Despite the success in still image recognition, deep neural networks for spatiotemporal signal tasks (such as human action recognition in videos) still suffers from low efficacy and inefficiency over the past years. Recently, human experts have put more efforts into analyzing the importance of different components in 3D convolutional neural networks (3D CNNs) to design more powerful spatiotemporal learning backbones. Among many others, spatiotemporal fusion is one of the essentials. It controls how spatial and temporal signals are extracted at each layer during inference. Previous attempts usually start by ad-hoc designs that empirically combine certain convolutions and then draw conclusions based on the performance obtained by training the corresponding networks. These methods only support network-level analysis on limited number of fusion strategies. In this paper, we propose to convert the spatiotemporal fusion strategies into a probability space, which allows us to perform network-level evaluations of various fusion strategies without having to train them separately. Besides, we can also obtain fine-grained numerical information such as layer-level preference on spatiotemporal fusion within the probability space. Our approach greatly boosts the efficiency of analyzing spatiotemporal fusion. Based on the probability space, we further generate new fusion strategies which achieve the state-of-the-art performance on four well-known action recognition datasets.
Spatiotemporal CNNs for Pornography Detection in Videos
UFSCar - Federal University of Sao Carlos(圣卡洛斯联邦大学);IFSP - Federal Institute of Education of Sao Paulo(圣保罗联邦教育学院);UNESP - Sao Paulo State University(圣保罗州立大学)
随着越来越多地使用社交网络和移动设备,发布在互联网上的视频数量呈指数级增长。在互联网上发布的不适当内容中,色情是最令人担忧的内容之一,因为青少年和儿童可以访问。在本研究中,评估了两种时空CNN,VGG-C3 D CNN和ResNet R(2+1)D CNN,用于视频中的色情检测。使用Pornography-800数据集的实验结果表明,这些时空CNN的性能优于一些基于视觉词袋的最先进方法,并且与其他基于CNN的方法相比具有竞争力,准确率达到95.1%。
Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning
University of Engineering and Technology, Taxila(塔克西拉工程技术大学);University of Jeddah(吉达大学);Peoples' Friendship University of Russia (RUDN University)(俄罗斯人民友谊大学(卢蒙巴大学));The Bonch-Bruevich Saint-Petersburg State University of Telecommunications(圣彼得堡国立电信大学(邦奇-布鲁耶维奇));Jeju National University(济州国立大学)
Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures
Department of Medical Physics and Biomedical Engineering, University College London(伦敦大学学院医学物理与生物医学工程系);Wellcome / EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London(伦敦大学学院韦尔科姆/工程与物理科学研究委员会介入与外科科学中心(WEISS));School of Biomedical Engineering & Imaging Sciences (BMEIS), King’s College London(伦敦国王学院生物医学工程与成像科学学院(BMEIS));UCL Queen Square Institute of Neurology, Department of Clinical and Experimental Epilepsy, London(伦敦大学学院女王广场神经学研究所临床与实验癫痫系);UCL Queen Square Institute of Neurology, Department of Clinical and Experimental(伦敦大学学院女王广场神经学研究所临床与实验(此处原文不完整,按现有内容提取))
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Intelligent Systems, Computer Architecture, Analytics, and Security Laboratory (ISCAAS Lab), Department of Electrical Engineering and Computer Science, Florida Atlantic University(智能系统、计算机架构、分析与安全实验室(ISCAAS实验室),电气工程与计算机科学系,佛罗里达 Atlantic 大学);Intelligent Systems, Computer Architecture, Analytics, and Security Laboratory (ISCAAS Lab), Department of Electrical and Computer Engineering, Kansas State University(智能系统、计算机架构、分析与安全实验室(ISCAAS实验室),电气与计算机工程系,堪萨斯州立大学)
PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
DIKU University of Copenhagen(哥本哈根大学DIKU);Biomediq A/S(Biomediq公司);Cerebriu A/S(Cerebriu公司);King’s College London(伦敦国王学院);University College London(伦敦大学学院)
VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Hong Kong Baptist University(香港浸会大学);The Hong Kong University of Science and Technology(香港科技大学)
Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
University of Oxford(牛津大学);University of Nottingham(诺丁汉大学);University of Minnesota(明尼苏达大学);European Space Agency(欧洲空间局);Haverford College(哈弗福德学院);University of Portsmouth(朴茨茅斯大学)
A Decade of Deep Learning for Remote Sensing Spatiotemporal Fusion: Advances, Challenges, and Opportunities
School of Computer Science, China University of Geosciences (Wuhan)(中国地质大学(武汉)计算机科学学院);Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院航空航天信息研究所);School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences(中国科学院大学电子电气与通信工程学院)
3D CNN在最近的视频识别任务中显示了其强大的时空表示学习能力。然而,将2D卷积膨胀到3D不可避免地会引入额外的计算成本,使其在实际部署中变得繁琐。我们考虑是否有一种方法来装备传统的2D卷积与时间视觉,而不需要扩展其内核。为此,我们提出了视频洗牌,一个无参数的插件组件,有效地重新分配2D卷积的输入,使其感受野可以扩展到时间维度。在实际应用中,视频混洗首先将每一帧的特征分成多个组,然后通过时间混洗操作聚合成组的特征。这允许以下2D卷积聚合全局时空特征。提出的视频洗牌可以灵活地插入到流行的2D CNN中,形成视频洗牌网络(VSN)。通过简单而有效的实现,VSN在时态建模基准测试中表现得令人惊讶。在实验中,VSN不仅在Kinetics和Moments in Time上获得了非平凡的改进,而且在Something-Something-V1,Something-Something-V2数据集上也获得了最先进的性能。
Using 3D Convolutional Neural Networks to Learn Spatiotemporal Features for Automatic Surgical Gesture Recognition in Video
National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心);University Hospital Carl Gustav Carus(卡尔·古斯塔夫·卡鲁斯大学医院);TU Dresden(德累斯顿工业大学);Centre for Tactile Internet with Human-in-the-Loop (CeTI)(人在环触觉互联网中心)
UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);Beijing University of Posts and Telecommunications(北京邮电大学);Sun Yat-sen University(中山大学);Peking University(北京大学);Defense Innovation Institute, Academy of Military Sciences(国防科技创新院,军事科学学院);Tianjin Artificial Intelligence Innovation Center(天津人工智能创新中心)
Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review
A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
Rice University(莱斯大学);University of California at Berkeley(加州大学伯克利分校);Baylor College of Medicine(贝勒医学院);California Institute of Technology(加州理工学院);NVIDIA(英伟达)
Generative artificial intelligence in ophthalmology: multimodal retinal images for the diagnosis of Alzheimer's disease with convolutional neural networks