We present an improved model and theory for time-causal and time-recursive spatio-temporal receptive fields, obtained by a combination of Gaussian receptive fields over the spatial domain and first-order integrators or equivalently truncated exponential filters coupled in cascade over the temporal domain. Compared to previous spatio-temporal scale-space formulations in terms of non-enhancement of local extrema or scale invariance, these receptive fields are based on different scale-space axiomatics over time by ensuring non-creation of new local extrema or zero-crossings with increasing temporal scale. Specifically, extensions are presented about parameterizing the intermediate temporal scale levels, analysing the resulting temporal dynamics and transferring the theory to a discrete implementation in terms of recursive filters over time.
Unified theory for joint covariance properties under geometric image transformations for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields
Computational Brain Science Lab(计算脑科学实验室);Division of Computational Science and Technology(计算科学与技术系);KTH Royal Institute of Technology(皇家理工学院)
Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
KTH Royal Institute of Technology(皇家理工学院);TU Wien(维也纳技术大学)
Efficient Image Super-Resolution using Vast-Receptive-Field Attention
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shanghai AI Laboratory(上海人工智能实验室);The University of Sydney(悉尼大学)
Spatiotemporal Pyramidal CNN with Depth-Wise Separable Convolution for Eye Blinking Detection in the Wild
School of Engineering Pedagogy, Hanoi University of Science and Technology(河内科学技术大学工程教育学院);Graduate School of Engineering and Science, Shibaura Institute of Technology(芝浦工业大学工程与科学研究生院)
Beijing Innovation Center of Humanoid Robotics(北京人形机器人创新中心);Beijing Institute of Technology(北京理工大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
University of Chinese Academy of Sciences(中国科学院大学);Meitu(美图公司);National Computer network Emergency Response technical Team/Coordination Center of China(国家计算机网络应急技术处理协调中心)
StripRFNet: A Strip Receptive Field and Shape-Aware Network for Road Damage Detection
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院数字地球科学重点实验室);International Research Center of Big Data for Sustainable Development Goals(可持续发展大数据国际研究中心);University of Chinese Academy of Sciences(中国科学院大学);Southeast University(东南大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
L-STEC: Learned Video Compression with Long-term Spatio-Temporal Enhanced Context
Shenzhen Graduate School, Peking University(北京大学深圳研究生院);Pengcheng Laboratory(鹏城实验室);National Engineering Research Center for Visual Technology, School of Computer Science, Peking University(国家视觉技术工程研究中心,北京大学计算机学院);Bytedance Inc(字节跳动公司)
UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School(一般人工智能国家重点实验室,北京大学深圳研究生院);The Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University(浙江大学-伊利诺伊大学 Urbana-Champaign 院,浙江大学);State University of New York at Buffalo(纽约州立大学布法罗分校)
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Mitsubishi Electric Research Laboratories(三菱电机研究实验室);Shanghai Jiao Tong University(上海交通大学);University of Southern California(南加州大学)
针对密集4D光场的能量压缩问题,设计了基于几何感知的局部图变换。局部图是在超射线上构建的,超射线可以被看作是空间和几何相关的角度相关像素的分组。不可分离和可分离的转换被认为是。尽管由超射线定义的有限大小的局部支持,不可分图的拉普拉斯矩阵仍然是高维的,并且其对角化以计算变换特征向量仍然是计算昂贵的。为了解决这个问题,我们然后执行本地空间角度变换在一个可分离的方式。我们发现,当不同视图中对应的超像素的形状不是等距的时,空间变换的基函数是不相干的,导致空间变换系数之间的相关性降低。因此,我们提出了一种新的变换优化方法,旨在保持角度相关性,即使当超像素的形状不是等距的。实验结果表明该方法在能量压缩方面的好处。还描述了一种编码方案,以评估所提出的变换的率失真性能,并将其与现有技术的编码器(即HEVC和JPEG Pleno VM 1.1)进行比较。
BEVANet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation
Graduate Institute of Networking and Multimedia, National Taiwan University(网络与多媒体研究所,国立台湾大学);Department of Computer Science and Information Engineering, National Taiwan University(计算机科学与信息工程系,国立台湾大学)
Space-Time-Separable Graph Convolutional Network for Pose Forecasting
Sapienza University of Rome(罗马大学)
人体姿态预测是一个复杂的结构化数据序列建模任务,由于其众多的潜在应用,已受到越来越多的关注。研究主要针对时间维的时间序列和人体关节的相互作用与运动树或图形。这使得这两个方面脱钩,并利用了相关领域的进展,但它也限制了对人类姿势的复杂结构关节时空动力学的理解。在这里,我们提出了一种新的时空可分离的图卷积网络(STS-GCN)的姿态预测。STS-GCN第一次只使用图卷积网络(GCN)对人体姿态动态进行建模,在单个图框架内包括时间演化和空间联合交互,这允许运动和空间相关性的串扰。同时,STS-GCN是第一个时空可分离的GCN:时空图的连通性被分解为空间和时间亲和矩阵,这限制了时空串扰,同时实现了完全的联合-联合和时间-时间相关。两个亲和矩阵都是端到端学习的,这导致连接基本上偏离标准运动树和线性时间序列。在对三个复杂的、最新的和大规模的基准测试(Human3.6M [Ionescu et al. TPAMI'14]、AMASS [Mahmood et al. ICCV'19]和3DPW [Von Marcard et al. ECCV'18])的实验评估中,STS-GCN的表现优于最先进的技术,在最困难的长期预测中,平均超过当前最好的技术[Mao et al. ECCV'20] 32%以上,而仅需要其参数的1.7%。我们定性地解释了结果,并说明了图的相互作用的因子联合联合和时间-时间学习图连…
DualX-VSR: Dual Axial Spatial$\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation
University of Science and Technology of China(中国科学技术大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);Sun Yat-sen University(中山大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence(人机混合增强智能国家重点实验室);Institute of Artificial Intelligence and Robotics(人工智能与机器人研究院);Xi’an Jiaotong University(西安交通大学);Harbin Institute of Technology(哈尔滨工业大学);Pengcheng Laboratory(鹏城实验室)
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition
School of Big Data and Software Engineering, Chongqing University(重庆大学大数据与软件学院);Center for Data Science, Peking University(北京大学数据科学中心);School of Mathematical Sciences, Peking University(北京大学数学科学学院);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院)