Practical Video Object Detection via Feature Selection and Aggregation
International Journal of Computer Vision · 2026-03 · 134 (3)
DOI: 10.1007/s11263-025-02700-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 30.01.2026. Verfasst von Yuheng Shi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Compared with still image object detection, video object detection (VOD) needs to particularly concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. In principle, the detection in a certain frame of a video can benefit from information in other frames. Thus, how to effectively aggregate features across different frames is key to the target problem. Most of contemporary aggregation methods are tailored for two-stage detectors, suffering from high computational costs due to the dual-stage nature. On the other hand, although one-stage detectors have made continuous progress in handling static images, their applicability to VOD lacks sufficient exploration. To tackle the above issues, this study invents a very simple yet potent strategy of feature selection and aggregation, gaining significant accuracy at marginal computational expense. Concretely, for cutting the massive computation and memory consumption from the dense prediction characteristic of one-stage object detectors, we first condense candidate features from dense prediction maps. Then, the relationship between a target frame and its reference frames is evaluated to guide the aggregation. Comprehensive experiments and ablation studies are conducted to validate the efficacy of our design, and showcase its advantage over other cutting-edge VOD methods in both effectiveness and efficiency. Notably, our model reaches a new record performance, i.e., 93.0% AP50 at over 30 FPS on the ImageNet VID dataset on a single 3090 GPU, making it a compelling option for large-scale or real-time applications. The implementation is simple, and accessible at https://github.com/YuHengsss/YOLOV.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Shi, Y., Zhang, T., & Guo, X. (2026). Practical Video Object Detection via Feature Selection and Aggregation. International Journal of Computer Vision, 134(3). https://doi.org/10.1007/s11263-025-02700-3
Vancouver
Shi Y, Zhang T, Guo X. Practical Video Object Detection via Feature Selection and Aggregation. International Journal of Computer Vision. 2026;134(3). doi:10.1007/s11263-025-02700-3
BibTeX
@article{Shi2026,
author = {Shi, Yuheng and Zhang, Tong and Guo, Xiaojie},
title = {Practical Video Object Detection via Feature Selection and Aggregation},
journal = {International Journal of Computer Vision},
year = {2026},
volume = {134},
number = {3},
doi = {10.1007/s11263-025-02700-3}
}
EUVIMED