Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Yan Shu, Weichao Zeng, Zhenhang Li, Fangmin Zhao, Yu Zhou
Visual text, a pivotal element in both document and scene images, speaks volumes and attracts significant attention in the computer vision domain. Beyond visual text detection and recognition, the field of visual text processing has experienced a surge in research, driven by the advent of fundamental generative models. However, challenges persist due to the unique properties and features that distinguish text from general objects. Effectively leveraging these unique textual characteristics is crucial in visual text processing, as observed in our study. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in this field. Initially, we introduce a hierarchical taxonomy encompassing areas ranging from text image enhancement and restoration to text image manipulation, followed by different learning paradigms. Subsequently, we conduct an in-depth discussion of how specific textual features such as structure, stroke, semantics, style, and spatial context are seamlessly integrated into various tasks. Furthermore, we explore available public datasets and benchmark the reviewed methods on several widely-used datasets. Finally, we identify principal challenges and potential avenues for future research. Our aim is to establish this survey as a fundamental resource, fostering continued exploration and innovation in the dynamic area of visual text processing.
WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing
School of Computer Science and Technology, Anhui University of Technology(安徽理工大学计算机科学与技术学院);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);College of Artificial Intelligence, Taiyuan University of Technology(太原科技大学人工智能学院)
When Vision Meets Graphs: A Survey on Graph Reasoning and Learning
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));University of Waterloo(滑铁卢大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Oxford(牛津大学)
Covariance Descriptors Meet General Vision Encoders: Riemannian Deep Learning for Medical Image Classification
1 School of Computation, Information;Technology, Technical University of Munich, Germany 2 Munich Center for Machine Learning (MCML), Germany 3 Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Germany 4 School of Biomedical Engineering;Imaging Sciences, King’s College London, UK
LViT: Language meets Vision Transformer in Medical Image Segmentation
Xiamen University(厦门大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);UT Southwestern Medical Center(德克萨斯大学西南医学中心);University of Hull(赫尔大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)
When LLaVA Meets Objects: Token Composition for Vision-Language-Models
Tuebingen AI Center/University of Tuebingen(图宾根人工智能中心/图宾根大学);Max Planck Institute for Informatics, SIC(马克斯·普朗克信息学院,SIC);MIT-IBM Watson AI Lab(麻省理工-IBM沃森人工智能实验室)
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);University of Science and Technology Beijing(北京科技大学)
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Fraunhofer IOSB(弗劳恩霍夫光电、系统技术与图像利用研究所);Kitware, Inc.(Kitware公司);JD Finance America Corporation(京东金融美国公司);Tianjin University(天津大学);Stony Brook University(石溪大学);University of Central Florida(中佛罗里达大学);Huazhong University of Science and Technology(华中科技大学);Northwestern Polytechnical University(西北工业大学);Unisoc, Inc.(紫光展锐公司);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);DeepBlue Technology(Shanghai) Co., Ltd(深兰科技(上海)有限公司);Qatar University(卡塔尔大学);Beijing University of Posts and Telecommunications(北京邮电大学)
When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
King’s College London(伦敦国王学院);University of Luxembourg(卢森堡大学);Tongji University(同济大学);Shanghai Institute of Intelligent Science and Technology, Tongji University(同济大学上海智能科学与技术研究院)
A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
Kyung Hee University(庆熙大学);Beijing Institue of Technology(北京理工大学);KAIST(韩国科学技术院);Microsoft STCA(微软STCA);Harbin Institute of Technology(哈尔滨工业大学);The State University of New York - SUNY(纽约州立大学);Hong Kong Polytechnic University(香港理工大学)
本文综述了 Meta 的 SAM 及 SAM 2 模型,分析其在图像和视频分割中的能力、局限与未来方向,重点关注高粒度分割和提示缺失场景。
EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation
Cedars-Sinai Medical Center(西达赛奈医疗中心);University of California Los Angeles(加州大学洛杉矶分校);Stanford University(斯坦福大学);University of California, San Francisco(加州大学旧金山分校);San Francisco Veterans Affairs Medical Center(旧金山退伍军人事务医疗中心)
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning
School of Information and Communication Engineering, University of Electronic Science and Technology of China(电子科技大学信息与通信工程学院);School of Automation Engineering, University of Electronic Science and Technology of China(电子科技大学自动化工程学院);The Hong Kong Polytechnic University(香港理工大学);Hong Kong Polytechnic University Shenzhen Research Institute(香港理工大学深圳研究院);No.1 Orthopedic Hospital of Chengdu(成都市第一骨科医院)
Physical Adversarial Attack meets Computer Vision: A Decade Survey
Wuhan University(武汉大学);Peking University(北京大学);Zhejiang University(浙江大学);National Institute of Informatics(情报通信研究机构);The University of Tokyo(东京大学);ETH Zurich(苏黎世联邦理工学院);KU Leuven(鲁汶大学);INSAIT