检索结果-内蒙古大学图书馆

Zero-Shot Audio Captioning Using Soft and Hard Prompts

学校读者我要写书评

暂无评论

IEEE Transactions on Audio, Speech and Language Processing

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

Online Discriminative Semantic-Preserving Hashing for Large-Scale Cross-Modal Retrieval 18th

学校读者我要写书评

暂无评论

Online Discriminative Semantic-Preserving Hashing for Large-...

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Yi, Jinhan He, Yi Liu, Xin Department of Computer Science and Technology Huaqiao University Xiamen361021 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Xiamen China

ISBN: (纸本)9783030891879

Cross-modal hashing has drawn increasing attentions for efficient retrieval across different modalities, and existing methods primarily learn the hash functions in a batch based mode, i.e., offline methods. Nevertheless, the multimedia data often comes in a streaming fashion, which makes the batch based learning methods uncompetitive for large-scale streaming data due to the large memory consumption and calculation. To address this problem, we present an Online Discriminative Semantic-Preserving Hashing (ODSPH) method for large-scale cross-modal retrieval, featuring on fast training speed, low memory consumption and high retrieval accuracy. Within the proposed ODSPH framework, we utilize the newly coming data points to learn the hash codes and update hash functions in a stream manner. When new data comes, the corresponding hash codes are obtained by regressing the class label of the training examples. For hash function, we update it with the accumulated information from each round. Besides, we design a novel momentum updating method to adaptively update the hash function and reduce quantization loss, which can produce discriminative hash codes for high retrieval precision. Extensive experiments on three benchmark datasets show that the proposed ODSPH method improves the retrieval performance over the state-of-the-arts. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

An Hybrid Attention-Based System for the Prediction of Facial Attributes 4th

学校读者我要写书评

暂无评论

An Hybrid Attention-Based System for the Prediction of Fac...

4th International Workshop on Brain-Inspired Computing, BrainComp 2019

作者： Khellat-Kihel, Souad Sun, Zhenan Tistarelli, Massimo Computer Vision Laboratory University of Sassari Viale Italia 39 Sassari07100 Italy Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Room 1605 Intelligence Bulding 95 Zhongguancun East Road Beijing100190 China Computer Vision Laboratory Department of Biomedical Sciences and Information Technology University of Sassari Viale S. Pietro 43/b Sassari07100 Italy

ISBN: (纸本)9783030824266

Recent research on face analysis has demonstrated the richness of information embedded in feature vectors extracted from a deep convolutional neural network. Even though deep learning achieved a very high performance on several challenging visual tasks, such as determining the identity, age, gender and race, it still lacks a well grounded theory which allows to properly understand the processes taking place inside the network layers. Therefore, most of the underlying processes are unknown and not easy to control. On the other hand, the human visual system follows a well understood process in analyzing a scene or an object, such as a face. The direction of the eye gaze is repeatedly directed, through purposively planned saccadic movements, towards salient regions to capture several details. In this paper we propose to capitalize on the knowledge of the saccadic human visual processes to design a system to predict facial attributes embedding a biologically-inspired network architecture, the HMAX. The architecture is tailored to predict attributes with different textural information and conveying different semantic meaning, such as attributes related and unrelated to the subject’s identity. Salient points on the face are extracted from the outputs of the S2 layer of the HMAX architecture and fed to a local texture characterization module based on LBP (Local Binary pattern). The resulting feature vector is used to perform a binary classification on a set of pre-defined visual attributes. The devised system allows to distill a very informative, yet robust, representation of the imaged faces, allowing to obtain high performance but with a much simpler architecture as compared to a deep convolutional neural network. Several experiments performed on publicly available, challenging, large datasets demonstrate the validity of the proposed approach. © 2021, The Author(s).

关键词： Network architecture

Zero-Shot Audio Captioning Using Soft and Hard Prompts

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yiming Xu, Xuenan Du, Ruoyi Liu, Haohe Dong, Yuan Tan, Zheng-Hua Wang, Wenwu Ma, Zhanyu The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Electronic Systems Aalborg University Aalborg9220 Denmark The Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We propose an effective audio captioning method based on the contrastive language-audio pre-training (CLAP) model to address these issues. Our proposed method requires only textual data for training, enabling the model to generate text from the textual feature in the cross-modal semantic space. In the inference stage, the model generates the descriptive text for the given audio from the audio feature by leveraging the audio-text alignment from CLAP. We devise two strategies to mitigate the discrepancy between text and audio embeddings: a mixed-augmentation-based soft prompt and a retrieval-based acoustic-aware hard prompt. These approaches are designed to enhance the generalization performance of our proposed model, facilitating the model to generate captions more robustly and accurately. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method. © 2024, CC BY.

关键词： Semantics

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Wenjie Wang, Mei Zhang, Kai Li, Juncheng Li, Xiaoming Zhang, Yuhang Gao, Guangwei Deng, Weihong Lin, Chia-Wen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China The Computer Vision Lab ETH Zürich Zürich Switzerland The School of Communication and Information Engineering Shanghai University Shanghai China The Nanyang Technological University Singapore The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://***/24wenjie-li/Awesome-Face-Restoration. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

Multi-granulation variable precision rough set based on limited tolerance relation

学校读者我要写书评

暂无评论

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第3期83卷 63-74页

作者： Wan, Renxia Yao, Yonghong Kumar, Hussain School of Mathematics and Information Science North Minzu University Ningxia750021 China HongYang Institute for Big Data in Health Fuzhou Fujian350028 China School of Mathematical Sciences Tiangong University Tianjin300387 China The Key Laboratory of Intelligent Information and Data Processing of NingXia Province North Minzu University and Health Big Data Research Institute of North Minzu University Yinchuan750021 China Machine vision and pattern recognition lab University of Regina ReginaSKS4S0A2 Canada

In this paper, the combination of the variable precision rough set and the limited tolerance relation under multi-granularity is explored. As an extension of rough set model, Multi-granularity variable precision limited tolerance rough set model is con-structed. Properties of upper and lower approximation operator and detailed structure of object class through threshold are discussed. Theoretical proofs are given to show the rationality and superiority of the proposed model. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Granulation

NTIRE 2023 Image Shadow Removal Challenge Report

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

2023 IEEE/CVF Conference on Computer vision and pattern recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

Regional attention with architecture-rebuilt 3D network for RGB-D gesture recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Benjia Li, Yunan Wan, Jun Macau University of Science and Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Computer Science and Technology Xidian Univeristy China Xi'an Key Laboratory of Big Data and Intelligent Vision China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Human gesture recognition has drawn much attention in the area of computer vision. However, the performance of gesture recognition is always influenced by some gesture-irrelevant factors like the background and the clothes of performers. Therefore, focusing on the regions of hand/arm is important to the gesture recognition. Meanwhile, a more adaptive architecture-searched network structure can also perform better than the block-fixed ones like ResNet since it increases the diversity of features in different stages of the network better. In this paper, we propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition. We replace the fixed Inception modules with the automatically rebuilt structure through the network via Neural Architecture Search (NAS), owing to the different shape and representation ability of features in the early, middle, and late stage of the network. It enables the network to capture different levels of feature representations at different layers more adaptively. Meanwhile, we also design a stackable regional attention module called Dynamic-Static Attention (DSA), which derives a Gaussian guidance heatmap and dynamic motion map to highlight the hand/arm regions and the motion information in the spatial and temporal domains, respectively. Extensive experiments on two recent large-scale RGB-D gesture datasets validate the effectiveness of the proposed method and show it outperforms state-of-the-art methods. The codes of our method are available at: https://***/zhoubenjia/RAAR3DNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

Differentiable neural architecture learning for efficient neural network design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks