检索结果-内蒙古大学图书馆

New Moments Based Fuzzy Similarity Measure for Text Detection in Distorted Social Media Images 5th

学校读者我要写书评

暂无评论

New Moments Based Fuzzy Similarity Measure for Text Detectio...

5th Asian Conference on pattern recognition, ACPR 2019

作者： Roy, Soumyadip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Blumenstein, Michael Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia National Key Lab for Novel Software Technology Nanjing University Nanjing China Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9783030414030

A trend towards capturing or filming images using cellphone and sharing images on social media is a part and parcel of day to day activities of humans. When an image is forwarded several times in social media it may be distorted a lot due to several different devices. This work deals with text detection from such distorted images. In this work, we consider images pass through three mobile devices on WhatsApp social media, which results in four images (including the original image) Unlike the existing methods that aim at developing new ways, we utilize the results detected by the existing ones to improve performances. The proposed method extracts Hu moments and fuzzy logic from detected texts of images. The similarity between text detection results given by three existing text detection methods is studied for determining the best pair of texts. The same similarity estimation is then used in a novel way to remove extra background or non-texts and restoring missing text information. Experimental results on own dataset and benchmark datasets of natural scene images, namely, MSRA-TD500, ICDAR2017-MLT, Total-Text, CTW1500 dataset and COCO datasets, show that the proposed method outperforms the existing methods. © Springer Nature Switzerland AG 2020.

关键词： Fuzzy logic

A Dual-Space Framework for General Knowledge Distillation of Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Xue Zhang, Songming Liang, Yunlong Meng, Fandong Chen, Yufeng Xu, Jinan Zhou, Jie School of Computer Science and Technology Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing Jiaotong University Beijing100044 China Pattern Recognition Center WeChat AI Tencent Inc China

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output distributions of the teacher model and the student model to transfer more information. However, we reveal that the current white-box KD framework exhibits two limitations: a) bridging probability distributions from different output spaces will limit the similarity between the teacher model and the student model;b) this framework cannot be applied to LLMs with different vocabularies. One of the root causes for these limitations is that the distributions from the teacher and the student for KD are output by different prediction heads, which yield distributions in different output spaces and dimensions. Therefore, in this paper, we propose a dual-space knowledge distillation (DSKD) framework that unifies the prediction heads of the teacher and the student models for KD. Specifically, we first introduce two projectors with ideal initialization to project the teacher/student hidden states into the student/teacher representation spaces. After this, the hidden states from different models can share the same head and unify the output spaces of the distributions. Furthermore, we develop an exact token alignment (ETA) algorithm to align the same tokens in two differently-tokenized sequences. Based on the above, our DSKD framework is a general KD framework that supports both off-policy and on-policy KD, and KD between any two LLMs regardless of their vocabularies. Extensive experiments on instruction-following, mathematical reasoning, and code generation benchmarks show that DSKD significantly outperforms existing methods based on the current white-box KD framework and surpasses other cross-tokenizer KD methods for LLMs with different vocabularies. © 2025, CC BY-NC-ND.

关键词： Distribution functions

PC-HMR: Pose calibration for 3d human mesh recovery from 2D images/videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luan, Tianyu Wang, Yali Zhang, Junhao Wang, Zhe Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China University of California Irvine United States

The end-to-end Human Mesh Recovery (HMR) approach (Kanazawa et al. 2018) has been successfully used for 3D body reconstruction. However, most HMR-based frameworks reconstruct human body by directly learning mesh parameters from images or videos, while lacking explicit guidance of 3D human pose in visual data. As a result, the generated mesh often exhibits incorrect pose for complex activities. To tackle this problem, we propose to exploit 3D pose to calibrate human mesh. Specifically, we develop two novel Pose Calibration frameworks, i.e., Serial PC-HMR and Parallel PC-HMR. By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module. Furthermore, since the calibration module is designed via non-rigid pose transformation, our PCHMR frameworks can flexibly tackle bone length variations to alleviate misplacement in the calibrated mesh. Finally, our frameworks are based on generic and complementary integration of data-driven learning and geometrical modeling. Via plug-and-play modules, they can be efficiently adapted for both image/video-based human mesh recovery. Additionally, they have no requirement of extra 3D pose annotations in the testing phase, which releases inference difficulties in practice. We perform extensive experiments on the popular benchmarks, i.e., Human3.6M, 3DPW and SURREAL, where our PC-HMR frameworks achieve the SOTA results. Copyright © 2021, The Authors. All rights reserved.

关键词： Mesh generation

RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax 1

学校读者我要写书评

暂无评论

16th European Conference on computer vision, ECCV 2020

作者： Zhang, Xiao Zhao, Rui Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong SenseTime Research Hong Kong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Deep neural networks have achieved remarkable successes in learning feature representations for visual classification. However, deep features learned by the softmax cross-entropy loss generally show excessive intra-class variations. We argue that, because the traditional softmax losses aim to optimize only the relative differences between intra-class and inter-class distances (logits), it cannot obtain representative class prototypes (class weights/centers) to regularize intra-class distances, even when the training is converged. Previous efforts mitigate this problem by introducing auxiliary regularization losses. But these modified losses mainly focus on optimizing intra-class compactness, while ignoring keeping reasonable relations between different class prototypes. These lead to weak models and eventually limit their performance. To address this problem, this paper introduces a novel Radial Basis Function (RBF) distances to replace the commonly used inner products in the softmax loss function, such that it can adaptively assign losses to regularize the intra-class and inter-class distances by reshaping the relative differences, and thus creating more representative prototypes of classes to improve optimization. The proposed RBF-Softmax loss function not only effectively reduces intra-class distances, stabilizes the training behavior, and reserves ideal relations between prototypes, but also significantly improves the testing performance. Experiments on visual recognition benchmarks including MNIST, CIFAR-10/100, and ImageNet demonstrate that the proposed RBF-Softmax achieves better results than cross-entropy and other state-of-the-art classification losses. The code is at https://***/2han9x1a0release/RBF-Softmax. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction

学校读者我要写书评

暂无评论

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreferen...

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wang, Xiaozhi Chen, Yulin Ding, Ning Peng, Hao Wang, Zimu Lin, Yankai Han, Xu Hou, Lei Li, Juanzi Liu, Zhiyuan Li, Peng Zhou, Jie Department of Computer Science and Technology BNRist Tsinghua University Beijing China Shenzhen International Graduate School Tsinghua University Beijing China THU-Siemens Ltd. China Joint Research Center for Industrial Intelligence and IoT Tsinghua University Beijing China Tsinghua University Beijing China Xi'an Jiaotong-Liverpool University Suzhou China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Pattern Recognition Center WeChat AI Tencent Inc China

The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation extraction (ERE) tasks: (1) Small scale. Due to the annotation complexity, the data scale of existing datasets is limited, which cannot well train and evaluate data-hungry models. (2) Absence of unified annotation. Different types of event relations naturally interact with each other, but existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions. To address these issues, we construct a unified large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103, 193 event coreference chains, 1, 216, 217 temporal relations, 57, 992 causal relations, and 15, 841 subevent relations, which is larger than existing datasets of all the ERE tasks by at least an order of magnitude. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances. The dataset and source codes can be obtained from https://***/THU-KEG/MAVEN-ERE. © 2022 Association for Computational Linguistics.

关键词： Extraction

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

Chebyshev-Harmonic-Fourier-Moments and Deep CNNs for Detecting Forged Handwriting

学校读者我要写书评

暂无评论

Chebyshev-Harmonic-Fourier-Moments and Deep CNNs for Detecti...

International Conference on pattern recognition

作者： Lokesh Nandanwar Palaiahnakote Shivakumara Sayani Kundu Umapada Pal Tong Lu Daniel Lopresti Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Science & Engineering Lehigh University Bethlehem PA USA

Recently developed sophisticated image processing techniques and tools have made easier the creation of high-quality forgeries of handwritten documents including financial and property records. To detect such forgeries of handwritten documents, this paper presents a new method by exploring the combination of Chebyshev-Harmonic-Fourier-Moments (CHFM) and deep Convolutional Neural Networks (D-CNNs). Unlike existing methods work based on abrupt changes due to distortion created by forgery operation, the proposed method works based on inconsistencies and irregular changes created by forgery operations. Inspired by the special properties of CHFM, such as its reconstruction ability by removing redundant information, the proposed method explores CHFM to obtain reconstructed images for the color components of the Original, Forged Noisy and Blurred classes. Motivated by the strong discriminative power of deep CNNs, for the reconstructed images of respective color components, the proposed method used deep CNNs for forged handwriting detection. Experimental results on our dataset and benchmark datasets (namely, ACPR 2019, ICPR 2018 FCD and IMEI datasets) show that the proposed method outperforms existing methods in terms of classification rate.

关键词： Image color analysis Chebyshev approximation Tools Benchmark testing Distortion Forgery pattern recognition

UCPM: Uncertainty-Guided Cross-Modal Retrieval with Partially Mismatched Pairs

学校读者我要写书评

暂无评论

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Quanxing Zha Xin Liu Yiu-Ming Cheung Shu-Juan Peng Xing Xu Nannan Wang Huaqiao University Department of Computer Science Xiamen 361021 China Key Laboratory of Pattern Recognition and Computer Vision Xiamen 361021 China Huaqiao University Fujian Key Laboratory of Big Data Intelligence and Security Xiamen 361021 China Hong Kong Baptist University Department of Computer Science Hong Kong Huaqiao University Department of Artificial Intelligence Xiamen 361021 China Fujian Province University Key Laboratory of Computer Vision and Machine Learning (Huaqiao University) Xiamen 361021 China University of Electronic Science and Technology of China Center for Future Multimedia School of Computer Science and Engineering Chengdu 610051 China Xidian University State Key Laboratory of Integrated Services Networks Xi’an 710071 China

The manual annotation of perfectly aligned labels for cross-modal retrieval (CMR) is incredibly labor-intensive. As an alternative, the collection of co-occurring data pairs from the Internet is a remarkably cost-effective way, but which, inevitably induces the Partially Mismatched Pairs (PMPs) and therefore significantly degrades the retrieval performance without particular treatment. Previous efforts often utilize the pair-wise similarity to filter out the mismatched pairs, and such operation is highly sensitive to mismatched or ambiguous data and thus leads to sub-optimal performance. To alleviate these concerns, we propose an efficient approach, termed UCPM, i.e., Uncertainty-guided Cross-modal retrieval with Partially Mismatched pairs, which can significantly reduce the adverse impact of mismatched data pairs. Specifically, a novel Uncertainty Guided Division (UGD) strategy is sophisticatedly designed to divide the corrupted training data into confident matched (clean), easily-identifiable mismatched (noisy) and hardly-determined hard subsets, and the derived uncertainty can simultaneously guide the informative pair learning while reducing the negative impact of potential mismatched pairs. Meanwhile, an effective Uncertainty Self-Correction (USC) mechanism is concurrently presented to accurately identify and rectify the fluctuated uncertainty during the training process, which further improves the stability and reliability of the estimated uncertainty. Besides, a Trusted Margin Loss (TML) is newly designed to enhance the discriminability between those hard pairs, by dynamically adjusting their soft margins to amplify the positive contributions of matched pairs while suppressing the negative impacts of mismatched pairs. Extensive experiments on three widely-used benchmark datasets, verify the effectiveness and reliability of UCPM compared with the existing SOTA approaches, and significantly improve the robustness in both synthetic and real-world PMPs. The code i

关键词： Cross-modal retrieval partially mismatched pairs trusted margin loss uncertainty guided division uncertainty self-correction

Neighbourhood-guided feature reconstruction for occluded person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Shijie Chen, Dapeng Zhao, Rui Chen, Haobin Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China SenseTime Group Limited Shanghai AI Lab Shanghai China

Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance. To tackle this challenge, we propose to reconstruct the feature representation of occluded parts by fully exploiting the information of its neighborhood in a gallery image set. Specifically, we first introduce a visible part-based feature by body mask for each person image. Then we identify its neighboring samples using the visible features and reconstruct the representation of the full body by an outlierremovable graph neural network with all the neighboring samples as input. Extensive experiments show that the proposed approach obtains significant improvements. In the large-scale Occluded- DukeMTMC benchmark, our approach achieves 64.2% mAP and 67.6% rank-1 accuracy which outperforms the state-of-the-art approaches by large margins, i.e.,20.4% and 12.5%, respectively, indicating the effectiveness of our method on occluded Re-ID problem. Copyright © 2021, The Authors. All rights reserved.

关键词： Security systems