Computer Vision and Pattern Recognition

Authors and titles for May 2025

[101] arXiv:2505.01431 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection Show Chinese title

Title: ZS-VCOS：通过光流和开放词汇目标检测的零样本视频伪装目标分割

Wenqi Guo, Mohamed Shehata, Shan Du

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[102] arXiv:2505.01481 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding Show Chinese title

Title: VideoHallu：评估和缓解合成视频理解中的多模态幻觉

Zongxia Li, Xiyang Wu, Guangyao Shi, Yubin Qin, Hongyang Du, Tianyi Zhou, Dinesh Manocha, Jordan Lee Boyd-Graber

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[103] arXiv:2505.01490 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation Show Chinese title

Title: WorldGenBench：一种整合世界知识的推理驱动文本到图像生成基准测试

Daoan Zhang, Che Jiang, Ruoshi Xu, Biaoxiang Chen, Zijian Jin, Yutian Lu, Jianguo Zhang, Liang Yong, Jiebo Luo, Shengda Luo

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[104] arXiv:2505.01530 (cross-list from cs.CV) [cn-pdf, pdf, other]

Title: Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer Show Chinese title

Title: 基于微调文档理解变压器的工程图自动解析用于结构化信息提取

Muhammad Tayyab Khan, Zane Yong, Lequn Chen, Jun Ming Tan, Wenhe Feng, Seung Ki Moon

Comments: This manuscript has been accepted for publication at IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[105] arXiv:2505.01548 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Learning Flow-Guided Registration for RGB-Event Semantic Segmentation Show Chinese title

Title: 基于学习流引导的RGB-事件语义分割

Zhen Yao, Xiaowen Ying, Zhiyu Zhu, Mooi Choo Chuah

Comments: 20 pages, 14 figures

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[106] arXiv:2505.01558 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning Show Chinese title

Title: 一种传感器无关的领域泛化框架以利用地理空间基础模型：通过协同伪标签和生成学习增强语义分割

Anan Yaghmour, Melba M. Crawford, Saurabh Prasad

Comments: Accepted in the 2025 CVPR Workshop on Foundation and Large Vision Models in Remote Sensing, to appear in CVPR 2025 Workshop Proceedings

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[107] arXiv:2505.01571 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: PainFormer: a Vision Foundation Model for Automatic Pain Assessment Show Chinese title

Title: 疼痛Former：一种用于自动疼痛评估的视觉基础模型

Stefanos Gkikas, Raul Fernandez Rojas, Manolis Tsiknakis

Journal-ref: IEEE Transactions on Affective Computing; 2025

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[108] arXiv:2505.01578 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Grounding Task Assistance with Multimodal Cues from a Single Demonstration Show Chinese title

Title: 基于单次演示的多模态线索的任务辅助接地

Gabriel Sarch, Balasaravanan Thoravi Kumaravel, Sahithya Ravi, Vibhav Vineet, Andrew D. Wilson

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[109] arXiv:2505.01583 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action Show Chinese title

Title: TEMPURA：用于动作推理的时间事件掩码预测和理解

Jen-Hao Cheng, Vivian Wang, Huayu Wang, Huapeng Zhou, Yi-Hao Peng, Hou-I Liu, Hsiang-Wei Huang, Kuang-Ming Chen, Cheng-Yen Yang, Wenhao Chai, Yi-Ling Chen, Vibhav Vineet, Qin Cai, Jenq-Neng Hwang

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[110] arXiv:2505.01615 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Multimodal and Multiview Deep Fusion for Autonomous Marine Navigation Show Chinese title

Title: 多模态和多视角深度融合在自主海洋导航中的应用

Dimitrios Dagdilelis, Panagiotis Grigoriadis, Roberto Galeazzi

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[111] arXiv:2505.01650 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Toward Onboard AI-Enabled Solutions to Space Object Detection for Space Sustainability Show Chinese title

Title: 面向在轨人工智能赋能的空间目标检测的太空可持续性解决方案

Wenxuan Zhang, Peng Hu

Comments: This paper has been accepted at the 18th International Conference on Space Operations (SpaceOps 2025)

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV)

[112] arXiv:2505.01656 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: A Novel WaveInst-based Network for Tree Trunk Structure Extraction and Pattern Analysis in Forest Inventory Show Chinese title

Title: 一种基于WaveInst的新型网络用于森林调查中的树干结构提取与模式分析

Chenyang Fan, Xujie Zhu, Taige Luo, Sheng Xu, Zhulin Chen, Hongxin Yang

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[113] arXiv:2505.01664 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Soft-Masked Semi-Dual Optimal Transport for Partial Domain Adaptation Show Chinese title

Title: 软掩码半双重最优传输用于部分领域自适应

Yi-Ming Zhai, Chuan-Xian Ren, Hong Yan

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[114] arXiv:2505.01680 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Automated ARAT Scoring Using Multimodal Video Analysis, Multi-View Fusion, and Hierarchical Bayesian Models: A Clinician Study Show Chinese title

Title: 基于多模态视频分析、多视角融合和分层贝叶斯模型的自动ARAT评分：一项临床医生研究

Tamim Ahmed, Thanassis Rikakis

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC) ; Probability (math.PR)

[115] arXiv:2505.01694 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Topology-Aware CLIP Few-Shot Learning Show Chinese title

Title: 基于拓扑感知的CLIP小样本学习

Dazhi Huang

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[116] arXiv:2505.01699 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning Show Chinese title

Title: 基于组件的公平性在贝叶斯网络引导的元学习中的面部属性分类

Yifan Liu, Ruichen Yao, Yaokun Liu, Ruohan Zong, Zelin Li, Yang Zhang, Dong Wang

Comments: Accepted by ACM FAccT 2025

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[117] arXiv:2505.01711 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings Show Chinese title

Title: 知识增强的语言模型解读结构化胸片检查结果

Alexander Davis, Rafael Souza, Jia-Hao Lim

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[118] arXiv:2505.01713 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Vision and Intention Boost Large Language Model in Long-Term Action Anticipation Show Chinese title

Title: 视觉与意图增强长期行动预测的大语言模型

Congqi Cao, Lanshu Hu, Yating Yu, Yanning Zhang

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[119] arXiv:2505.01726 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes Show Chinese title

Title: 具有分层神经过程的概率交互式3D分割

Jie Liu, Pan Zhou, Zehao Xiao, Jiayi Shen, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves

Comments: ICML 2025 Proceedings

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[120] arXiv:2505.01729 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth Show Chinese title

Title: PosePilot：通过自监督深度引导生成世界模型的相机姿态

Bu Jin, Weize Li, Baihan Yang, Zhenxin Zhu, Junpeng Jiang, Huan-ang Gao, Haiyang Sun, Kun Zhan, Hengtong Hu, Xueyang Zhang, Peng Jia, Hao Zhao

Comments: Accepted at IEEE/RSJ IROS 2025

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[121] arXiv:2505.01737 (cross-list from cs.CV) [cn-pdf, pdf, other]

Title: Learning Multi-frame and Monocular Prior for Estimating Geometry in Dynamic Scenes Show Chinese title

Title: 学习多帧和单目先验以估计动态场景中的几何结构

Seong Hyeon Park, Jinwoo Shin

Comments: This paper was supported by RLWRLD

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[122] arXiv:2505.01743 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding Show Chinese title

Title: 一种基于大型语言模型的低分辨率视觉系统用于设备端人类行为理解

Siyang Jiang, Bufang Yang, Lilin Xu, Mu Yuan, Yeerzhati Abudunuer, Kaiwei Liu, Liekang Zeng, Hongkai Chen, Zhenyu Yan, Xiaofan Jiang, Guoliang Xing

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG)

[123] arXiv:2505.01746 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion Show Chinese title

Title: 协同$^{3}$手势：迈向交互式扩散的连贯并发口语 3D 手势生成

Xingqun Qi, Yatian Wang, Hengyuan Zhang, Jiahao Pan, Wei Xue, Shanghang Zhang, Wenhan Luo, Qifeng Liu, Yike Guo

Comments: Accepted as ICLR 2025 (Spotlight)

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[124] arXiv:2505.01766 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement Show Chinese title

Title: 基于多模态图表示学习的鲁棒手术工作流程识别与对抗特征解缠

Long Bai, Boyi Ma, Ruohan Wang, Guankun Wang, Beilei Cui, Zhongliang Jiang, Mobarakol Islam, Zhe Min, Jiewen Lai, Nassir Navab, Hongliang Ren

Comments: Accepted by Information Fusion

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO)

[125] arXiv:2505.01790 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Enhancing the Learning Experience: Using Vision-Language Models to Generate Questions for Educational Videos Show Chinese title

Title: 提升学习体验：利用视觉-语言模型为教育视频生成问题

Markos Stamatakis, Joshua Berger, Christian Wartena, Ralph Ewerth, Anett Hoppe

Comments: 12 pages (excluding references), 8 tables, 1 equation

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL) ; Multimedia (cs.MM)

[126] arXiv:2505.01799 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: AquaGS: Fast Underwater Scene Reconstruction with SfM-Free Gaussian Splatting Show Chinese title

Title: AquaGS：基于无SfM高斯点绘制的快速水下场景重建

Junhao Shi, Jisheng Xu, Jianping He, Zhiliang Lin

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[127] arXiv:2505.01802 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows Show Chinese title

Title: 基于时间窗口的稀疏跟踪输入的高效三维全身运动生成

Georgios Fotios Angelis, Savas Ozkan, Sinan Mutlu, Paul Wisbey, Anastasios Drosou, Mete Ozay

Comments: Accepted to CVPRW2025 - 4D Vision Workshop

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[128] arXiv:2505.01805 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Not Every Tree Is a Forest: Benchmarking Forest Types from Satellite Remote Sensing Show Chinese title

Title: 并非每棵树都是森林：基于卫星遥感的森林类型基准测试

Yuchang Jiang, Maxim Neumann

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[129] arXiv:2505.01809 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: 3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment Show Chinese title

Title: 3DWG: 通过类别和实例级对齐的弱监督三维视觉定位

Xiaoqi Li, Jiaming Liu, Nuowei Han, Liang Heng, Yandong Guo, Hao Dong, Yang Liu

Comments: ICRA 2025

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[130] arXiv:2505.01823 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach Show Chinese title

Title: PhytoSynth：利用多模态生成模型进行作物病害数据生成并采用新颖的基准测试和提示工程方法

Nitin Rai, Arnold W. Schumann, Nathan Boyd

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Emerging Technologies (cs.ET)

[131] arXiv:2505.01837 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: CVVNet: A Cross-Vertical-View Network for Gait Recognition Show Chinese title

Title: CVVNet：一种用于步态识别的跨垂直视图网络

Xiangru Li, Wei Song, Yingda Huang, Wei Meng, Le Chang, Hongyang Li

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[132] arXiv:2505.01838 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization Show Chinese title

Title: MVHumanNet++：一个大规模多视角日常穿衣人体捕捉数据集，具有更丰富的三维人体数字化标注

Chenghong Li, Hongjie Liao, Yihao Zhi, Xihe Yang, Zhengwentai Sun, Jiahao Chang, Shuguang Cui, Xiaoguang Han

Comments: project page: https://kevinlee09.github.io/research/MVHumanNet++/. arXiv admin note: substantial text overlap with arXiv:2312.02963

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[133] arXiv:2505.01851 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Mitigating Group-Level Fairness Disparities in Federated Visual Language Models Show Chinese title

Title: 缓解联邦视觉语言模型中的群体级公平性差异

Chaomeng Chen, Zitong Yu, Junhao Dong, Sen Su, Linlin Shen, Shutao Xia, Xiaochun Cao

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[134] arXiv:2505.01857 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion Show Chinese title

Title: DualDiff：具有语义融合的双分支扩散模型在自动驾驶中的应用

Haoteng Li, Zhao Yang, Zezhong Qian, Gongpeng Zhao, Yuqi Huang, Jun Yu, Huazheng Zhou, Longjun Liu

Comments: 8 pages, 6 figures,

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[135] arXiv:2505.01869 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Visual enhancement and 3D representation for underwater scenes: a review Show Chinese title

Title: 水下场景的视觉增强和三维表示：一项综述

Guoxi Huang, Haoran Wang, Brett Seymour, Evan Kovacs, John Ellerbrock, Dave Blackham, Nantheera Anantrasirichai

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[136] arXiv:2505.01881 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications Show Chinese title

Title: PhysNav-DG：导航应用中稳健的VLM-传感器融合的新自适应框架

Trisanth Srinivasan, Santosh Patapati

Comments: Accepted at IEEE/CVF Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2025 (CVPRW)

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG) ; Multimedia (cs.MM) ; Robotics (cs.RO)

[137] arXiv:2505.01882 (cross-list from cs.CV) [cn-pdf, pdf, other]

Title: CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture Show Chinese title

Title: CMAWRNet：基于统一四元数神经架构的多种恶劣天气去除方法

Vladimir Frants, Sos Agaian, Karen Panetta, Peter Huang

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[138] arXiv:2505.01888 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Rethinking Score Distilling Sampling for 3D Editing and Generation Show Chinese title

Title: 重思三维编辑和生成中的分数蒸馏采样方法

Xingyu Miao, Haoran Duan, Yang Long, Jungong Han

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[139] arXiv:2505.01928 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: GenSync: A Generalized Talking Head Framework for Audio-driven Multi-Subject Lip-Sync using 3D Gaussian Splatting Show Chinese title

Title: GenSync：一种用于多主体唇同步的通用音频驱动3D高斯点撒布谈话头框架

Anushka Agarwal, Muhammad Yusuf Hassan, Talha Chafekar

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[140] arXiv:2505.01934 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels Show Chinese title

Title: 高斯-SLAM：基于高斯曲面片的密集RGB-D SLAM

Yongxin Su, Lin Chen, Kaiting Zhang, Zhongliang Zhao, Chenfeng Hou, Ziping Yu

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[141] arXiv:2505.01938 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder Show Chinese title

Title: HybridGS：基于双通道稀疏表示和点云编码器的高效率高斯散射数据压缩

Qi Yang, Le Yang, Geert Van Der Auwera, Zhu Li

Comments: Accepted by ICML2025

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Image and Video Processing (eess.IV)

[142] arXiv:2505.01950 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Segment Any RGB-Thermal Model with Language-aided Distillation Show Chinese title

Title: 带有语言辅助蒸馏的任意RGB-热模型分割

Dong Xing, Xianxun Zhu, Wei Zhou, Qika Lin, Hang Yang, Yuqing Wang

Comments: arXiv admin note: text overlap with arXiv:2412.04220 by other authors

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI)

[143] arXiv:2505.01958 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models Show Chinese title

Title: 大型视觉-语言模型中视觉目标幻觉的综合分析

Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du

Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL)

[144] arXiv:2505.01969 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection Show Chinese title

Title: MC3D-AD：多类别3D异常检测的统一几何感知重建模型

Jiayi Cheng, Can Gao, Jie Zhou, Jiajun Wen, Tao Dai, Jinbao Wang

Comments: 7 pages of main text, 3 pages of appendix, accepted to IJCAI 2025

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[145] arXiv:2505.01973 (cross-list from cs.CV) [cn-pdf, pdf, other]

Title: Visual Dominance and Emerging Multimodal Approaches in Distracted Driving Detection: A Review of Machine Learning Techniques Show Chinese title

Title: 分心驾驶检测中的视觉主导与新兴多模态方法：机器学习技术回顾

Anthony Dontoh, Stephanie Ivey, Logan Sirbaugh, Andrews Danyo, Armstrong Aboah

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[146] arXiv:2505.01984 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation Show Chinese title

Title: 终身全幻灯片图像分析：在线视觉-语言适应和过去到现在的梯度蒸馏

Doanh C. Bui, Hoai Luan Pham, Vu Trung Duong Le, Tuan Hai Vu, Van Duy Tran, Khang Nguyen, Yasuhiko Nakashima

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[147] arXiv:2505.01986 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Drug classification based on X-ray spectroscopy combined with machine learning Show Chinese title

Title: 基于X射线光谱结合机器学习的药物分类

Yongming Li, Peng Wang, Bangdong Han

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[148] arXiv:2505.02005 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields Show Chinese title

Title: 学习用于大规模神经辐射场的异质场景专家混合模型

Zhenxing Mi, Ping Yin, Xue Xiao, Dan Xu

Comments: Accepted by TPAMI

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[149] arXiv:2505.02007 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: Efficient Noise Calculation in Deep Learning-based MRI Reconstructions Show Chinese title

Title: 基于深度学习的MRI重建中的高效噪声计算

Onat Dalmaz, Arjun D. Desai, Reinhard Heckel, Tolga Çukur, Akshay S. Chaudhari, Brian A. Hargreaves

Comments: Accepted ICML 2025. Supplementary material included

Subjects: Computer Vision and Pattern Recognition (cs.CV)

[150] arXiv:2505.02013 (cross-list from cs.CV) [cn-pdf, pdf, html, other]

Title: MLLM-Enhanced Face Forgery Detection: A Vision-Language Fusion Solution Show Chinese title

Title: 基于多语言大型模型增强的面部伪造检测：一种视觉-语言融合解决方案

Siran Peng, Zipei Wang, Li Gao, Xiangyu Zhu, Tianshuo Zhang, Ajian Liu, Haoyuan Zhang, Zhen Lei

Subjects: Computer Vision and Pattern Recognition (cs.CV)