DGC-Net: Dynamic Graph Contrastive Network for Video Object Detection

计算机科学 人工智能 计算机视觉 目标检测 图形 图论 网(多面体) 模式识别(心理学) 理论计算机科学 数学 几何学 组合数学
作者
Qiang Qi,Hanzi Wang,Yan Yan,Xuelong Li
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:34: 2269-2284 被引量:10
标识
DOI:10.1109/tip.2025.3551158
摘要

Video object detection is a challenging task in computer vision since it needs to handle the object appearance degradation problem that seldom occurs in the image domain. Off-the-shelf video object detection methods typically aggregate multi-frame features at one stroke to alleviate appearance degradation. However, these existing methods do not take supervision knowledge into consideration and thus still suffer from insufficient feature aggregation, resulting in the false detection problem. In this paper, we take a different perspective on feature aggregation, and propose a dynamic graph contrastive network (DGC-Net) for video object detection, including three improvements against existing methods. First, we design a frame-level graph contrastive module to aggregate frame features, enabling our DGC-Net to fully exploit discriminative contextual feature representations to facilitate video object detection. Second, we develop a proposal-level graph contrastive module to aggregate proposal features, making our DGC-Net sufficiently learn discriminative semantic feature representations. Third, we present a graph transformer to dynamically adjust the graph structure by pruning the useless nodes and edges, which contributes to improving accuracy and efficiency as it can eliminate the geometric-semantic ambiguity and reduce the graph scale. Furthermore, inherited from the framework of DGC-Net, we develop DGC-Net Lite to perform real-time video object detection with a much faster inference speed. Extensive experiments conducted on the ImageNet VID dataset demonstrate that our DGC-Net outperforms the performance of current state-of-the-art methods. Notably, our DGC-Net obtains 86.3%/87.3% mAP when using ResNet-101/ResNeXt-101.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
观云舞完成签到,获得积分10
刚刚
1秒前
1秒前
2秒前
yy完成签到,获得积分10
3秒前
Ava的应助被赵兵采纳,获得10
3秒前
5秒前
小林太郎完成签到,获得积分0
5秒前
NexusExplorer的应助被gwd采纳,获得10
6秒前
zhu发布了新的文献求助10
6秒前
所所的应助被higgs采纳,获得10
6秒前
科研通AI6.4的应助被小太阳采纳,获得10
6秒前
天天快乐的应助被重要的忆雪采纳,获得30
6秒前
科研通AI6.3的应助被平生采纳,获得10
7秒前
桃桃子完成签到,获得积分10
7秒前
内向灵凡发布了新的文献求助10
8秒前
9秒前
晨gegeai完成签到,获得积分10
11秒前
11秒前
12秒前
领导范儿的应助被CTx采纳,获得10
12秒前
ll发布了新的文献求助10
12秒前
12秒前
12秒前
隐形曼青的应助被xiaojie采纳,获得10
13秒前
TEDDY发布了新的文献求助20
13秒前
14秒前
涛老三完成签到 ,获得积分10
14秒前
今后的应助被酷酷的柚子采纳,获得10
15秒前
16秒前
17秒前
YikY完成签到 ,获得积分10
17秒前
樱满集发布了新的文献求助10
17秒前
赵兵发布了新的文献求助10
18秒前
18秒前
马秀玲发布了新的文献求助10
19秒前
gwd发布了新的文献求助10
20秒前
21秒前
21秒前
Tan完成签到,获得积分10
21秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183263
求助须知:如何正确求助?哪些是违规求助? 9572532
关于积分的说明 21826339
捐赠科研通 7780187
什么是DOI,文献DOI怎么找? 3433993
关于科研通互助平台的介绍 2558131
邀请新用户注册赠送积分活动 2480239