HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Joohyun, Hong, Soyeon, Lee, Hyogun, Ha, Seong Jong, Lee, Dongho, Kim, Seong Tae, Choi, Jinwoo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916926046863360
author Chang, Joohyun
Hong, Soyeon
Lee, Hyogun
Ha, Seong Jong
Lee, Dongho
Kim, Seong Tae
Choi, Jinwoo
author_facet Chang, Joohyun
Hong, Soyeon
Lee, Hyogun
Ha, Seong Jong
Lee, Dongho
Kim, Seong Tae
Choi, Jinwoo
contents In this work, we tackle the egocentric visual query localization (VQL), where a model should localize the query object in a long-form egocentric video. Frequent and abrupt viewpoint changes in egocentric videos cause significant object appearance variations and partial occlusions, making it difficult for existing methods to achieve accurate localization. To tackle these challenges, we introduce Hierarchical, Egocentric and RObust Visual Query Localization (HERO-VQL), a novel method inspired by human cognitive process in object recognition. We propose i) Top-down Attention Guidance (TAG) and ii) Egocentric Augmentation based Consistency Training (EgoACT). Top-down Attention Guidance refines the attention mechanism by leveraging the class token for high-level context and principal component score maps for fine-grained localization. To enhance learning in diverse and challenging matching scenarios, EgoAug enhances query diversity by replacing the query with a randomly selected corresponding object from groundtruth annotations and simulates extreme viewpoint changes by reordering video frames. Additionally, CT loss enforces stable object localization across different augmentation scenarios. Extensive experiments on VQ2D dataset validate that HERO-VQL effectively handles egocentric challenges, significantly outperforming baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00385
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization
Chang, Joohyun
Hong, Soyeon
Lee, Hyogun
Ha, Seong Jong
Lee, Dongho
Kim, Seong Tae
Choi, Jinwoo
Computer Vision and Pattern Recognition
In this work, we tackle the egocentric visual query localization (VQL), where a model should localize the query object in a long-form egocentric video. Frequent and abrupt viewpoint changes in egocentric videos cause significant object appearance variations and partial occlusions, making it difficult for existing methods to achieve accurate localization. To tackle these challenges, we introduce Hierarchical, Egocentric and RObust Visual Query Localization (HERO-VQL), a novel method inspired by human cognitive process in object recognition. We propose i) Top-down Attention Guidance (TAG) and ii) Egocentric Augmentation based Consistency Training (EgoACT). Top-down Attention Guidance refines the attention mechanism by leveraging the class token for high-level context and principal component score maps for fine-grained localization. To enhance learning in diverse and challenging matching scenarios, EgoAug enhances query diversity by replacing the query with a randomly selected corresponding object from groundtruth annotations and simulates extreme viewpoint changes by reordering video frames. Additionally, CT loss enforces stable object localization across different augmentation scenarios. Extensive experiments on VQ2D dataset validate that HERO-VQL effectively handles egocentric challenges, significantly outperforming baselines.
title HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.00385