Analysing domain shift factors between videos and images for object detection

V. Kalogeiton, Vittorio Ferrari, C. Schmid

Research output: Contribution to journalArticlepeer-review


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.
Original languageEnglish
Number of pages8
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number11
Early online date6 Apr 2016
Publication statusPublished - 1 Nov 2016


Dive into the research topics of 'Analysing domain shift factors between videos and images for object detection'. Together they form a unique fingerprint.

Cite this