GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts
机构 * Dalian University of Technology（大连理工大学） ； Alibaba Group（阿里巴巴集团）
Comments ACM Multimedia 2025
期刊&会议
ACM MM
ACM International Conference on Multimedia · 会议 · Multimedia
Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
机构 * School of Computer Science and Technology, Xi'an Jiaotong University（计算机科学与技术学院，西安交通大学） ； Department of Electrical and Computer Engineering, University of Virginia（电气与计算机工程系，弗吉尼亚大学） ； Saw Swee Hock School of Public Health, National University of Singapore（Saw Swee Hock 公共卫生学院，新加坡国立大学） ； China Telecom Corporation Ltd. Shaanxi Branch（中国电信股份有限公司陕西分公司） ； School of Distance Education, Xi'an Jiaotong University（继续教育学院，西安交通大学）
Comments Accepted by ACM Multimedia 2025 (MM '25)
From Individuals to Crowds: Dual-Level Public Response Prediction in Social Media
Comments ACM MM 2025
UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken
机构 * School of Control Science and Engineering, Shandong University（控制科学与工程学院，山东大学） ； School of Data Science, Lingnan University（数据科学学院，岭南大学）
Comments ACM MM 2025
Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement
机构 * College of Artificial Intelligence, Southwest University（西南大学人工智能学院） ； Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Comments Accepted by ACM MM 2025
MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models
机构 * Harbin Institute of Technology（哈尔滨工业大学） ； The University of Hong Kong（香港大学） ； Central South University（中南大学）
Comments Accepted to ACM Multimedia 2025
Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
机构 * Northwestern Polytechnical University（西北工业大学） ； National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（集成空天地海大数据应用技术国家工程实验室）
Comments Accepted By ACM MM 25
ST-SAM: SAM-Driven Self-Training Framework for Semi-Supervised Camouflaged Object Detection
机构 * Jilin University（吉林大学） ； Dalian Minzu University（大连民族大学）
Comments 10 pages, 6 figures, ACM MM 2025
Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
机构 * School of Aeronautics and Astronautics, Sichuan University（四川大学航空宇航学院） ； Xiaomi Inc.（小米公司） ； University of Electronic Science and Technology of China（电子科技大学）
Comments Accepted by ACM MM 2025
LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks
机构 * Tianjin University of Technology（天津理工大学） ； Hainan University（海南大学）
Comments This paper has been accepted by ACM MM 2025
Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection
机构 * Tsinghua University（清华大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Southeast University（东南大学） ； University of Liverpool（利物浦大学） ； Beijing Institute of Technology（北京理工大学） ； Beijing University of Posts and Telecommunications（北京邮电大学）
Comments 10 pages, 6 figures. Supplementary material: 8 pages, 7 figures. Accepted at ACM Multimedia 2025
HER2 Expression Prediction with Flexible Multi-Modal Inputs via Dynamic Bidirectional Reconstruction
机构 * School of Computer Science and Technology, University of the Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院） ； School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院） ； Institute for Clarity in Documentation（清晰文档研究所） ； Inria Paris-Rocquencourt（巴黎- Rocquencourt 国家信息与自动化所） ； Rajiv Gandhi University（拉贾·甘地大学） ； Tsinghua University（清华大学） ； Palmer Research Laboratories（帕勒实验室）
Comments 8 pages,6 figures,3 tables,accepted by the 33rd ACM International Conference on Multimedia(ACM MM 2025)
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
机构 * Tsinghua University, Tencent（清华大学、腾讯） ； Tencent（腾讯） ； Tencent, University of Macau（腾讯、澳门大学） ； University of Science and Technology Beijing（北京科技大学） ； Tsinghua University（清华大学）
Comments Accepted by ACM Multimedia 2025
EEG-SCMM: Soft Contrastive Masked Modeling for Cross-Corpus EEG-Based Emotion Recognition
机构 * Shenzhen University（深圳大学）
Comments 18 pages, 10 figures, 14 tables. Accepted in ACMMM 2025
UIF: An Objective Quality Assessment for Underwater Image Enhancement
机构 * College of Physics and Information Engineering, Fuzhou University（物理与信息工程学院，福州大学）
Comments This paper was submitted to ACMMM 2021
Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； University of Toronto（多伦多大学）
Comments 15 pages, 11 figures, to be published in ACMMM 2025 Conference
DACA-Net: A Degradation-Aware Conditional Diffusion Network for Underwater Image Enhancement
机构 * The Hong Kong University of Science and Technology (Guangzhou), Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)（香港科学与技术大学（广州）、广东海洋工程科学实验室（广州）） ； The Hong Kong University of Science（香港科学与技术大学） ； Engineering Guangdong Laboratory (Guangzhou)（广东工程实验室（广州））
Comments accepted by ACM MM 2025
Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation
机构 * Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University（上海智能信息处理重点实验室，计算机科学与人工智能学院，复旦大学） ； The School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）
Comments Accepted to ACM MM'25: The 33rd ACM International Conference on Multimedia Proceedings
Traits Run Deep: Enhancing Personality Assessment via Psychology-Guided LLM Representations and Multimodal Apparent Behaviors
机构 * Hefei University of Technology（合肥工业大学）
Comments 8 pages, 3 figures, ACM MM 2025
See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
Comments Accepted by ACM MM25
Journal ref 33rd ACM International Conference on Multimedia 2025
Rethinking Individual Fairness in Deepfake Detection
机构 * Clarkstown High School South（Clarkstown 高中南分校） ； Purdue University（普渡大学） ； Carmel High School（Carmel 高中）
Comments This paper has been accepted by ACM MM 2025
Journal ref Proceedings of the 33rd ACM International Conference on Multimedia, 2025
Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection
机构 * School of Computer Science ； Engineering, Sun Yat-sen University Guangzhou China ； State Key Laboratory of Mathematical Engineering ； Engineering, Sun Yat-sen University
Comments Accepted by ACM MM 2025
Differential Contrastive Training for Gaze Estimation
机构 * Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通大数据挖掘与具身智能重点实验室） ； Beijing Jiaotong University（北京交通大学） ； School of Computer Science and Technology（计算机科学与技术学院）
Comments Accepted by ACM MM 2025
Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models
机构 * Shanghai Key Laboratory of Computer Software Testing and Evaluating（上海软件测试与评估 key laboratory） ； Shanghai Normal University（上海Normal University） ； TrustAI Pte. Ltd. ； East China Normal University（东华师范大学）
Comments Accepted by ACM Multimedia 2025
Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection
机构 * Hong Kong Polytechnic University（香港理工大学） ； Eastern Institute of Technology（东部技术研究所） ； Stanford University（斯坦福大学） ； Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究所，东部技术研究所） ； Institute for Clarity in Documentation（文档清晰研究所） ； Inria Paris-Rocquencourt（巴黎-罗克琴堡研究所） ； Rajiv Gandhi University（拉贾·甘地大学） ； Tsinghua University（清华大学） ； Palmer Research Laboratories（帕勒研究实验室）
Comments accepted by ACMMM 2025
PPJudge: Towards Human-Aligned Assessment of Artistic Painting Process
机构 * School of Computer Science and Technology（计算机科学与技术学院） ； East China Normal University（东华师范大学） ； School of Design（设计学院）
Comments ACM International Conference on Multimedia 2025
Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning
Comments Accepted by ACM MM 2025
Controllable Video-to-Music Generation with Multiple Time-Varying Conditions
机构 * Zhejiang University（浙江大学）
Comments Accepted by the 33rd ACM International Conference on Multimedia (ACMMM 2025). The project page is available at https://kita-wjx.github.io/MCV2M/
Lightweight Remote Sensing Scene Classification on Edge Devices via Knowledge Distillation and Early-exit
机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳研究院）
Comments 9 pages, 5 figures, to be published in ACM Multimedia 2025
VLMPlanner: Integrating Visual Language Models with Motion Planning
机构 * University of Science and Technology of China（科学技术大学） ； University of Adelaide（阿德莱德大学） ； 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）
Comments 8 pages, 3 figures, this paper has been accepted by ACM MM 2025
