HOTR: End-to-End Human-Object Interaction Detection with Transformers

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 74 - 83
• Main Authors: Kim, Bumsoo, Lee, Junhyun, Kang, Jaewoo, Kim, Eun-Sol, Kim, Hyunwoo J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Benchmark testing; Detectors; Prediction algorithms; Predictive models; Semantics; Training; Transformers

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods hav...