ACM MM - arXivDaily 期刊&会议

2507.19201 2025-07-28 eess.IV cs.AI cs.CV

Joint Holistic and Lesion Controllable Mammogram Synthesis via Gated Conditional Diffusion Model

Xin Li, Kaixiang Yang, Qiang Li, Zhiwei Wang

机构 * Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学光电研究院）

Comments Accepted, ACM Multimedia 2025, 10 pages, 5 figures

2507.19077 2025-07-28 cs.CV

Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts

Yangyang Xu, Xi Ye, Duo Su

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）

Comments Accepted to ACM Multimedia 2025 (MM'25)

2507.19062 2025-07-28 cs.SD eess.AS

From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models

Zhaoxi Mu, Rilin Chen, Andong Li, Meng Yu, Xinyu Yang, Dong Yu

机构 * Xi'an Jiaotong University（西安交通大学）； Tencent AI Lab（腾讯AI实验室）； Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）

Comments ACMMM 2025

2507.18881 2025-07-28 cs.CV cs.RO

Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?

Bolei Chen, Jiaxu Kang, Haonan Yang, Ping Zhong, Jianxin Wang

机构 * School of Computer Science ； Engineering, Central South University Changsha Hunan China ； Engineering, Central South University

Comments Accepted by ACM MM 2025

2504.09540 2025-07-28 cs.CV

EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler

Hao Wang, Xiaobao Wei, Xiaoan Zhang, Jianing Li, Chengyu Bai, Ying Li, Ming Lu, Wenzhao Zheng, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）； School of electronic science and engineering, Nanjing University（电子科学与工程学院，南京大学）； Berkeley Artificial Intelligence Research Lab, Department of EECS, University of California, Berkeley（伯克利人工智能研究实验室，电子工程与计算机科学系，加州大学伯克利分校）

Comments Accepted by ACM MM 2025

2501.15775 2025-07-28 cs.CV cs.SE

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?

Yunbo Lyu, Zhou Yang, Yuqing Niu, Jing Jiang, David Lo

机构 * Singapore Management University（新加坡管理大学）； University of Alberta（阿尔伯塔大学）； Australian National University（澳大利亚国立大学）

Comments Accepted to ACM MM 2025