MLPPose: Human Keypoint Localization via MLP-Mixer

计算机科学 人工智能 安全性令牌 模式识别(心理学) 嵌入 姿势 依赖关系(UML) 变压器 计算机视觉 特征提取 卷积神经网络 特征(语言学) 物理 哲学 量子力学 语言学 电压 计算机安全
作者
Biao Guo,K Liu,Qian He
出处
期刊:Lecture Notes in Computer Science 卷期号:: 574-585
标识
DOI:10.1007/978-3-031-15919-0_48
摘要

Although existing methods have made great progress in human pose estimation, there are still a lot of challenging situations not well-handled, such as occluded limbs, invisible body parts or complex scenarios. In this work, we propose a novel approach called MLPPose, which combining the MLP-Mixer layers with the convolutional token embedding for human pose estimation. The MLP-Mixer layers are consisted of two types of MLP blocks, one concerns the global receptive field and the other mixes the channel feature at each location. This composition can not only obtain the association between different keypoints, but also efficiently capture the global dependency relationships between keypoints and scenes. Thus, it allows our model to efficiently locate the keypoints, despite that some of them are occluded, invisible or in complex scenarios. Meanwhile, it is able to simplify the progress of extracting the global dependency relationships compared to the attentional mechanism which is widely used in transformer models. Experiments show that our model achieves competitive results with state-of-the-art methods on the MS-COCO and MPII human pose estimation benchmarks. Moreover, our model is more lightweight and faster than other best performance methods.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
刚刚
刚刚
武丝丝完成签到,获得积分10
2秒前
ccc完成签到,获得积分10
2秒前
3秒前
开心人达发布了新的文献求助10
4秒前
YX完成签到,获得积分10
4秒前
武丝丝发布了新的文献求助10
4秒前
Hesper完成签到 ,获得积分10
4秒前
8秒前
脑洞疼应助樱桃小王子采纳,获得10
9秒前
领导范儿应助樱桃小王子采纳,获得10
9秒前
科研通AI2S应助樱桃小王子采纳,获得10
9秒前
Rondab应助樱桃小王子采纳,获得10
9秒前
深情安青应助樱桃小王子采纳,获得10
9秒前
杨羽发布了新的文献求助10
9秒前
9秒前
10秒前
王先生完成签到,获得积分10
10秒前
11秒前
小姜完成签到,获得积分10
12秒前
马登完成签到,获得积分10
13秒前
Akim应助王浩宇采纳,获得10
15秒前
顺心若魔发布了新的文献求助10
15秒前
16秒前
16秒前
17秒前
19秒前
踏实季节发布了新的文献求助10
20秒前
yar应助威武鸽子采纳,获得10
20秒前
时运完成签到,获得积分10
20秒前
zihanwang应助甜甜的盼海采纳,获得30
20秒前
皮蛋努力科研完成签到 ,获得积分10
21秒前
Jasper应助开心人达采纳,获得10
22秒前
万能图书馆应助津津采纳,获得10
24秒前
汉堡包应助怡春院李老鸨采纳,获得10
24秒前
24秒前
可爱灵安发布了新的文献求助10
25秒前
汉堡包应助zozo采纳,获得30
25秒前
JamesPei应助艾科研采纳,获得10
26秒前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
Problems of point-blast theory 400
北师大毕业论文 基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 390
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
Novel Preparation of Chitin Nanocrystals by H2SO4 and H3PO4 Hydrolysis Followed by High-Pressure Water Jet Treatments 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3998724
求助须知:如何正确求助?哪些是违规求助? 3538169
关于积分的说明 11273611
捐赠科研通 3277151
什么是DOI,文献DOI怎么找? 1807423
邀请新用户注册赠送积分活动 883867
科研通“疑难数据库(出版商)”最低求助积分说明 810070