检索结果-内蒙古大学图书馆

ICDAR 2023 Video Text Reading Competition for Dense and Small Text

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Weijia Zhao, Yuzhong Li, Zhuang Li, Jiahong Shou, Mike Zheng Pal, Umapada Karatzas, Dimosthenis Bai, Xiang Zhejiang University China University of Chinese Academy of Sciences China Kuaishou Technology China National University of Singapore Singapore Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Computer Vision Centre Universitat Autónoma de Barcelona Spain Huazhong University of Science and Technology China

Recently, video text detection, tracking and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenario, while ignore extreme video texts challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a video text reading benchmark, named DSText, which focuses on dense and small text reading challenge in the video with various scenarios. Compared with the previous datasets, the proposed dataset mainly include three new challenges: 1) Dense video texts, new challenge for video text spotter. 2) High-proportioned small texts. 3) Various new scenarios, e.g., ‘Game’, ‘Sports’, etc. The proposed DSText includes 100 video clips from 12 open scenarios, supporting two tasks (i.e., video text tracking (Task 1) and end-to-end video text spotting (Task2)). During the competition period (opened on 15th February, 2023 and closed on 20th March, 2023), a total of 24 teams participated in the three proposed tasks with around 30 valid submissions, respectively. In this article, we describe detailed statistical information of the dataset, tasks, evaluation protocols and the results summaries of the ICDAR 2023 on DSText competition. Moreover, we hope the benchmark will promise the video text research in the community. © 2023, CC BY.

关键词： Character recognition

Combining feature aggregation and geometric similarity for re-identification of patterned animals

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Immonen, Veikka Nepovinnykh, Ekaterina Eerola, Tuomas Stewart, Charles V. Kälviäinen, Heikki Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering School of Engineering Sciences Lappeenranta-Lahti University of Technology LUT LappeenrantaFI-53851 Finland Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States

Image-based re-identification of animal individuals allows gathering of information such as migration patterns of the animals over time. This, together with large image volumes collected using camera traps and crowdsourcing, opens novel possibilities to study animal populations. For many species, the re-identification can be done by analyzing the permanent fur, feather, or skin patterns that are unique to each individual. In this paper, we address the re-identification by combining two types of pattern similarity metrics: 1) pattern appearance similarity obtained by pattern feature aggregation and 2) geometric pattern similarity obtained by analyzing the geometric consistency of pattern similarities. The proposed combination allows to efficiently utilize both the local and global pattern features, providing a general re-identification approach that can be applied to a wide variety of different pattern types. In the experimental part of the work, we demonstrate that the method achieves promising re-identification accuracies for Saimaa ringed seals and whale sharks. © 2023, CC BY-NC-SA.

关键词： Animals

A New Lightweight Attention-based Model for Emotion recognition on Distorted Social Media Face Images

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Roy, Ayush Shivakumara, Palaiahnakote Pal, Umapada Gornale, Shivanand S. Liu, Cheng-Lin Jadavpur University India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Department of Computer Science Rani Channamma University Belagavi India Institute of Automation Chinese Academy of Sciences China

The recognition of human emotions remains a challenging task for social media images. This is due to distortions created by different social media conflict with the minute changes in facial expression. This study presents a new model called the Global Spectral-Spatial Attention Network (GSSAN), which leverages both local and global information simultaneously. The proposed model comprises a shallow Convolutional Neural Network (CNN) with an MBResNext block, which integrates the features extracted from MobileNet, ResNet, and DenseNet for extracting local features. In addition, to strengthen the discriminating power of the features, GSSAN incorporates Fourier features, which provide essential cues for minute changes in the face images. To test the proposed model for emotion recognition using social media images, we conduct experiments on two widely-used datasets: FER-2013 and AffectNet. The same benchmark datasets are uploaded and downloaded to create a distorted social media image dataset to test the proposed model. Experiments on distorted social media images dataset show that the model surpasses the accuracy of SOTA models by 0.69% for FER-2013 and 0.51% for AffectNet social mediad datasets. The same inference can be drawn from the experiments on standard datasets. © 2023, CC BY.

关键词： Face recognition

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC SEGMENTATION

学校读者我要写书评

暂无评论

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC ...

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Shi, Guangchen Wu, Yirui Palaiahnakote, Shivakumara Pal, Umapada Lu, Tong College of Computer and Information Hohai University China Department of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India National Key Lab for Novel Software Technology Nanjing University China

ISBN: (纸本)9781665438643

To make predictions on unseen classes, few-shot segmentation becomes a research focus recently. However, most methods build on pixel-level annotation requiring quantity of manual work. Moreover, inherent information on same-category objects to guide segmentation could have large diversity in feature representation due to differences in size, appearance, layout, and so on. To tackle these problems, we present an active-reference network (ARNet) for few-shot segmentation. The proposed active-reference mechanism not only supports accurately co-occurrent objects in either support or query images, but also relaxes high constraint on pixel-level labeling, allowing for weakly boundary labeling. To extract more intrinsic feature representation, a category-modulation module (CMM) is further applied to fuse features extracted from multiple support images, thus forgetting useless and enhancing contributive information. Experiments on PASCAL-5i dataset show the proposed method achieves a m-IOU score of 56.5% for 1-shot and 59.8% for 5-shot segmentation, being 0.5% and 1.3% higher than current state-of-the-art method. © 2021 IEEE

关键词： Semantic Segmentation

Distance Metric Learned Collaborative Representation Classifier(DML-CRC)

学校读者我要写书评

暂无评论

IEEE Letters of the Computer Society

IEEE Letters of the computer Society 2020年第2期3卷 34-37页

作者： Chakraborti, Tapabrata McCane, Brendan Mills, Steven Pal, Umapada Department of Computer Science University of Otago Dunedin9016 New Zealand Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Any generic deep machine learning algorithm is essentially a function fitting exercise, where the network tunes its weights and parameters to learn discriminatory features by minimizing some cost function. Though the network tries to learn the optimal feature space, it seldom tries to learn an optimal distance metric in the cost function, and hence misses out on an additional layer of abstraction. We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner. The proposed method DML-CRC gives state-of-the-art performance on benchmark fine-grained classification datasets CUB Birds, Oxford Flowers and Oxford-IIIT Pets using the VGG-19 deep network. The method is network agnostic and can be used for other similar classification tasks. © 2018 IEEE.

关键词： Learning algorithms

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Haoran Zhang, Yifu Wang, Wenxuan Chen, Chen Liu, Jing Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

学校读者我要写书评

暂无评论

OSRT: Omnidirectional Image Super-Resolution with Distortion...

Conference on computer vision and pattern recognition (CVPR)

作者： Fanghua Yu Xintao Wang Mingdeng Cao Gen Li Ying Shan Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences ARC Tencent PCG The University of Tokyo Platform Technologies Tencent Online Video Shanghai Artificial Intelligence Laboratory

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT.

关键词：

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mo, Ningkai Gan, Wanshui Yokoya, Naoto Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The University of Tokyo Japan RIKEN Japan

In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects. This framework is designed in a simple architecture that efficiently extracts point-wise features from RGB-D data using a fully convolutional network, called XYZNet, and directly regresses the 6D pose without any post refinement. In the case of symmetric object, one object has multiple ground-truth poses, and this one-to-many relationship may lead to estimation ambiguity. In order to solve this ambiguity problem, we design a symmetry-invariant pose distance metric, called average (maximum) grouped primitives distance or A(M)GPD. The proposed A(M)GPD loss can make the regression network converge to the correct state, i.e., all minima in the A(M)GPD loss surface are mapped to the correct poses. Extensive experiments on YCB-Video and TLESS datasets demonstrate the proposed framework's substantially superior performance in top accuracy and low computational cost. The relevant code is available in https://***/GANWANSHUI/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Computational efficiency

TIC: Text-Guided Image Colorization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ghosh, Subhankar Roy, Prasun Bhattacharya, Saumik Pal, Umapada Blumenstein, Michael Faculty of Engineering and IT University of Technology SydneyNSW Australia The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Indian Institute of Technology Kharagpur India

Image colorization is a well-known problem in computer vision. However, due to the ill-posed nature of the task, image colorization is inherently challenging. Though several attempts have been made by researchers to make the colorization pipeline automatic, these processes often produce unrealistic results due to a lack of conditioning. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of the colorization process. To the best of our knowledge, this is one of the first attempts to incorporate textual conditioning in the colorization pipeline. To do so, we have proposed a novel deep network that takes two inputs (the grayscale image and the respective encoded text description) and tries to predict the relevant color gamut. As the respective textual descriptions contain color information of the objects present in the scene, the text encoding helps to improve the overall quality of the predicted colors. We have evaluated our proposed model using different metrics and found that it outperforms the state-of-the-art colorization algorithms both qualitatively and quantitatively. © 2022, CC BY.

关键词： Pipelines