Exploring conditional multi-modal prompts for zero-shot hoi detection

T Lei, S Yin, Y Peng, Y Liu - arXiv preprint arXiv:2408.02484, 2024 - arxiv.org
Zero-shot Human-Object Interaction (HOI) detection has emerged as a frontier topic due to
its capability to detect HOIs beyond a predefined set of categories. This task entails not only …

Learning Self-and Cross-Triplet Context Clues for Human-Object Interaction Detection

W Ren, J Luo, W Jiang, L Qu, Z Han… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Human-Object Interaction (HOI) detection aims to infer interactions between humans and
objects, and it is very important for scene analysis and understanding. The existing methods …

Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection

Y Guo, Y Liu, J Li, W Wang, Q Jia - arXiv preprint arXiv:2408.05974, 2024 - arxiv.org
Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI
categories even not encountered during training. Inspired by the impressive zero-shot …

Towards Open-vocabulary HOI Detection with Calibrated Vision-language Models and Locality-aware Queries

Z Yang, X Liu, D Ouyang, G Duan, D Zhang, T He… - ACM Multimedia … - openreview.net
The open-vocabulary human-object interaction (Ov-HOI) detection aims to identify both base
and novel categories of humanobject interactions while only base categories are available …