Photographs taken through a glass surface often contain an approximately linear superposition of reflected and transmitted layers. Decomposing an image into these layers is generally an ill-posed task and the use of an additional image prior and user provided cues is presently necessary in order to obtain good results. Current annotation approaches rely on a strong sparsity assumption. For images with significant texture this assumption does not typically hold, thus rendering the annotation process unviable. In this paper we show that using a Gaussian Mixture Model patch prior, the correct local decomposition can almost always be found as one of 100 likely modes of the posterior. Thus, the user need only choose one of these modes in a sparse set of patches and the decomposition may then be completed automatically. We demonstrate the performance of our method using synthesized and real reflection images.
School of Computer Science, Peking University（北京大学计算机学院）；National Key Laboratory for Multimedia Information Processing（多媒体信息处理国家重点实验室）；National Engineering Research Center of Visual Technology（视觉技术国家工程研究中心）；AI Innovation Center（人工智能创新中心）
Wangxuan Institute of Computer Technology, Peking University（北京大学计算机技术研究院）；Chongqing Changan Automobile Co., Ltd（重庆长安汽车有限公司）；University of California, Merced（加州大学默塞德分校）
Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night
Dr. Ing. h.c. F. Porsche AG（保时捷股份公司）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；NEC Laboratories Europe GmbH（NEC欧洲实验室有限公司）；Leibniz University Hannover（汉诺威莱布尼茨大学）
在夜间对其他道路使用者进行有效的检测，有可能提高道路安全。为此，人类直观地使用视觉提示，例如其他道路使用者发出的光锥和光反射，以便能够在早期阶段对迎面而来的交通做出反应。这种行为可以由计算机视觉方法通过基于由车辆前灯引起的发射光反射来预测车辆的外观来模仿。由于当前的目标检测算法主要基于检测经由边界框注释的直接可见的目标，因此没有尖锐边界的光反射的检测和注释是具有挑战性的。出于这个原因，发布了广泛的开源数据集PVDN（Provident Vehicle Detection at Night），其中包括通过关键点注释的光反射的夜间交通场景。在本文中，我们探讨了基于显着性的方法来创建不同的对象表示的PVDN数据集的视觉显着性和稀疏的关键点注释的基础上的潜力。为此，我们扩展了布尔地图显着性的一般思想，考虑到稀疏的关键点注释的人类对上下文感知的方法。我们表明，这种方法允许自动推导不同的对象表示，如二进制地图或边界框，以便检测模型可以在不同的注释变体上进行训练，并且可以从不同的角度解决在夜间检测车辆的问题。有了这些，我们提供了更强大的工具和方法来研究在夜间车辆实际可见之前检测车辆的问题。
Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院机械工程系）；Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院医学工程与科学研究所）；MIT.nano Immersion Lab, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院MIT.nano沉浸实验室）
Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University College London（伦敦大学学院）；Zhejiang Lab（之江实验室）
Enhancing Point Annotations with Superpixel and Confidence Learning Guided for Improving Semi-Supervised OCT Fluid Segmentation
Zhejiang Sci-Tech University（浙江理工大学）；Lishui University（丽水学院）；the Second Affiliated Hospital of Zhejiang University, College of Medicine（浙江大学医学院附属第二医院）；Communication University of Zhejiang（浙江传媒学院）；Hangzhou Dianzi University（杭州电子科技大学）；UT Southwestern Medical Center（德克萨斯大学西南医学中心）；Suzhou Research Institute of Shandong University（山东大学苏州研究院）
Beyond Point Annotation: A Weakly Supervised Network Guided by Multi-Level Labels Generated from Four-Point Annotation for Thyroid Nodule Segmentation in Ultrasound Image
Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China（机器人科学与工程学院，东北大学，沈阳，中国）；Division of Biomedical Engineering, University of Saskatchewan, Saskatoon, Canada（生物医学工程系，萨斯喀彻温大学，萨斯喀彻温，加拿大）；Department of Ultrasound, Shengjing Hospital of China Medical University, Shenyang, China（超声科，中国医科大学附属盛京医院，沈阳，中国）
FG-TreeSeg: Flow-Guided Tree Crown Segmentation without Instance Annotations
Department of Geography, University of South Carolina（南卡罗来纳大学地理系）；Department of Geography, Virginia Polytechnic Institute and State University（弗吉尼亚理工大学地理系）
PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；Department of Computer Science at Memorial University of Newfoundland（纪念大学计算机科学系）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；School of Engineering, University of California at Merced（加州大学默塞德分校工程学院）
Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment
University of California Los Angeles（加州大学洛杉矶分校）；Zhejiang University（浙江大学）；The First Affiliated Hospital, College of Medicine, Zhejiang University（浙江大学医学院附属第一医院）
User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation
PAII Inc.（PAII公司）；The University of Texas at Arlington（德克萨斯大学阿灵顿分校）；University at Buffalo（纽约州立大学布法罗分校）；Chang Gung Memorial Hospital（长庚纪念医院）；PingAn Technology（平安科技）
Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes
Department of Computer Science, Old Dominion University（奥德赛大学计算机科学系）；Department of Biology, Massachusetts Institute of Technology（麻省理工学院生物学系）；The Picower Institute for Learning and Memory, Massachusetts Institute of Technology（麻省理工学院学习与记忆研究所）；Department of Physics and Technology, UiT--The Arctic University of Norway（挪威北极大学物理与技术系）；Department of Physics, University of Oslo（奥斯陆大学物理系）；School of Data Science, Old Dominion University（奥德赛大学数据科学学院）；Department of Physics, Old Dominion University（奥德赛大学物理系）
