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

arXiv: https://arxiv.org/abs/2409.09616 · HTML: https://mlsanity.com/paper/2409.09616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 15 Sep 2024.

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Learning Features by Watching Objects Move](https://mlsanity.com/paper/1612.06370/) (2016)
- [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://mlsanity.com/paper/1702.00824/) (2017)
- [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](https://mlsanity.com/paper/2004.04725/) (2020)
- [Siamese Network for RGB-D Salient Object Detection and Beyond](https://mlsanity.com/paper/2008.12134/) (2020)
- [Im2Flow: Motion Hallucination from Static Images for Action Recognition](https://mlsanity.com/paper/1712.04109/) (2017)
- [Salvage of Supervision in Weakly Supervised Object Detection](https://mlsanity.com/paper/2106.04073/) (2021)
- [Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth](https://mlsanity.com/paper/2303.10937/) (2023)

## Abstract (arXiv)

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.