.png){kind=icon}
返回
Practical Video Object Detection via Feature Selection and Aggregation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-025-02700-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 .
Keyword:
Object detection
Video object detection
Feature selection
Feature aggregation
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
.png){kind=icon}
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks更快的r-cnn: 基于区域建议网络的实时目标检测
OAAI
OAAI分享收藏
Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection通过自适应训练样本选择弥合基于锚点和无锚检测之间的差距OAAI
OAAI分享收藏
查看更多内容