English
Related papers

Related papers: Unbiased Sliced Wasserstein Kernels for High-Quali…

200 papers

Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-08-03 Kanzhi Cheng , Zheng Ma , Shi Zong , Jianbing Zhang , Xinyu Dai , Jiajun Chen

Generative semantic communication models are reshaping semantic communication frameworks by moving beyond pixel-wise optimization to align with human perception. However, many existing approaches prioritize image-level perceptual quality,…

Signal Processing · Electrical Eng. & Systems 2025-04-08 Kailang Ye , Mingze Gong , Shuoyao Wang , Daquan Feng

Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are particularly important for understanding emotions from a…

Sound · Computer Science 2025-04-02 Jiachen Luo , Huy Phan , Lin Wang , Joshua Reiss

In current multimodal tasks, models typically freeze the encoder and decoder while adapting intermediate layers to task-specific goals, such as region captioning. Region-level visual understanding presents significant challenges for…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Yuan Sun , Zhao Zhang , Jorge Ortiz

Real-world speech communication is rarely affected by a single type of degradation. Instead, it suffers from a complex interplay of acoustic interference, codec compression, and, increasingly, secondary artifacts introduced by upstream…

Sound · Computer Science 2025-12-30 Junan Zhang , Mengyao Zhu , Xin Xu , Hui Bu , Zhenhua Ling , Zhizheng Wu

In this work, we propose Wasserstein distributionally robust shallow convex neural networks (WaDiRo-SCNNs) to provide reliable nonlinear predictions when subject to adverse and corrupted datasets. Our approach is based on the reformulation…

Machine Learning · Computer Science 2025-08-22 Julien Pallage , Antoine Lesage-Landry

The recently proposed relaxed binaural beamforming (RBB) optimization problem provides a flexible trade-off between noise suppression and binaural-cue preservation of the sound sources in the acoustic scene. It minimizes the output noise…

Sound · Computer Science 2019-05-28 Andreas I. Koutrouvelis , Richard C. Hendriks , Richard Heusdens , Jesper Jensen

The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Haoyu Zhao , Jiaxi Gu , Shicong Wang , Xing Zhang , Hang Xu , Zuxuan Wu , Yu-Gang Jiang

The reconstruction fidelity of computational optical imaging is fundamentally constrained by the model-reality gap, i.e., the inevitable discrepancy between idealized forward models and the physical imaging process. Conventional paradigms…

Optics · Physics 2026-05-22 Sui-peng Wang , Si-yi Xie , Chang-tao Cai , Zhun Wei , Rui Chen

We present a machine learning approach that ranked on the first place in the Arabic Dialect Identification (ADI) Closed Shared Tasks of the 2018 VarDial Evaluation Campaign. The proposed approach combines several kernels using multiple…

Computation and Language · Computer Science 2018-07-31 Andrei M. Butnaru , Radu Tudor Ionescu

Keyword spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction. However, standard KWS systems deployed on embedded devices often suffer performance degradation under real-world operating…

In this report we describe an ongoing line of research for solving single-channel source separation problems. Many monaural signal decomposition techniques proposed in the literature operate on a feature space consisting of a time-frequency…

Sound · Computer Science 2015-04-29 Pablo Sprechmann , Joan Bruna , Yann LeCun

Pre-trained models for automatic speech recognition (ASR) and speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, these models often suffer from severe performance degradation…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-03 Chien-Chun Wang , Hung-Shin Lee , Hsin-Min Wang , Berlin Chen

Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user navigation and downstream applications. However, current methods do not fully leverage acoustic…

Computation and Language · Computer Science 2026-02-09 Steffen Freisinger , Philipp Seeberger , Tobias Bocklet , Korbinian Riedhammer

Multimodal question answering (QA) often requires identifying which video, audio, or sensor tokens are relevant to the question. Yet modality disagreements are common: off-camera speech, background noise, or motion outside the field of view…

Computation and Language · Computer Science 2025-09-08 Subrata Biswas , Mohammad Nur Hossain Khan , Bashima Islam

Speaker verification is hampered by background noise, particularly at extremely low Signal-to-Noise Ratio (SNR) under 0 dB. It is difficult to suppress noise without introducing unwanted artifacts, which adversely affects speaker…

Sound · Computer Science 2024-01-08 Yi Ma , Kong Aik Lee , Ville Hautamäki , Meng Ge , Haizhou Li

Remote Sensing Image Change Captioning (RSICC) aims to generate spatially grounded natural language descriptions of scene evolution from bi-temporal imagery, moving beyond binary change masks toward semantic-level understanding. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Yupeng Gao , Tianyu Li , Guoqing Wang , Yang Yang

The Wasserstein distance received a lot of attention recently in the community of machine learning, especially for its principled way of comparing distributions. It has found numerous applications in several hard problems, such as domain…

Machine Learning · Statistics 2017-10-23 Nicolas Courty , Rémi Flamary , Mélanie Ducoffe

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

Computer Vision and Pattern Recognition · Computer Science 2021-03-01 Marimuthu Kalimuthu , Aditya Mogadala , Marius Mosbach , Dietrich Klakow

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, such methods are…

Machine Learning · Computer Science 2022-03-17 Dara Bahri , Heinrich Jiang , Yi Tay , Donald Metzler