Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study

著者: Ghorbanpour, Faeze, Dementieva, Daryna, Fraser, Alexander

件名: Computer Science - Computation and Language, Computer Science - Computers and Society, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.06149

Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models

著者: Ghorbanpour, Faeze, Malaguth, Thiago Zordan, Akbaritabar, Aliakbar

件名: Computer Science - Digital Libraries, Computer Science - Computation and Language, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.06107

Does CLIP perceive art the same way we do?

著者: Asperti, Andrea, Dessì, Leonardo, Tonetti, Maria Chiara, Wu, Nico

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia, 68T45, 68T07 (Primary) 68T50, 68U10 (Secondary), I.2.7, I.2.10

アクセスURL: http://arxiv.org/abs/2505.05229

SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal

著者: Liu, Wenyang, Gao, Jianjun, Yap, Kim-Hui

件名: Computer Science - Multimedia, Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing

アクセスURL: http://arxiv.org/abs/2505.05088

Learning Item Representations Directly from Multimodal Features for Effective Recommendation

著者: Zhou, Xin, Zhang, Xiaoxiong, Niyato, Dusit, Shen, Zhiqi

件名: Computer Science - Information Retrieval, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.04960

Unsupervised Blind Speech Separation with a Diffusion Prior

著者: Xu, Zhongweiyang, Fan, Xulin, Wang, Zhong-Qiu, Jiang, Xilin, Choudhury, Romit Roy

件名: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Multimedia, Computer Science - Sound, Electrical Engineering and Systems Science - Signal Processing

アクセスURL: http://arxiv.org/abs/2505.05657

'I Can See Forever!': Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments

著者: Zhang, Ziyi, Sun, Zhen, Zhang, Zongmin, Peng, Zifan, Zhao, Yuemeng, Wang, Zichun, Luo, Zeren, Zuo, Ruiting, He, Xinlei

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.04488

Securing Immersive 360 Video Streams through Attribute-Based Selective Encryption

著者: Usmani, Mohammad Waquas, Shannigrahi, Susmit, Zink, Michael

件名: Computer Science - Multimedia, Computer Science - Cryptography and Security, Electrical Engineering and Systems Science - Image and Video Processing

アクセスURL: http://arxiv.org/abs/2505.04466

Automatic Music Transcription using Convolutional Neural Networks and Constant-Q transform

著者: Telila, Yohannis, Cucinotta, Tommaso, Bacciu, Davide

ソース: 3rd National CINI Conference on Artificial Intelligence (Ital-IA 2023)

件名: Computer Science - Sound, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing

アクセスURL: http://arxiv.org/abs/2505.04451

HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation

著者: Fu, Yajie, Huang, Chaorui, Li, Junwei, Kong, Hui, Tian, Yibin, Li, Huakang, Zhang, Zhiyuan

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.04276

RFNNS: Robust Fixed Neural Network Steganography with Popular Deep Generative Models

著者: Cheng, Yu, Zhou, Jiuan, Chen, Jiawei, Yin, Zhaoxia, Zhang, Xinpeng

件名: Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.04116

A Multi-Agent AI Framework for Immersive Audiobook Production through Spatial Audio and Neural Narration

著者: Selvamani, Shaja Arul, Ganapathy, Nia D'Souza

件名: Computer Science - Sound, Computer Science - Human-Computer Interaction, Computer Science - Multiagent Systems, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing

アクセスURL: http://arxiv.org/abs/2505.04885

EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning

著者: Xing, Zhenghao, Hu, Xiaowei, Fu, Chi-Wing, Wang, Wenhai, Dai, Jifeng, Heng, Pheng-Ann

件名: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia, Computer Science - Sound

アクセスURL: http://arxiv.org/abs/2505.04623

Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond

著者: Richter-Powell, Jessie, Torralba, Antonio, Lorraine, Jonathan

件名: Computer Science - Sound, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing, 68T07, I.2.6, H.5.5, H.5.1

アクセスURL: http://arxiv.org/abs/2505.04621

PAHA: Parts-Aware Audio-Driven Human Animation with Diffusion Model

著者: Wang, Y. B., Zhou, S. Z., Wu, J. F., Hu, T., Zhang, J. N., Liu, Y.

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.03603

Modeling Musical Genre Trajectories through Pathlet Learning

著者: Marey, Lilian, Laclau, Charlotte, Sguerra, Bruno, Viard, Tiphaine, Moussallam, Manuel

件名: Computer Science - Information Retrieval, Computer Science - Machine Learning, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.03480

Mitigating Image Captioning Hallucinations in Vision-Language Models

著者: Zhao, Fei, Zhang, Chengcui, Zhang, Runlin, Wang, Tianyang, Li, Xi

件名: Computer Science - Multimedia, Computer Science - Computer Vision and Pattern Recognition

アクセスURL: http://arxiv.org/abs/2505.03420

SD-VSum: A Method and Dataset for Script-Driven Video Summarization

著者: Mylonas, Manolis, Apostolidis, Evlampios, Mezaris, Vasileios

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.03319

FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios

著者: Zhang, Shiyi, Zhuang, Junhao, Zhang, Zhaoyang, Shan, Ying, Tang, Yansong

件名: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.03730

EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events

著者: Wei, Shuoyan, Li, Feng, Tang, Shengeng, Zhao, Yao, Bai, Huihui

件名: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Multimedia

アクセスURL: http://arxiv.org/abs/2505.04657