Work

Enhancing Weakly-Supervised Object Detection on Static Images Through (Hallucinated) Motion

Year: 2025

Type: conference-paper

Abstract: While motion has garnered attention in various tasks, its potential as a modality for weakly-supervised object de-tection (WSOD) in static images remains unexplored. Our study introduces an approach to enhance WSOD methods by integrating motion information. This method involves leveraging hallucinated motion from static images to im-prove WSOD on image datasets, utilizing a Siamese network for enhanced representation learning with motion, addressing camera motion through motion normalization, and selectively training images based on object motion. Experimental validation on the COCO and YouTube-BB datasets demonstrates improvements over a state-of-the-art method.

Source: IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

DOI: 10.1109/wacvw65960.2025.00117

Authors: Cagri Gungor, Adriana Kovashka

Institution: University of Pittsburgh

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Award: CAREER: Natural Narratives and Multimodal Context as Weak Supervision for Learning Object Categories