Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion
This work addresses object detection for computer vision applications, but it is incremental as it builds on existing WSOD methods by adding motion as a modality.
The paper tackles the problem of weakly-supervised object detection in static images by integrating hallucinated motion information, resulting in improvements over a state-of-the-art method on COCO and YouTube-BB datasets.
While motion has garnered attention in various tasks, its potential as a modality for weakly-supervised object detection (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 improve 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.