and recognizing interactions between humans and objects. Existing works focus on the visual and linguistic features of humans and objects. However, they do not captalise on the high-level and semantic relationships present in the image, which provides crucial contextual and detailed relational knowledge for HOI inference. We propose a novel method to exploit this information, through the scene graph, for the HumanObject Interaction (SG2HOI) detection task. Our method, SG2HOI, incorporates the SG information in two ways: (1) we embed a scene graph into a global context clue, serving as the scene-specific environmental context; and (2) we build a relation-aware message-passing module to gather relationships from objects' neighborhood and transfer them into interactions. Empirical evaluation shows that our SG2HOI method outperforms the state-of-the-art methods on two benchmark HOI datasets: V-COCO and HICO-DET. Code will be available at https://github.com/ht014/SG2HOI.

Related Material

[pdf] [arXiv]
@InProceedings{He_2021_ICCV, author = {He, Tao and Gao, Lianli and Song, Jingkuan and Li, Yuan-Fang}, title = {Exploiting Scene Graphs for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {15984-15993} }