Skip Connection Aggregation Transformer for Occluded Person Reidentification

联营 计算机科学 编码器 人工智能 变压器 计算机视觉 模式识别(心理学) 特征提取 突出 工程类 电压 电气工程 操作系统
作者
Huijie Fan,Xiaotong Wang,Qiang Wang,Shengpeng Fu,Yandong Tang
出处
期刊:IEEE Transactions on Industrial Informatics [Institute of Electrical and Electronics Engineers]
卷期号:20 (1): 442-451 被引量:43
标识
DOI:10.1109/tii.2023.3266372
摘要

The occlusion problem is a significant challenge for person reidentification. Recently, transformer-based methods have been introduced to solve the occlusion problem and achieve performance improvements. However, the existing methods only apply the features of the last transformer layer and fail to consider the alignment of visible body parts. They also ignore fine-grained local features. Thus, they usually suffer from misalignment in occluded image matching. We observe that features from the high layers of the transformer focus on classification information and global features, while those from the middle layers pay more attention to pedestrians. We think that making full use of the features of different layers will facilitate alignment and then will promote reidentification accuracy. Therefore, we propose a novel skip connection aggregation transformer (SCAT) network by utilizing features from different transformer layers to increase the diversity of features and align visible body parts in occluded images. The diverse features include the following: first, features of the middle layer, which focus on the pedestrian in nonoccluded regions and favor alignment, second, features of high layers, which focus on global information, third fine-grained local features, which are obtained by the part pooling encoder and the fusion reconstruction module. The part pooling encoder and the fusion reconstruction module are proposed to obtain part-based local features and fused local features, respectively. The experimental results on the occluded, partial, and holistic benchmarks demonstrate that our method can significantly promote the accuracy of occluded person reidentification.
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
mnilyra发布了新的文献求助10
1秒前
1秒前
乔达摩悉达多完成签到 ,获得积分0
1秒前
2秒前
647完成签到,获得积分10
2秒前
2秒前
韵掀完成签到,获得积分10
3秒前
郑睿涛发布了新的文献求助10
3秒前
5秒前
5秒前
Homura完成签到,获得积分10
6秒前
6秒前
灵长类完成签到,获得积分10
6秒前
李爱国的应助被欣慰的文昊采纳,获得30
6秒前
7秒前
xing_xing的应助被CWJ采纳,获得20
7秒前
7秒前
郭姗姗发布了新的文献求助10
7秒前
TaoJ的应助被CWJ采纳,获得20
7秒前
是小周发布了新的文献求助10
8秒前
完美世界的应助被浮云客采纳,获得10
8秒前
把握传送时机完成签到,获得积分10
8秒前
zhao完成签到,获得积分10
9秒前
11秒前
11秒前
11秒前
核桃发布了新的文献求助50
12秒前
充电宝的应助被DFT_Gu采纳,获得10
12秒前
12秒前
马世杰发布了新的文献求助10
13秒前
13秒前
那没事了完成签到,获得积分10
13秒前
green完成签到,获得积分10
14秒前
Lucas的应助被TAT采纳,获得10
14秒前
15秒前
乐乐的应助被汤包采纳,获得10
15秒前
FashionBoy的应助被年轻雁枫采纳,获得10
15秒前
万万发布了新的文献求助10
15秒前
mabel发布了新的文献求助10
15秒前
16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 8183792
求助须知:如何正确求助?哪些是违规求助? 9573020
关于积分的说明 21828776
捐赠科研通 7780959
什么是DOI,文献DOI怎么找? 3434116
关于科研通互助平台的介绍 2558301
邀请新用户注册赠送积分活动 2480611