检索结果-内蒙古大学图书馆

Query-oriented data Augmentation for Session Search

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Haonan Dou, Zhicheng Zhu, Yutao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Engineering Research Center of Next-Generation Intelligent Search and Recommendation Ministry of Education Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing100872 China

Modeling contextual information in a search session has drawn more and more attention when understanding complex user intents. Recent methods are all data-driven, i.e., they train different models on large-scale search log data to identify the relevance between search contexts and candidate documents. The common training paradigm is to pair the search context with different candidate documents and train the model to rank the clicked documents higher than the unclicked ones. However, this paradigm neglects the symmetric nature of the relevance between the session context and document, i.e., the clicked documents can also be paired with different search contexts when training. In this work, we propose query-oriented data augmentation to enrich search logs and empower the modeling. We generate supplemental training pairs by altering the most important part of a search context, i.e., the current query, and train our model to rank the generated sequence along with the original sequence. This approach enables models to learn that the relevance of a document may vary as the session context changes, leading to a better understanding of users’ search patterns. We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty. Through experimentation on two extensive public search logs, we have successfully demonstrated the effectiveness of our model. © 2024, CC BY.

关键词： Search engines

Denoi-SpEx+: A Speaker Extraction Network based Speech Dialogue System 17

学校读者我要写书评

暂无评论

Denoi-SpEx+: A Speaker Extraction Network based Speech Dialo...

17th IEEE International Conference on e-Business Engineering, ICEBE 2021

作者： Hao, Yun Huang, Xiangkang Huang, Huichou Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Lab Guangzhou China University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9781665444187

The speech dialogue system has gradually been widely used in daily life. Users can consult and communicate with the system through natural language. However, in practical applications, third-person background sounds and background noise interference in real dialogue scenes will be encountered. The uncertainty and complexity of these background sounds will have a bad impact on the recognition of the system. A good speech enhancement module can help us to separate the target speaker from the original speech. Recently, a solution called SpEx+ was proposed from the time domain, but SpEx+ needs a reference speech to assist in training. This reference speech may have noise in actual applications that will affect performance. Therefore, we propose a Denoi-SpEx+ model. Before the reference speech is input to the network, a speech denoising network is added, so that the quality of speech separation in practical applications can be guaranteed. Experiments show that our model can significantly improve the performance of speech separation model of noisy reference speech. © 2021 IEEE.

关键词： Speech enhancement

PP-LDG: A Medical Privacy-Preserving Labeled data Generation Framework

学校读者我要写书评

暂无评论

PP-LDG: A Medical Privacy-Preserving Labeled Data Generation...

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Haoxiang Yuan Xiaochen Yuan Xiuli Bi Weisheng Li Guoyin Wang Bin Xiao Chongqing Key Laboratory of Image Cognition School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Faculty of Applied Sciences Macao Polytechnic University Macao China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China

ISBN: (数字)9798350377613

ISBN: (纸本)9798350377620

The rapid development of deep learning has led to an increasing demand for data. However, such data are scarce in many fields and often contain private and sensitive information, such as medical images. The fact that data owners are unwilling to share these high-privacy data further exacerbates the scarcity of data. A prevalent research direction is to combine differential privacy and image generation, by which we can obtain a large amount of synthetic data with a similar distribution to the original dataset, and that synthetic dataset does not compromise the privacy of the original dataset. However, these methods cannot provide labels for the generated data, limiting the subsequent uses of the data. To solve the problem, we propose a generic privacy-preserving labeled data generation framework named PP-LDG. It is the first data publishing framework to generate labeled data while not disclosing the privacy of original data. We theoretically demonstrate that our proposed framework can provide strict privacy guarantees with differential privacy and demonstrate the effectiveness of the synthetic dataset obtained from the framework under practical privacy budgets through extensive experiments.

关键词： Deep learning Differential privacy Accuracy Limiting Image synthesis Publishing data collection Synthetic data Biomedical imaging Image classification

GLCONet: Learning Multi-source Perception Representation for Camouflaged Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Yanguang Xuan, Hanyu Yang, Jian Luo, Lei The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China The School of Big Data and Statistics Anhui University Hefei230601 China

Recently, biological perception has been a powerful tool for handling the camouflaged object detection (COD) task. However, most existing methods are heavily dependent on the local spatial information of diverse scales from convolutional operations to optimize initial features. A commonly neglected point in these methods is the long-range dependencies between feature pixels from different scale spaces that can help the model build a global structure of the object, inducing a more precise image representation. In this paper, we propose a novel Global-Local Collaborative Optimization Network, called GLCONet. Technically, we first design a collaborative optimization strategy from the perspective of multi-source perception to simultaneously model the local details and global long-range relationships, which can provide features with abundant discriminative information to boost the accuracy in detecting camouflaged objects. Furthermore, we introduce an adjacent reverse decoder that contains cross-layer aggregation and reverse optimization to integrate complementary information from different levels for generating high-quality representations. Extensive experiments demonstrate that the proposed GLCONet method with different backbones can effectively activate potentially significant pixels in an image, outperforming twenty state-of-the-art methods on three public COD datasets. The source code is available at: https://***/CSYSI/GLCONet. © 2024, CC BY.

关键词： Object detection

An Offensive Language Identification Based on Deep Semantic Feature Fusion 8

学校读者我要写书评

暂无评论

An Offensive Language Identification Based on Deep Semantic ...

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Li, Xiang Zeng, Zhi Wu, Mingmin Huang, Zhongqiang Sha, Ying Shi, Lei College of Informatics Huazhong Agricultural University Wuhan China Key Laboratory of Smart Farming for Agricultural Animals Wuhan China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education China

ISBN: (纸本)9781665450515

Various forms of social interactions are often char-acterized by toxic or offensive words that can be collectively referred to as offensive languages, which has become a unique linguistic phenomenon in social media platforms. How to detect and identify these offensive languages in social media platforms has become one of the important research in the field of natural language processing. Existing methods utilize machine learning algorithms or text representation models based on deep learning to learn the features of offensive languages and identify them, which have achieved good performances. However, traditional machine learning-based methods mainly rely on keyword identi-fication and blocking, deep learning-based methods do not ade-quately explore the fused deep semantic features of the content by combining word-level embeddings and sentence-level deep semantic feature representations of sentences, which cannot ef-fectively identify offensive languages that do not contain common offensive words but indicate offensive meanings. In this research, we propose a novel offensive language identification model based on deep semantic feature fusion, which uses the pre-trained model Bert to obtain word-level embedding representations of offensive languages, and then integrates the RCNN that combines with the attention mechanism to extract the fused deep semantic feature representations of offensive languages, and label encoder and offensive predictor to improve the identification accuracy and generalization ability of the model so that the performances of the model do not rely on the offensive language lexicon entirely and can identify offensive languages that do not contain common offensive words but indicate offensive meanings. Experimental results on Wikipedia and Twitter comment datasets show that our proposed model can better understand the context and discover potential offensive meanings, and outperforms existing methods. © 2022 IEEE.

关键词： Embeddings

FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Xinyu Chen, Peihao Fan, Jugang Li, Thomas H. Chen, Jian Tan, Mingkui South China University of Technology China Pazhou Laboratory China Information Technology R&D Innovation Center of Peking University China Peking University Shenzhen Graduate School China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Hong Kong

Learning to navigate to an image-specified goal is an important but challenging task for autonomous systems. The agent is required to reason the goal location from where a picture is shot. Existing methods try to solve this problem by learning a navigation policy, which captures semantic features of the goal image and observation image independently and lastly fuses them for predicting a sequence of navigation actions. However, these methods suffer from two major limitations. 1) They may miss detailed information in the goal image, and thus fail to reason the goal location. 2) More critically, it is hard to focus on the goal-relevant regions in the observation image, because they attempt to understand observation without goal conditioning. In this paper, we aim to overcome these limitations by designing a Fine-grained Goal Prompting (FGPrompt) method for image-goal navigation. In particular, we leverage fine-grained and high-resolution feature maps in the goal image as prompts to perform conditioned embedding, which preserves detailed information in the goal image and guides the observation encoder to pay attention to goal-relevant regions. Compared with existing methods on the image-goal navigation benchmark, our method brings significant performance improvement on 3 benchmark datasets (i.e., Gibson, MP3D, and HM3D). Especially on Gibson, we surpass the state-of-the-art success rate by 8% with only 1/50 model size. Copyright © 2023, The Authors. All rights reserved.

关键词： Navigation

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension 39

学校读者我要写书评

暂无评论

Hierarchical Alignment-enhanced Adaptive Grounding Network f...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yaxian Ding, Henghui He, Shuting Jiang, Xudong Wei, Bifan Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University China Institute of Big Data Fudan University China Shanghai University of Finance and Economics China Nanyang Technological University Singapore School of Continuing Education Xi'an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China

ISBN: (纸本)157735897X

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Modal analysis

Enhanced Contrastive Learning with Multi-view Longitudinal data for Chest X-ray Report Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Kang Ma, Zhuoqi Kang, Xiaolu Li, Yunan Xie, Kun Jiao, Zhicheng Miao, Qiguang School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China Warren Alpert Medical School Brown University Providence United States

Automated radiology report generation offers an effective solution to alleviate radiologists’ workload. However, most existing methods focus primarily on single or fixed-view images to model current disease conditions, which limits diagnostic accuracy and overlooks disease progression. Although some approaches utilize longitudinal data to track disease progression, they still rely on single images to analyze current visits. To address these issues, we propose enhanced contrastive learning with Multi-view Longitudinal data to facilitate chest X-ray Report Generation, named MLRG. Specifically, we introduce a multi-view longitudinal contrastive learning method that integrates spatial information from current multi-view images and temporal information from longitudinal data. This method also utilizes the inherent spatiotemporal information of radiology reports to supervise the pre-training of visual and textual representations. Subsequently, we present a tokenized absence encoding technique to flexibly handle missing patient-specific prior knowledge, allowing the model to produce more accurate radiology reports based on available prior knowledge. Extensive experiments on MIMIC-CXR, MIMIC-ABN, and Two-view CXR datasets demonstrate that our MLRG outperforms recent state-of-the-art methods, achieving a 2.3% BLEU-4 improvement on MIMIC-CXR, a 5.5% F1 score improvement on MIMIC-ABN, and a 2.7% F1 RadGraph improvement on Two-view CXR. Copyright © 2025, The Authors. All rights reserved.

关键词： Radiology