检索结果-内蒙古大学图书馆

An Empirical Study of Super-Resolution on Low-Resolution Micro-Expression Recognition

学校读者我要写书评

暂无评论

IEEE Transactions on Affective Computing 2025年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying Macau University of Science and Technology School of Computer Science and Engineering 999078 China Nanjing Institute of Technology School of International Education Oulu School Jiangsu Nanjing211167 China Southeast University Key Laboratory of Child Development and Learning Science Ministry of Education Nanjing210096 China Southeast University Research Center for Learning Science China Southeast University School of Biological Science and Medical Engineering Jiangsu Nanjing210096 China Jiangsu University School of Computer Science and Communication Engineering Jiangsu Zhenjiang212013 China University of Oulu Center for Machine Vision and Signal Analysis 90014 Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution (SR) techniques for enhancing the quality of LR images and videos, few study has focused on investigate SR for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of SR-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both SR and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 22 SOTA SR techniques, thereby addressing the problem of SR in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. © 2010-2012 IEEE.

关键词： Optical resolving power

Robustness of object detectors in degrading weather conditions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mirza, Muhammad Jehanzeb Buerkle, Cornelius Jarquin, Julio Opitz, Michael Oboril, Fabian Scholl, Kay-Ulrich Bischof, Horst Christian Doppler Laboratory for Embedded Machine Learning Institute for Computer Graphics and Vision Graz University of Technology Austria Intel Labs Karlsruhe Germany

State-of-the-art object detection systems for autonomous driving achieve promising results in clear weather conditions. However, such autonomous safety critical systems also need to work in degrading weather conditions, such as rain, fog and snow. Unfortunately, most approaches evaluate only on the KITTI dataset, which consists only of clear weather scenes. In this paper we address this issue and perform one of the most detailed evaluation on single and dual modality architectures on data captured in real weather conditions. We analyse the performance degradation of these architectures in degrading weather conditions. We demonstrate that an object detection architecture performing good in clear weather might not be able to handle degrading weather conditions. We also perform ablation studies on the dual modality architectures and show their limitations. © 2021, CC BY.

关键词： Object detection

VidHarm: A Clip Based Dataset for Harmful Content Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Edstedt, Johan Berg, Amanda Felsberg, Michael Karlsson, Johan Benavente, Francisca Novak, Anette Pihlgren, Gustav Grund Computer Vision Laboratory Linköping University Sweden Statens Medieråd Stockholm Sweden EISLAB Machine Learning Luleå University of Technology Sweden

Automatically identifying harmful content in video is an important task with a wide range of applications. However, there is a lack of professionally labeled open datasets available. In this work VidHarm, an open dataset of 3589 video clips from film trailers annotated by professionals, is presented. An analysis of the dataset is performed, revealing among other things the relation between clip and trailer level annotations. Audiovisual models are trained on the dataset and an in-depth study of modeling choices conducted. The results show that performance is greatly improved by combining the visual and audio modality, pre-training on large-scale video recognition datasets, and class balanced sampling. Lastly, biases of the trained models are investigated using discrimination probing. VidHarm is openly available, and further details are available at the webpage https://***/. © 2021, CC BY-NC-SA.

关键词： Light trailers

Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Yonghao Yu, Weikang Ghamisi, Pedram Kopp, Michael Hochreiter, Sepp Vienna1030 Austria Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping58183 Sweden Helmholtz-Zentrum Dresden-Rossendorf Helmholtz Institute Freiberg for Resource Technology Machine Learning Group Freiberg09599 Germany ELLIS Unit Linz and LIT AI Lab Institute for Machine Learning Johannes Kepler University Linz4040 Austria

The synthesis of high-resolution remote sensing images based on text descriptions has great potential in many practical application scenarios. Although deep neural networks have achieved great success in many important remote sensing tasks, generating realistic remote sensing images from text descriptions is still very difficult. To address this challenge, we propose a novel text-to-image modern Hopfield network (Txt2Img-MHN). The main idea of Txt2Img-MHN is to conduct hierarchical prototype learning on both text and image embeddings with modern Hopfield layers. Instead of directly learning concrete but highly diverse text-image joint feature representations for different semantics, Txt2Img-MHN aims to learn the most representative prototypes from text-image embeddings, achieving a coarse-to-fine learning strategy. These learned prototypes can then be utilized to represent more complex semantics in the text-to-image generation task. To better evaluate the realism and semantic consistency of the generated images, we further conduct zero-shot classification on real remote sensing data using the classification model trained on synthesized images. Despite its simplicity, we find that the overall accuracy in the zero-shot classification may serve as a good metric to evaluate the ability to generate an image from text. Extensive experiments on the benchmark remote sensing text-image dataset demonstrate that the proposed Txt2Img-MHN can generate more realistic remote sensing images than existing methods. Code and pre-trained models are available online (https://***/YonghaoXu/Txt2Img-MHN). Copyright © 2022, The Authors. All rights reserved.

关键词： Remote sensing

HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： He, Chunming Li, Kai Xu, Guoxia Yan, Jiangpeng Tang, Longxiang Zhang, Yulun Li, Xiu Wang, Yaowei Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China Machine Learning Department NEC Laboratories America Inc. NJ08540 United States Department of Computer Science Norwegian University of Science and Technology Gjovik2815 Norway The Computer Vision Lab ETH Zürich Zürich8092 Switzerland Peng Cheng Laboratory Shenzhen518066 China

Unpaired Medical Image Enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most existing approaches are based on Pix2Pix/CycleGAN and are effective to some extent, they fail to explicitly use HQ information to guide the enhancement process, which can lead to undesired artifacts and structural distortions. In this paper, we propose a novel UMIE approach that avoids the above limitation of existing methods by directly encoding HQ cues into the LQ enhancement process in a variational fashion and thus model the UMIE task under the joint distribution between the LQ and HQ domains. Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module. We train the enhancement network adversarially with a discriminator to ensure the generated HQ image falls into the HQ domain. We further propose a content-aware loss to guide the enhancement process with wavelet-based pixel-level and multi-encoder-based feature-level constraints. Additionally, as a key motivation for performing image enhancement is to make the enhanced images serve better for downstream tasks, we propose a bi-level learning scheme to optimize the UMIE task and downstream tasks cooperatively, helping generate HQ images both visually appealing and favorable for downstream tasks. Experiments on three medical datasets, including two newly collected datasets, verify that the proposed method outperforms existing techniques in terms of both enhancement quality and downstream task performance. We will make the code and the newly collected datasets publicly available for community study. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

An Empirical Study of Super-resolution on Low-resolution Micro-expression Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Ling Wang, Mingpei Huang, Xiaohua Zheng, Wenming Mao, Qirong Zhao, Guoying The School of Computer Science and Engineering Macau University of Science and Technology China The Key Laboratory of Child Development and Learning Science Ministry of Education Southeast University Nanjing210096 China School of Computer Engineering Nanjing Institute of Technology Jiangsu China The School of Biological Science and Medical Engineering Southeast University Jiangsu Nanjing210096 China The School of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang China The Center for Machine Vision and Signal Analysis University of Oulu Finland

Micro-expression recognition (MER) in low-resolution (LR) scenarios presents an important and complex challenge, particularly for practical applications such as group MER in crowded environments. Despite considerable advancements in super-resolution techniques for enhancing the quality of LR images and videos, few study has focused on investigate super-resolution for improving LR MER. The scarcity of investigation can be attributed to the inherent difficulty in capturing the subtle motions of micro-expressions, even in original-resolution MER samples, which becomes even more challenging in LR samples due to the loss of distinctive features. Furthermore, a lack of systematic benchmarking and thorough analysis of super-resolution-assisted MER methods has been noted. This paper tackles these issues by conducting a series of benchmark experiments that integrate both super-resolution (SR) and MER methods, guided by an in-depth literature survey. Specifically, we employ seven cutting-edge state-of-the-art (SOTA) MER techniques and evaluate their performance on samples generated from 13 SOTA SR techniques, thereby addressing the problem of super-resolution in MER. Through our empirical study, we uncover the primary challenges associated with SR-assisted MER and identify avenues to tackle these challenges by leveraging recent advancements in both SR and MER methodologies. Our analysis provides insights for progressing toward more efficient SR-assisted MER. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

Estimating Polyp Size From a Single Colonoscopy Image Using a Shape-From-Shading Model

学校读者我要写书评

暂无评论

Estimating Polyp Size From a Single Colonoscopy Image Using ...

IEEE International Symposium on Biomedical Imaging

作者： Josué Ruano Diego Bravo Diana Giraldo Martín Gómez Fabio A. González Antoine Manzanera Eduardo Romero Computer Imaging and Medical Applications Laboratory (CIM@LAB) Universidad Nacional de Colombia Bogotá Colombia Department of Physics Imec-Vision Lab University of Antwerp Antwerp Belgium Unidad de Gastroenterología Hospital Universitario Nacional de Colombia Bogotá Colombia Machine Learning Perception and Discovery Lab (MindLab) ENSTA-Institut Polytechnique de Paris Unité d’Informatique et d’Ingénierie des Systémes France

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Colonoscopy (CO) is the most useful procedure to estimate the polyp size as part of surveillance and therapeutic management to prevent Colorectal cancer. Studies have reported a high rate of misestimated lesions by experts, reaching a relative accuracy of 67%. This work presents a method to estimate polyp size from a raw CO frame. A shape-from-shading model trained with synthetic images estimates a depth map to reconstruct the three-dimensional (3d) colon structure. Polyp is segmented in RGB image with a U-Net, to compute diameter in pixels. This diameter is projected onto the 3d surface to compute polyp size in millimeters. The method obtained a mean absolute error of 2.16 mm and relative accuracy of 88.17% in 2802 synthetic images, and 2.06 mm in 100 real images. In a binary classification task (< 10 mm or > 10 mm), the method achieved macro F1 scores of 89% and 72% in the synthetic and real databases respectively.

关键词： Surface reconstruction Solid modeling Image segmentation Three-dimensional displays Accuracy Surveillance Colonoscopy

learning referee evaluation and assessing action quality from coarse to fine in diving sport

学校读者我要写书评

暂无评论

Neurocomputing 2025年

作者： Hong-Ming Qiu Hong-Bo Zhang Qing Lei Jing-Hua Liu Ji-Xiang Du Department of Computer Science and Technology Huaqiao University Xiamen 361021 China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen 361021 China Key Laboratory of Computer Vision and Machine Learning (Huaqiao University) Fujian Province University Xiamen 361021 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen 361021 China

Intelligently assessing the quality of athletic performances in sports scenarios remains a fascinating challenge in computer vision. However, unraveling the subtle distinctions between two similar actions in videos and mapping those video representations to quality scores remain significant obstacles. To address these challenges, this work redefines the paradigm of quality score estimation from traditional relative quality score prediction to relative referee score prediction. To make this shift, a cross-feature fusion module rooted in Transformer-based video representation is introduced, to improve pairwise video feature learning in the realm of action quality assessment. Then, a novel contrastive action parsing decoder module generates mid-level representations to effectively connect visual features with detailed quality scores. Both modules utilize cross-attention mechanisms; the former refines the pairwise video features to represent the differences between video pairs, while the latter updates the input queries corresponding to each referee’s evaluation. Finally, to achieve precise quality score estimation, we introduce a meticulous coarse-to-fine decision process, integrating a score classifier and offset regressor. After validation on challenging diving datasets, including MTL-AQA, FineDiving, and TASD-2, the experimental results show that the proposed approach demonstrates effectiveness and feasibility when compared with state-of-the-art methods.

关键词：

Discriminatively Learned Convex Models for Set Based Face Recognition

学校读者我要写书评

暂无评论

Discriminatively Learned Convex Models for Set Based Face Re...

International Conference on computer vision (ICCV)

作者： Hakan Cevikalp Golara Ghorban Dordinejad Machine Learning and Computer Vision Laboratory Eskisehir Osmangazi University

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Majority of the image set based face recognition methods use a generatively learned model for each person that is learned independently by ignoring the other persons in the gallery set. In contrast to these methods, this paper introduces a novel method that searches for discriminative convex models that best fit to an individual's face images but at the same time are as far as possible from the images of other persons in the gallery. We learn discriminative convex models for both affine and convex hulls of image sets. During testing, distances from the query set images to these models are computed efficiently by using simple matrix multiplications, and the query set is assigned to the person in the gallery whose image set is closest to the query images. The proposed method significantly outperforms other methods using generative convex models in terms of both accuracy and testing time, and achieves the state-of-the-art results on four of the five tested datasets. Especially, the accuracy improvement is significant on the challenging PaSC, COX and ESOGU video datasets.

关键词： Face Computational modeling Face recognition Symmetric matrices Measurement Manifolds Optimization