Identity-Consistent Aggregation for Video Object Detection

Chaorui Deng, Da Chen, Qi Wu

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

Abstract

In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects indiscriminately and ignore their different identities. While intuitively, aggregating local views of the same object in different frames may facilitate a better understanding of the object. Thus, in this paper, we aim to enable the model to focus on the identity-consistent temporal contexts of each object to obtain more comprehensive object representations and handle the rapid object appearance variations such as occlusion, motion blur, etc. However, realizing this goal on top of existing VID models faces low-efficiency problems due to their redundant region proposals and nonparallel frame-wise prediction manner. To aid this, we propose ClipVID, a VID model equipped with Identity-Consistent Aggregation (ICA) layers specifically designed for mining fine-grained and identity-consistent temporal contexts. It effectively reduces the redundancies through the set prediction strategy, making the ICA layers very efficient and further allowing us to design an architecture that makes parallel clip-wise predictions for the whole video clip. Extensive experimental results demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7× faster (39.3 fps) than previous SOTAs.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PublisherIEEE
Pages13388-13398
Number of pages11
ISBN (Electronic)9798350307184
ISBN (Print)9798350307191
DOIs
Publication statusPublished - 6 Oct 2023
Event2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France
Duration: 2 Oct 20236 Oct 2023

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Conference

Conference2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Country/TerritoryFrance
CityParis
Period2/10/236/10/23

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Identity-Consistent Aggregation for Video Object Detection'. Together they form a unique fingerprint.

Cite this