This work deals with content-based video indexing. Our viewpoint is semi-automatic analysis of compressed video. We consider the possible applications of motion analysis and moving object detection : assisting moving object indexing, summarising videos, and allowing image and motion queries. We propose an approach based on interest points. As first results, we test and compare the stability of different types of interest point detectors in compressed sequences.
Automated player identification and indexing using two-stage deep learning network
Stevens Institute of Technology(斯蒂文斯理工学院);University of Alabama(阿拉巴马大学);Columbia University in the City of New York(纽约市哥伦比亚大学);The University of Alabama(阿拉巴马大学)
Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection
Georgia Institute of Technology(佐治亚理工学院);Twentieth Century Fox(二十世纪福克斯公司);Starfleet Academy(星际舰队学院);Tyrell Inc.(泰瑞尔公司)
机器人辅助手术(RAS)视频的视频理解是一个活跃的研究领域。对外科医生的手势和技能水平进行建模提出了一个有趣的问题。所得出的见解可以应用于有效的技能获取、客观的技能评估、实时反馈和人机协作手术。我们提出了一个解决方案的工具检测和本地化开放的问题,在RAS视频理解,使用严格的计算机视觉的方法和深度学习的最新进展。我们提出了一个架构,使用多模态卷积神经网络的快速检测和RAS视频中的工具定位。据我们所知,这种方法将是第一个将深度神经网络用于RAS视频中的工具检测和定位的方法。我们的架构应用区域建议网络(RPN),和多模态双流卷积网络的目标检测,共同预测对象和定位的融合图像和时间的运动线索。我们的平均精度(AP)为91%,每个测试帧检测的平均计算时间为0.1秒,这表明我们的研究优于传统的医学成像方法,同时也强调了使用RPN的精度和效率的好处。我们还介绍了一个新的数据集,ATLAS Dione,RAS视频理解。我们的数据集提供了来自Roswell Park Cancer Institute(RPCI)(Buffalo,NY)的十名外科医生在达芬奇手术系统(dVSS R)上执行六种不同手术任务的视频数据,每帧都有机器人工具的注释。
Deep-Learning-Assisted Analysis of Cataract Surgery Videos
Alpen-Adria-Universität Klagenfurt(阿尔卑斯-亚得里亚大学克拉根福分校);University of Applied Sciences Western Switzerland(瑞士西部应用科学大学);University of Bern(伯尔尼大学);University of Geneva(日内瓦大学)
Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living
Alicante Institute for Health and Biomedical Research (ISABIAL)(阿利坎特健康与生物医学研究所(ISABIAL));ValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence(瓦尔格AI——瓦伦西亚人工智能研究生院与研究网络)
A Survey of Semen Quality Evaluation in Microscopic Videos Using Computer Assisted Sperm Analysis
Northeastern University(东北大学);University of Washington (Seattle Campus)(华盛顿大学(西雅图校区));University of Luebeck(吕贝克大学);Chengdu University of Information Technology(成都信息工程大学)
TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation
Birmingham City University(伯明翰城市大学);University Hospitals Birmingham(伯明翰大学医院);University of Birmingham(伯明翰大学);University of the West of England(西英格兰大学);University of Hertfordshire(赫特福德大学);University of Bristol(布里斯托大学);Qatar University(卡塔尔大学)
GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Cardiff University(卡迪夫大学);Kling AI;The Hong Kong University of Science and Technology(香港科技大学)
Velocity Disambiguation for Video Frame Interpolation
School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院);Cornell University(康奈尔大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);OtoNexus Medical Technologies(OtoNexus医疗科技公司);Snap Inc(Snap公司)
PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos
Bosch Research North America(博世北美研究院);Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心);Department of Computer Science and Engineering, Texas A&M University(德克萨斯农工大学计算机科学与工程学院)
PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning
University of Chinese Academy of Sciences(中国科学院大学);CASIA(中国科学院自动化研究所);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)
FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning
School of Automation, Northwestern Polytechnical University(自动化学院,西北工业大学);The University of Hong Kong(香港大学);School of Software, Northwestern Polytechnical University(软件学院,西北工业大学);Unmanned System Research Institute, Northwestern Polytechnical University(无人系统研究院,西北工业大学)
Automatic Operating Room Surgical Activity Recognition for Robot-Assisted Surgery
Intuitive Surgical Inc.(直觉外科公司)
手术室(OR)中手术活动的自动识别是创建下一代智能手术设备和工作流程监控/支持系统的关键技术。这种系统可以潜在地提高OR的效率,从而降低成本并改善对患者的护理。在本文中,我们研究了机器人辅助手术中的自动手术活动识别。我们收集了第一个大规模的数据集,包括400个完整长度的多视角视频,这些视频来自使用飞行时间相机捕获的各种机器人手术病例。我们用10种最受认可和临床相关的活动类别对视频进行了密集注释。此外,我们研究了最先进的计算机视觉动作识别技术,并使其适应OR环境和数据集。首先,我们对Inflated 3D ConvNet(I3 D)进行微调,以便在我们的数据集上进行剪辑级活动识别,并使用它从视频中提取特征。然后,这些特征被馈送到3个时间高斯混合层的堆栈,该堆栈从相邻剪辑中提取上下文,并最终通过长短期记忆网络来学习全长视频中的活动顺序。我们广泛地评估了模型,并达到了88%的平均平均精度的峰值性能。
FTDMamba: Frequency-Assisted Temporal Dilation Mamba for Unmanned Aerial Vehicle Video Anomaly Detection
Information Materials and Intelligent Sensing Laboratory of Anhui Province(安徽省信息材料与智能感知实验室);Anhui Provincial Key Laboratory of Multimodal Cognitive Computation(安徽省多模态认知计算重点实验室);School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)计算机科学与工程系)
ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compression
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Artificial Intelligence, Ningbo University(宁波大学人工智能学院);National University of Singapore(新加坡国立大学);Zhejiang University of Technology(浙江工业大学);School of Information Engineering, Zhongnan University of Economics and Law(中南财经政法大学信息工程学院)
Event-assisted Low-Light Video Object Segmentation
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
Video-based surgical skill assessment using 3D convolutional neural networks
National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心);Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden(德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院暨大学医院)