检索结果-内蒙古大学图书馆

Overview of the Tenth Dialog System Technology Challenge: DSTC10

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

Progressive Dual Priori Network for Generalized Breast Tumor Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Li Wang, Lihui Kuai, Zixiang Tang, Lei Ou, Yingfeng Ye, Chen Zhu, Yuemin Wu, Min Shi, Tianliang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Imaging Center Harbin Medical University Cancer Hospital Harbin150081 China Radiology Department Guizhou Provincial People’s Hospital Guiyang550002 China Radiology Department Tongren People’s Hospital Tongren554300 China Univ Lyon INSA Lyon CNRS Inserm CREATIS UMR 5220 U1206 LyonF-69621 France

To promote the generalization ability of breast tumor segmentation models, as well as to improve the segmentation performance for breast tumors with smaller size, low-contrast and irregular shape, we propose a progressive dual priori network (PDPNet) to segment breast tumors from dynamic enhanced magnetic resonance images (DCE-MRI) acquired at different centers. The PDPNet first cropped tumor regions with a coarse-segmentation based localization module, then the breast tumor mask was progressively refined by using the weak semantic priori and cross-scale correlation prior knowledge. To validate the effectiveness of PDPNet, we compared it with several state-of-the-art methods on multi-center datasets. The results showed that, comparing against the suboptimal method, the DSC and HD95 of PDPNet were improved at least by 5.13% and 7.58% respectively on multi-center test sets. In addition, through ablations, we demonstrated that the proposed localization module can decrease the influence of normal tissues and therefore improve the generalization ability of the model. The weak semantic priors allow focusing on tumor regions to avoid missing small tumors and low-contrast tumors. The cross-scale correlation priors are beneficial for promoting the shape-aware ability for irregular tumors. Thus integrating them in a unified framework improved the multicenter breast tumor segmentation performance. The source code and open data can be accessed at https://github. com/wangli100209/PDPNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dong, Chengbo Chen, Xinru Hu, Ruohan Cao, Juan Li, Xirong The Key Lab of Data Engineering and Kowledge Engineering Renmin University of China Beijing100872 China The AIMC Lab. School of Information Renmin University of China Beijing100872 China Institute of Computing Technology Chinese Academy of Sciences The the Key Laboratory of Media Convergence Production Technology and Systems Beijing100864 China

As manipulating images by copy-move, splicing and/or inpainting may lead to misinterpretation of the visual content, detecting these sorts of manipulations is crucial for media forensics. Given the variety of possible attacks on the content, devising a generic method is nontrivial. Current deep learning based methods are promising when training and test data are well aligned, but perform poorly on independent tests. Moreover, due to the absence of authentic test images, their image-level detection specificity is in doubt. The key question is how to design and train a deep neural network capable of learning generalizable features sensitive to manipulations in novel data, whilst specific to prevent false alarms on the authentic. We propose multi-view feature learning to jointly exploit tampering boundary artifacts and the noise view of the input image. As both clues are meant to be semantic-agnostic, the learned features are thus generalizable. For effectively learning from authentic images, we train with multi-scale (pixel/edge/image) supervision. We term the new network MVSS-Net and its enhanced version MVSS-Net++. Experiments are conducted in both within-dataset and cross-dataset scenarios, showing that MVSS-Net++ performs the best, and exhibits better robustness against JPEG compression, Gaussian blur and screenshot based image re-capturing. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Unsupervised hashing with contrastive information bottleneck

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qiu, Zexuan Su, Qinliang Ou, Zijing Yu, Jianxing Chen, Changyou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China CSE Department SUNY at Buffalo Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines. © 2021, CC BY.

关键词： Semantics

Two-Stage Attention-Based Model for Code Search with Textual and Structural Features

学校读者我要写书评

暂无评论

Two-Stage Attention-Based Model for Code Search with Textual...

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Ling Xu Huanhuan Yang Chao Liu Jianhang Shuai Meng Yan Yan Lei Zhou Xu Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science and Technology Zhejiang University Hangzhou China

Searching and reusing existing code from a large scale codebase can largely improve developers' programming efficiency. To support code reuse, early code search models leverage information retrieval (IR) techniques to index a large-scale code corpus and return relevant code according to developers' search query. However, IR-based models fail to capture the semantics in code and query. To tackle this issue, developers applied deep learning (DL) techniques to code search models. However, these models either are too complex to determine an effective method efficiently or learning for semantic correlation between code and query *** bridge the semantic gap between code and query effectively and efficiently, we propose a code search model TabCS (Two-stage Attention-Based model for Code Search) in this study. TabCS extracts code and query information from the code textual features (i.e., method name, API sequence, and tokens), the code structural feature (i.e., abstract syntax tree), and the query feature (i.e., tokens). TabCS performs a two-stage attention net-work structure. The first stage leverages attention mechanisms to extract semantics from code and query considering their semantic gap. The second stage leverages a co-attention mechanism to capture their semantic correlation and learn better code/query representation. We evaluate the performance of TabCS on two existing large-scale datasets with 485k and 542k code snippets, respectively. Experimental results show that TabCS achieves an MRR of 0.57 on Hu et al.'s dataset, outperforming three state-of-the-art models CARLCS-CNN, DeepCS, and UNIF by 18%, 70%, 12%, respectively. Meanwhile, TabCS gains an MRR of 0.54 on Husain et al.'s, outperforming CARLCS-CNN, DeepCS, and UNIF by 32%, 76%, 29%, respectively.

关键词： Deep learning Correlation Semantics Syntactics Programming Feature extraction Information retrieval

An Asymmetric Modeling for Action Assessment 1

学校读者我要写书评

暂无评论

16th European Conference on Computer Vision, ECCV 2020

作者： Gao, Jibin Zheng, Wei-Shi Pan, Jia-Hui Gao, Chengying Wang, Yaowei Zeng, Wei Lai, Jianhuang School of Data and Computer Science Sun Yat-sen University Guangzhou China Peng Cheng Laboratory Shenzhen518005 China School of Electronics Engineering and Computer Science Peking University Beijing China Pazhou Lab Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (数字)9783030585778

ISBN: (纸本)9783030585761

Action assessment is a task of assessing the performance of an action. It is widely applicable to many real-world scenarios such as medical treatment and sporting events. However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e.g., between persons and objects);and this limitation undermines their ability to assess actions containingasymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions. In this work, we model the asymmetric interactions among agents for action assessment. In particular, we propose an asymmetric interaction module (AIM), to explicitly model asymmetric interactions between intelligent agents within an action, where we group these agents into a primary one (e.g., human) and secondary ones (e.g., objects). We perform experiments on JIGSAWS dataset containing surgical actions, and additionally collect a new dataset, TASD-2, for interactive sporting actions. The experimental results on two interactive action datasets show the effectiveness of our model, and our method achieves state-of-the-art performance. The extended experiment on AQA-7 dataset also demonstrates the generalization capability of our framework to conventional action assessment. © 2020, Springer Nature Switzerland AG.

关键词： Intelligent agents

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yuhao Chang, Ao Dou, Haoran Tao, Xing Zhou, Xinrui Cao, Yan Huang, Ruobing Frangi, Alejandro F. Bao, Lingyun Yang, Xin Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Lab Shenzhen University Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen China School of Computing University of Leeds Leeds United Kingdom Shenzhen RayShape Medical Technology Co. Ltd Shenzhen China Division of Informatics Imaging and Data Science School of Health Sciences University of Manchester Manchester United Kingdom Department of Computer Science School of Engineering University of Manchester Manchester United Kingdom Department of Electrical Engineering Department of Cardiovascular Sciences KU Leuven Belgium Alan Turing Institute London United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom Department of Ultrasound Affiliated Hangzhou First People’s Hospital School of Medicine Westlake University China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: 1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. 2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents’ erasing process precisely, thereby avoiding both under- and over-segmentation. 3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

USEV: Universal Speaker Extraction with visual Cue

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pan, Zexu Ge, Meng Li, Haizhou The Integrative Sciences and Engineering Programme The Institute of Data Science The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin300072 China The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The University of Bremen 28359 Germany Kriston AI Xiamen China

A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the target-interference speaker overlapping ratios could vary over a wide range from 0% to 100% in natural speech communication, furthermore, the target speaker could be absent in the speech mixture, the speech mixtures in such universal multi-talker scenarios are described as general speech mixtures. The speaker extraction algorithm requires an auxiliary reference, such as a video recording or a pre-recorded speech, to form top-down auditory attention on the target speaker. We advocate that a visual cue, i.e., lip movement, is more informative than an audio cue, i.e., pre-recorded speech, to serve as the auxiliary reference for speaker extraction in disentangling the target speaker from a general speech mixture. In this paper, we propose a universal speaker extraction network with a visual cue, that works for all multi-talker scenarios. In addition, we propose a scenario-aware differentiated loss function for network training, to balance the network performance over different target-interference speaker pairing scenarios. The experimental results show that our proposed method outperforms various competitive baselines for general speech mixtures in terms of signal fidelity. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

OPR-Miner: Order-preserving rule mining for time series

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Youxi Zhao, Xiaoqian Li, Yan Guo, Lei Zhu, Xingquan Fournier-Viger, Philippe Wu, Xindong School of Artificial Intelligence Hebei University of Technology Tianjin300401 China Hebei Key Laboratory of Big Data Computing Tianjin300401 China School of Economics and Management Hebei University of Technology Tianjin300401 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin300401 China The Department of Computer & Electrical Engineering and Computer Science Florida Atlantic University FL33431 United States Shenzhen University Shenzhen China Hefei University of Technology Hefei230009 China

Discovering frequent trends in time series is a critical task in data mining. Recently, order-preserving matching was proposed to find all occurrences of a pattern in a time series, where the pattern is a relative order (regarded as a trend) and an occurrence is a sub-time series whose relative order coincides with the pattern. Inspired by the order-preserving matching, the existing order-preserving pattern (OPP) mining algorithm employs order-preserving matching to calculate the support, which leads to low efficiency. To address this deficiency, this paper proposes an algorithm called efficient frequent OPP miner (EFO-Miner) to find all frequent OPPs. EFO-Miner is composed of four parts: a pattern fusion strategy to generate candidate patterns, a matching process for the results of sub-patterns to calculate the support of super-patterns, a screening strategy to dynamically reduce the size of prefix and suffix arrays, and a pruning strategy to further dynamically prune candidate patterns. Moreover, this paper explores the order-preserving rule (OPR) mining and proposes an algorithm called OPR-Miner to discover strong rules from all frequent OPPs using EFO-Miner. Experimental results verify that OPR-Miner gives better performance than other competitive algorithms. More importantly, clustering and classification experiments further validate that OPR-Miner achieves good performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Time series