EUVIMEDEUVIMED entdecken
Crossref

Context Enhanced Transformer for Single Image Object Detection in Video Data

Seungjun An, Seonghoon Park, Gyeongnyeon Kim, Jeongyeol Baek, Byeongwon Lee, Seungryong Kim

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 682-690

DOI: 10.1609/aaai.v38i2.27825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Seungjun An und 5 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various strategies to address this challenge, they typically depend on locally adjacent frames or randomly sampled images within a clip. Although recent Transformer-based VOD methods have shown promising results, their reliance on multiple inputs and additional network complexity to incorporate temporal information limits their practical applicability. In this paper, we propose a novel approach to single image object detection, called Context Enhanced TRansformer (CETR), by incorporating temporal context into DETR using a newly designed memory module. To efficiently store temporal information, we construct a class-wise memory that collects contextual information across data. Additionally, we present a classification-based sampling technique to selectively utilize the relevant memory for the current image. In the testing, We introduce a test-time memory adaptation method that updates individual memory functions by considering the test distribution. Experiments with CityCam and ImageNet VID datasets exhibit the efficiency of the framework on various video systems. The project page and code will be made available at: https://ku-cvlab.github.io/CETR.

Zitieren

APA

An, S., Park, S., Kim, G., Baek, J., Lee, B., & Kim, S. (2024). Context Enhanced Transformer for Single Image Object Detection in Video Data. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 682-690. https://doi.org/10.1609/aaai.v38i2.27825

Vancouver

An S, Park S, Kim G, Baek J, Lee B, Kim S. Context Enhanced Transformer for Single Image Object Detection in Video Data. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):682-690. doi:10.1609/aaai.v38i2.27825

BibTeX
@article{An2024,
  author = {An, Seungjun and Park, Seonghoon and Kim, Gyeongnyeon and Baek, Jeongyeol and Lee, Byeongwon and Kim, Seungryong},
  title = {Context Enhanced Transformer for Single Image Object Detection in Video Data},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {2},
  pages = {682--690},
  doi = {10.1609/aaai.v38i2.27825}
}
Kostenlos starten →