# Analysing domain shift factors between videos and images for object detection

arXiv: https://arxiv.org/abs/1501.01186 · HTML: https://mlsanity.com/paper/1501.01186/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2015.

## Built on by (most cited first, 9 of 9)

- [Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset](https://mlsanity.com/paper/2207.10664/) (2022)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild](https://mlsanity.com/paper/2401.04210/) (2024)
- [Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization](https://mlsanity.com/paper/2204.09334/) (2022)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Objects do not disappear: Video object detection by single-frame object location anticipation](https://mlsanity.com/paper/2308.04770/) (2023)
- [Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video](https://mlsanity.com/paper/2407.15794/) (2024)
- [Pixel-level Correspondence for Self-Supervised Learning from Video](https://mlsanity.com/paper/2207.03866/) (2022)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)

## Abstract (arXiv)

Object detection is one of the most important challenges in computer vision. Object detectors are usually trained on bounding-boxes from still images. Recently, video has been used as an alternative source of data. Yet, for a given test domain (image or video), the performance of the detector depends on the domain it was trained on. In this paper, we examine the reasons behind this performance gap. We define and evaluate different domain shift factors: spatial location accuracy, appearance diversity, image quality and aspect distribution. We examine the impact of these factors by comparing performance before and after factoring them out. The results show that all four factors affect the performance of the detectors and their combined effect explains nearly the whole performance gap.