AI 大模型

多模态大模型

跨文本、图像、视频、音频等模态的大模型与学习方法。

2025-08-05 至 2025-08-05 共收录 5 篇信号源：cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 音频语音多模态 5 篇

2508.02000 2025-08-05 cs.SD cs.CV eess.AS eess.IV 81%

Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling

Xuanjun Chen, Shih-Peng Cheng, Jiawei Du, Lin Zhang, Xiaoxiao Miao, Chung-Che Wang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang

专题命中音频语音多模态：audio-visual(title,abstract)；分类 cs.CV、eess.AS

Comments Work in progress

2507.21448 2025-08-05 eess.AS cs.ET cs.LG 79%

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations

T. Aleksandra Ma, Sile Yin, Li-Chia Yang, Shuo Zhang

机构 * School of Music（音乐学院）； Research（研究）

专题命中音频语音多模态：audio-visual(title,abstract)；分类 eess.AS

Comments Accepted into Interspeech 2025; corrected author name typo

2508.01915 2025-08-05 cs.CV cs.ET cs.HC cs.LG cs.SD eess.AS 62%

EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses

Akshay Paruchuri, Sinan Hersek, Lavisha Aggarwal, Qiao Yang, Xin Liu, Achin Kulshrestha, Andrea Colaco, Henry Fuchs, Ishan Chatterjee

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校）； Google（谷歌）

专题命中音频语音多模态：multi-modal(abstract)；分类 cs.CV、eess.AS

Comments 15 pages, 6 figres, 6 tables. Accepted to ISMAR 2025 as a TVCG journal paper

2409.06690 2025-08-05 cs.SD cs.AI cs.MM 62%

Benchmarking Sub-Genre Classification For Mainstage Dance Music

Hongzhi Shu, Xinglin Li, Hongyu Jiang, Minghao Fu, Xinyu Li

机构 * Johns Hopkins University（约翰霍普金斯大学）； Southeast University（东南大学）； National University of Defense Technology（国防科技大学）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

专题命中音频语音多模态：multimodal(abstract)；分类 cs.AI、cs.MM

Comments WASPAA 2025

2508.01092 2025-08-05 cs.HC 50%

DescribePro: Collaborative Audio Description with Human-AI Interaction

Maryam Cheema, Sina Elahimanesh, Samuel Martin, Pooyan Fazli, Hasti Seifi

专题命中音频语音多模态：multimodal(abstract)

Comments ASSETS 25 19 pages, 8 figures