MM-HSD: Multi-Modal Hate Speech Detection in Videos
机构 * EPFL（苏黎世联邦理工学院） ； Idiap Research Institute（日内瓦研究所）
Comments Accepted at ACM Multimedia 2025
期刊&会议
ACM MM
ACM International Conference on Multimedia · 会议 · Multimedia
Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection
机构 * PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（PCA实验室，计算机科学与工程学院，南京理工大学）
Comments Accepted by ACM MM 2025
A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task
机构 * The University of Tokyo（东京大学）
Comments Accepted to ACM Multimedia 2025. The dataset are publicly available at: https://huggingface.co/datasets/mashi6n/nhkrecipe-100-anno-1
SMARTe-VR: Student Monitoring and Adaptive Response Technology for e-Learning in Virtual Reality
机构 * BiDA Lab（BiDA实验室） ； Universidad Autonoma de Madrid（马德里自治大学） ； Nagao Laboratory（Nagao实验室） ； Nagoya University（名古屋大学）
Comments 10 pages, 3 figures. Published in ACM Intl. Conf. on Multimedia Workshops (ACM MM Workshops 2025, I2M-MM 25). Also presented at IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW) and AAAI Workshop on Artificial Intelligence for Education (AI4EDU)
DiffArtist: Towards Structure and Appearance Controllable Image Stylization
机构 * The Hong Kong Polytechnic University（香港理工大学）
Comments Accepted to ACM MM 2025, Homepage: https://DiffusionArtist.github.io
Event-Enriched Image Analysis Grand Challenge at ACM Multimedia 2025
机构 * University of Science（科学大学） ； University of Dayton（代顿大学）
Comments ACM Multimedia 2025
adder-viz: Real-Time Visualization Software for Transcoding Event Video
机构 * Baylor University（贝勒大学）
Comments Accepted to the Open-Source Track at ACM Multimedia 2025
MultiRef: Controllable Image Generation with Multiple Visual References
机构 * Zhejiang Wanli University（浙江万里大学） ； University of Washington（华盛顿大学） ； Huazhong University of Science and Technology（华中科技大学） ； Allen Institute for AI（人工智能研究院）
Comments Accepted to ACM MM 2025 Datasets
Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation
机构 * Korea Advanced Institute of Science \& Technology School of Electrical Engineering Daejeon Republic of Korea ； Kyungpook National University School of Computer Science ； Korea Advanced Institute of Science \& Technology ； Kyungpook National University
Comments Accepted to ACM MM 2025. 9 pages, 8 figures, 6 tables
OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding
机构 * University of Science（科学大学） ； University of Dayton（戴维森大学）
Comments ACM Multimedia 2025
Decoupled Global-Local Alignment for Improving Compositional Understanding
机构 * Beijing Institute of Technology（北京理工大学） ； Zhejiang University（浙江大学）
Comments ACMMM 2025
VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（多媒体可信感知与高效计算重点实验室，教育部，厦门大学） ； Tencent Youtu Lab（腾讯优图实验室）
Comments Accepted by ACMMM 2025
Generative Flow Networks for Personalized Multimedia Systems: A Case Study on Short Video Feeds
Comments ACM Multimedia 2025
Generative AI for Multimedia Communication: Recent Advances, An Information-Theoretic Framework, and Future Opportunities
Comments ACM Multimedia 2025
E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
机构 * School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学） ； National University of Singapore（新加坡国立大学） ； School of Future Technology, Dalian University of Technology（未来技术学院，大连理工大学）
Comments 16 pages, 10 figures, 5 Tables, accepted by ACMMM 2025
Frequency Regulation for Exposure Bias Mitigation in Diffusion Models
机构 * School of Information Science and Engineering（信息科学与工程学院）
Comments ACM Multimedia 2025 accepted!
Boosting Temporal Sentence Grounding via Causal Inference
机构 * School of Electronic Engineering, Xidian University Xi'an China ； School of Information Science \& Engineering, Lanzhou University Lanzhou China ； Xidian University ； Lanzhou University
Comments Accepted by ACM MM 2025
Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning Benchmark
机构 * Hefei University of Technology（合肥工业大学） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； University of Science and Technology of China（中国科学技术大学） ； Institute of Artificial Intelligence (IAI), Hefei Comprehensive National Science Center（人工智能研究院（IAI），合肥综合性国家科学中心）
Comments ACM Multimedia 2025
PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting
机构 * Sungkyunkwan University（成均馆大学）
Comments Accepted to ACM MM 2025
Hierarchical Vision-Language Reasoning for Multimodal Multiple-Choice Question Answering
机构 * 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） ； Chongqing University of Posts and Telecommunications（重庆邮电大学）
Comments This paper has been accepted by ACM MM 2025
Cross-Modal Prototype Augmentation and Dual-Grained Prompt Learning for Social Media Popularity Prediction
Comments This paper has been accepted by ACM MM 2025
AudioSet-R: A Refined AudioSet with Multi-Stage LLM Label Reannotation
机构 * College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）
Comments 8 pages, 5 figures, accepted in ACM MM 2025 dataset track
TiP4GEN: Text to Immersive Panorama 4D Scene Generation
机构 * Institute of Information Science, Beijing Jiaotong University（信息科学研究院，北京交通大学） ； Visual Intelligence + X International Joint Laboratory（视觉智能+X国际联合实验室） ； University of Toronto（多伦多大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments Accepted In Proceedings of the 33rd ACM International Conference on Multimedia (MM' 25)
Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
机构 * School of Software（软件学院） ； Beihang University（北航） ； Qingdao Research Institute（青岛研究院）
Comments Accepted by ACM MM 2025
RATopo: Improving Lane Topology Reasoning via Redundancy Assignment
机构 * School of Artificial Intelligence Beihang University Beijing China（人工智能学院 北航 北京 中国） ； Zhongguancun Academy Beijing China（中关村学院 北京 中国） ； Hangzhou International Innovation Institute Beihang University Hangzhou China（杭州国际创新研究院 北航 杭州 中国） ； Beihang University（北航） ； Zhongguancun Academy（中关村学院） ； University of Macau（澳门大学）
Comments Accepted by ACM MM 2025
AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation
机构 * Beihang University（北京航空航天大学） ； Sangfor Technologies Inc.（深信服科技有限公司） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Comments Accepted by ACM MM 2025
Generating Negative Samples for Multi-Modal Recommendation
Comments Accepted by ACM Multimedia
AnchorSync: Global Consistency Optimization for Long Video Editing
机构 * MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University Shanghai China（人工智能联合实验室，人工智能研究院，上海交通大学）
Comments ACM MM 2025; Code is released at https://github.com/VISION-SJTU/AnchorSync
Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement
机构 * Singapore Management University（新加坡国立管理学院） ； Fudan University（复旦大学）
Comments Accepted by ACM MM 2025
Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks
机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Nanyang Technological University（南洋理工大学）
Comments Accepted for publication at ACM Multimedia (ACM MM) 2025. 10 pages, 5 figures. Code and dataset: https://github.com/zqxwcevrtyui/DP2Rec
