English
Related papers

Related papers: SemanticAC: Semantics-Assisted Framework for Audio…

200 papers

We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not…

Computation and Language · Computer Science 2019-08-30 Angel Daza , Anette Frank

Deep learning has shown remarkable success in medical image analysis, but its reliance on large volumes of high-quality labeled data limits its applicability. While noisy labeled data are easier to obtain, directly incorporating them into…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Chengxuan Qian , Kai Han , Jianxia Ding , Chongwen Lyu , Zhenlong Yuan , Jun Chen , Zhe Liu

Cross-modal retrieval maps data under different modality via semantic relevance. Existing approaches implicitly assume that data pairs are well-aligned and ignore the widely existing annotation noise, i.e., noisy correspondence (NC).…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Shuai Lyu , Zijing Tian , Zhonghong Ou , Yifan Zhu , Xiao Zhang , Qiankun Ha , Haoran Luo , Meina Song

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining…

Computer Vision and Pattern Recognition · Computer Science 2018-03-26 Hang Zhang , Kristin Dana , Jianping Shi , Zhongyue Zhang , Xiaogang Wang , Ambrish Tyagi , Amit Agrawal

One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the…

Computer Vision and Pattern Recognition · Computer Science 2015-12-16 Marian-Andrei Rizoiu , Julien Velcin , Stéphane Lallich

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

Sound · Computer Science 2025-11-11 Mathias Rose Bjare , Giorgia Cantisani , Marco Pasini , Stefan Lattner , Gerhard Widmer

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-13 Imad Rida , Romain Hérault , Gilles Gasso

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-15 Shaoshi Ling , Yuzong Liu , Julian Salazar , Katrin Kirchhoff

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

Machine Learning · Computer Science 2025-05-29 Zi-Hao Zhou , Jun-Jie Wang , Tong Wei , Min-Ling Zhang

In this work, we aim to analyze and optimize the EnCLAP framework, a state-of-the-art model in automated audio captioning. We investigate the impact of modifying the acoustic encoder components, explore pretraining with different dataset…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Jaeyeon Kim , Minjeon Jeon , Jaeyoon Jung , Sang Hoon Woo , Jinjoo Lee

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

Computer Vision and Pattern Recognition · Computer Science 2017-06-12 Zhe Wang , Hongsheng Li , Wanli Ouyang , Xiaogang Wang

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…

Sound · Computer Science 2022-02-14 Yuan Gong , Cheng-I Jeff Lai , Yu-An Chung , James Glass

Incorporating pixel contextual information is critical for accurate segmentation. In this paper, we show that an effective way to incorporate contextual information is through a patch-based classifier. This patch classifier is trained to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Prantik Howlader , Srijan Das , Hieu Le , Dimitris Samaras

In order to leverage and profit from unlabelled data, semi-supervised frameworks for semantic segmentation based on consistency training have been proven to be powerful tools to significantly improve the performance of purely supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-12-09 Max Coenen , Tobias Schack , Dries Beyer , Christian Heipke , Michael Haist

Generating schema labels automatically for column values of data tables has many data science applications such as schema matching, and data discovery and linking. For example, automatically extracted tables with missing headers can be…

Machine Learning · Computer Science 2020-11-02 Mohamed Trabelsi , Jin Cao , Jeff Heflin

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

Sound · Computer Science 2026-04-21 Xingyuan Li , Mengyue Wu

Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Wangkai Li , Rui Sun , Zhaoyang Li , Tianzhu Zhang

This paper presents a semi-supervised learning framework that is new in being designed for automatic modulation classification (AMC). By carefully utilizing unlabeled signal data with a self-supervised contrastive-learning pre-training…

Machine Learning · Computer Science 2022-03-31 Dongxin Liu , Peng Wang , Tianshi Wang , Tarek Abdelzaher

Semantic communication is an increasingly popular framework for wireless image transmission due to its high communication efficiency. With the aid of the joint-source-and-channel (JSC) encoder implemented by neural network, semantic…

Information Theory · Computer Science 2022-12-02 Maojun Zhang , Yang Li , Zezhong Zhang , Guangxu Zhu , Caijun Zhong

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However,…

Sound · Computer Science 2019-07-05 Zhichao Zhang , Shugong Xu , Tianhao Qiao , Shunqing Zhang , Shan Cao