检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Dong, Lu Zhang, Haiyu Zhang, Hongjie Huang, Yifei Ling, Zhen-Hua Qiao, Yu Wang, Limin Wang, Yali University of Science and Technology of China Hefei230027 China Shanghai Artificial Intelligence Laboratory Shanghai202150 China Beihang University Beijing100191 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence. For an anchor sample, most existing approaches generate negative samples either from other videos or within the same video for contrastive learning. However, some training samples are highly similar to the anchor sample, directly regarding them as negative samples leads to difficulties for optimization and ignores the correlations between these similar samples and the anchor sample. To address this, we propose Positive Sample Mining (PSM), a novel framework that mines positive samples from the training set to provide more discriminative supervision. Specifically, for a given anchor sample, we partition the remaining training set into semantically similar and dissimilar subsets based on the similarity of their text queries. To effectively leverage these correlations, we introduce a PSM-guided contrastive loss to ensure that the anchor proposal is closer to similar samples and further from dissimilar ones. Additionally, we design a PSM-guided rank loss to ensure that similar samples are closer to the anchor proposal than to the negative intra-video proposal, aiming to distinguish the anchor proposal and the negative intra-video proposal. Experiments on the WSTSG and grounded VideoQA tasks demonstrate the effectiveness and superiority of our method. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-lingual Handwriting Recovery Framework based on Convolutional Denoising Autoencoder with Attention model

TechRxiv

引用

TechRxiv 2022年

作者： Rabhi, Besma Elbaati, Abdelkarim Boubaker, Houcine Pal, Umapada Alimi, Adel M. University of Sfax National Engineering School of Sfax REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Sfax3038 Tunisia University of Monastir Higher Institute of Applied Sciences and Technology of Mahdia REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Mahdia5121 Tunisia Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa

For several decades, the offline handwriting recognition problem has escaped a satisfactory solution. In the field of online recognition, researchers have had more successful performance, but the ability to extract dynamic information from static images has not been well explored yet. In this paper, we introduce a novel multi-lingual word handwriting recovery framework based on a convolutional denoising autoencoder with an attention model for pen up / down, velocity and temporal order recovery. The proposed framework consists of extracting robust features from a handwriting image using a stacked denoising autoencoder and an encoder Bidirectional Gated Recurrent Unit (BGRU) model. Then, the obtained vectors are decoded to produce an online script with dynamic characteristics using a BGRU with temporal attention. Evaluation is done on a Latin and Arabic Online and offline handwriting character / word databases and the proposed framework achieves high competitive results. To the best of our knowledge, this is the first work of its kind. © 2022, CC BY.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Shijie Yu Shihua Li Dapeng Chen Rui Zhao Junjie Yan Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Institute of Microelectronics of the Chinese Academy of Sciences

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named Clothes Changing Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates.

关键词： Face Feature extraction Benchmark testing Protocols Biological system modeling Shape

来源：评论

学校读者我要写书评

暂无评论

A simple real-word error detection and correction using local word bigram and trigram 25

A simple real-word error detection and correction using loca...

引用

25th Conference on Computational Linguistics and Speech Processing, ROCLING 2013

作者： Samanta, Pratip Chaudhuri, Bidyut B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9789573079262

Spelling error is broadly classified in two categories namely non word error and real word error. In this paper a localized real word error detection and correction method is proposed where the scores of bigrams generated by immediate left and right neighbour of the candidate word and the trigram of these three words are combined. A single character position error model is assumed so that if a word W is erroneous then the correct word belongs to the set of real words S generated by single character edit operation on W. The above combined score is calculated also on all members of S. These words are ranked in the decreasing order of the score. By observing the rank and using a rule based approach, the error decision and correction candidates are simultaneously selected. The approach gives comparable accuracy with other existing approaches but is computationally attractive. Since only left and right neighbor are involved, multiple errors in a sentence can also be detected (if the error occurs in every alternate words). © ROCLING *** rights reserved.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

COCAS: A large-scale clothes changing person dataset for re-identification

arXiv

引用

arXiv 2020年

作者： Yu, Shijie Li, Shihua Chen, Dapeng Zhao, Rui Yan, Junjie Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Institute of Microelectronics of the Chinese Academy of Sciences

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Attention-driven dynamic graph convolutional network for multi-label image recognition

arXiv

引用

arXiv 2020年

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-label benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. All codes can be found at https://***/Yejin0111/ADD-GCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A new convolutional neural network based on a saprse convolutional layer for animal face detection

TechRxiv

引用

TechRxiv 2021年

作者： Jarraya, Islem BenSaid, Fatma Ouarda, Wael Pal, Umapada Alimi, Adel M. BP 1173 Sfax3038 Tunisia Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T. Road Kolkata700 108 India Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg South Africa

This paper focuses on the face detection problem of three popular animal categories that need control such as horses, cats and dogs. To be precise, a new Convolutional Neural Network for Animal Face Detection (CNNAFD) is actually investigated using processed filters based on gradient features and applied with a new way. A new convolutional layer is proposed through a sparse feature selection method known as Automated Negotiation-based Online Feature Selection (ANOFS). CNNAFD ends by stacked fully connected layers which represent a strong classifier. The fusion of CNNAFD and MobileNetV2 constructs the new network CNNAFD-MobileNetV2 which improves the classification results and gives better detection decisions. Our work also introduces a new Tunisian Horse Detection Database (THDD). The proposed detector with the new CNNAFDMobileNetV2 network achieved an average precision equal to 99.78%, 99% and 98.28% for cats, dogs and horses respectively. © 2021, CC BY.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

Detach and Enhance: Learning Disentangled Cross-modal Latent...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhenning Yu Xin Liu Yiu-Ming Cheung Minghang Zhu Xing Xu Nannan Wang Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Dept. of Comput. Sci. and Institute of Research and Continuing Education HK Baptist University Hong Kong SAR China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China State Key Lab. of Integrated Services Networks & School of Telecommun. Eng. Xidian University Xi’an China

Many researches in cognitive science have shown that humans often perform face-voice association for various perception tasks, and some recent data mining works have been designed in emulating such ability intelligently. Nevertheless, most methods often suffer from the degraded performance when there exist semantically irrelevant interference factors across different modalities. To alleviate this concern, this paper presents an efficient Disentangled Cross-modal Latent Representation (DCLR) method to adaptively detach the discriminative feature attributes and enhance the face-voice association. To be specific, the proposed DCLR framework consists of two-stage cross-modal disentangling process. First, the former stage employs the supervised contrastive learning to push the representations of face-voice data from the same person closer while pulling those representations of different person away. Then, the latter stage freezes all the parameters of the former stage, and further innovates a multi-layer orthogonal decoupling scheme to learn the disentangled latent representations, while filtering out the modality-dependent irrelevant factors. Besides, the cross-modal reconstruction loss is further utilized to narrow down the semantic gap between heterogeneous feature expressions. Through the joint exploitation of the above, the proposed framework can well associate the face-voice data to benefit various kinds of cross-modal perception tasks. Extensive experiments verify the superiorities of the proposed face-voice association framework and show its competitive performances.

关键词： Representation learning Filtering Semantics Interference Data models Cognitive science Data mining

来源：评论

学校读者我要写书评

暂无评论

Context-transformer: Tackling object confusion for few-shot detection

arXiv

引用

arXiv 2020年

作者： Yang, Ze Wang, Yali Chen, Xianyu Liu, Jianzhuang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Huawei Noah’s Ark Lab. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches. The codes are available at https://***/Ze-Yang/ContextTransformer. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

TSNet: Deep Network for Human Action recognition in Hazy Videos

TSNet: Deep Network for Human Action Recognition in Hazy Vid...

引用

2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

作者： Chaudhary, Sachin Murala, Subrahmanyam Computer Vision and Pattern Recognition Lab Depatment of Electrical Engineering Indian Institute of Technology Ropar India

ISBN: (纸本)9781538666500

The all-weather intelligent surveillance system is the prime challenge for computer vision researchers. The surveillance is mostly done to analyze the human activity in a particular region. Several extreme weather conditions like rain, snow, haze, fog etc. halts the surveillance process and thus decreases the reliability of the surveillance system. Here, an attempt is made to tackle one of these weather situation i.e. haze in case of surveillance. Haze distorts the quality of images and videos captured by camera. Due to poor quality, it is difficult to analyze the haze degraded video for the human activities using the existing state-of-the-art methods for human action recognition (HAR). Therefore, in this paper, a new two level saliency based end-to-end network (TSNet) for HAR in hazy videos is proposed. De-hazing approaches given in [1]-[9] have certain limitations and therefore we fine-tuned the de-hazing network given in [10] for HAR. The concept of rank pooling given in [11] is further utilized to efficiently represent the temporal saliency of the video. The transmission map information is utilized here to fix the spatial saliency in each frame. As currently, there is no dataset available for HAR in hazy video, here a new dataset of hazy video is generated from two benchmark datasets namely HMDB51 [12] and UCF101 [13] by adding synthetic haze. The existing methods for HAR proposed in [11], [14], [15] are applied and compared with the proposed method on proposed hazy-HMDB51 and hazy-UCF101. The proposed method clearly outperforms the above mentioned methods in terms of average recognition rate (ARR). © 2018 IEEE.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：