Geometric Features Enhanced Human-Object Interaction Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Manli, Ho, Edmond S. L., Chen, Shuang, Yang, Longzhi, Shum, Hubert P. H.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914849973338112
author Zhu, Manli
Ho, Edmond S. L.
Chen, Shuang
Yang, Longzhi
Shum, Hubert P. H.
author_facet Zhu, Manli
Ho, Edmond S. L.
Chen, Shuang
Yang, Longzhi
Shum, Hubert P. H.
contents Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Recently, Transformer-based models have become the dominant approach for HOI detection due to their advanced network architectures and thus promising results. However, most of them follow the one-stage design of vanilla Transformer, leaving rich geometric priors under-exploited and leading to compromised performance especially when occlusion occurs. Given that geometric features tend to outperform visual ones in occluded scenarios and offer information that complements visual cues, we propose a novel end-to-end Transformer-style HOI detection model, i.e., geometric features enhanced HOI detector (GeoHOI). One key part of the model is a new unified self-supervised keypoint learning method named UniPointNet that bridges the gap of consistent keypoint representation across diverse object categories, including humans. GeoHOI effectively upgrades a Transformer-based HOI detector benefiting from the keypoints similarities measuring the likelihood of human-object interactions as well as local keypoint patches to enhance interaction query representation, so as to boost HOI predictions. Extensive experiments show that the proposed method outperforms the state-of-the-art models on V-COCO and achieves competitive performance on HICO-DET. Case study results on the post-disaster rescue with vision-based instruments showcase the applicability of the proposed GeoHOI in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18691
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Geometric Features Enhanced Human-Object Interaction Detection
Zhu, Manli
Ho, Edmond S. L.
Chen, Shuang
Yang, Longzhi
Shum, Hubert P. H.
Computer Vision and Pattern Recognition
Cameras are essential vision instruments to capture images for pattern detection and measurement. Human-object interaction (HOI) detection is one of the most popular pattern detection approaches for captured human-centric visual scenes. Recently, Transformer-based models have become the dominant approach for HOI detection due to their advanced network architectures and thus promising results. However, most of them follow the one-stage design of vanilla Transformer, leaving rich geometric priors under-exploited and leading to compromised performance especially when occlusion occurs. Given that geometric features tend to outperform visual ones in occluded scenarios and offer information that complements visual cues, we propose a novel end-to-end Transformer-style HOI detection model, i.e., geometric features enhanced HOI detector (GeoHOI). One key part of the model is a new unified self-supervised keypoint learning method named UniPointNet that bridges the gap of consistent keypoint representation across diverse object categories, including humans. GeoHOI effectively upgrades a Transformer-based HOI detector benefiting from the keypoints similarities measuring the likelihood of human-object interactions as well as local keypoint patches to enhance interaction query representation, so as to boost HOI predictions. Extensive experiments show that the proposed method outperforms the state-of-the-art models on V-COCO and achieves competitive performance on HICO-DET. Case study results on the post-disaster rescue with vision-based instruments showcase the applicability of the proposed GeoHOI in real-world applications.
title Geometric Features Enhanced Human-Object Interaction Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.18691