检索结果-内蒙古大学图书馆

Low-Resolution Action recognition for Tiny Actions Challenge

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Boyu Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and appear in a small resolution without much discriminative clue. Second, these activities are naturally distributed in a long-tailed way. It is hard to alleviate data bias for such heavy category imbalance. To tackle these problems, we propose a comprehensive recognition solution in this paper. First, we train video backbones with data balance, in order to alleviate overfitting in the challenge benchmark. Second, we design a dual-resolution distillation framework, which can effectively guide low-resolution action recognition by super-resolution knowledge. Finally, we apply model ensemble with post-processing, which can further boost performance on the long-tailed categories. Our solution ranks Top-1 on the leaderboard. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Reflash Dropout in Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kong, Xiangtao Liu, Xina Gu, Jinjin Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China The University of Sydney Australia Shanghai AI Laboratory Shanghai China

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools – one is from a recent network interpretation work, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical resolving power

Sentiment analysis using cosine similarity measure

学校读者我要写书评

暂无评论

Sentiment analysis using cosine similarity measure

International Conference on Recent Trends in Information Systems (ReTIS)

作者： Saprativa Bhattacharjee Anirban Das Ujjwal Bhattacharya Swapan K. Parui Sudipta Roy Department of Information Technology Sikkim Manipal Institute of Technology Sikkim India School of Computing Jimma University Jimma Ethiopia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Information Technology Assam University Silchar Assam India

The opinion of other people is often a major factor influencing our decisions. For a consumer it affects purchase decisions and for a producer or a service provider it helps in making business decisions. Companies spend a lot of money and time on surveys for gathering the public opinion on products and services. Now-a-days the web has become a hotspot for finding user opinions on almost anything under the sun. Both money and time can be saved by mining opinions from the web. Moreover, no survey can have a sample size, which can match that of the web. Each opinion generally expresses either positive, negative or neutral sentiment. The task of identifying these sentiments is called Sentiment Analysis. This work deals with the analysis of user sentiments in the Telecom domain. Since no such related standard database of users' opinions could be found, we developed one by mining the WWW. A major issue with these sample comments is that these are usually extremely noisy, containing numerous spelling and grammatical errors, acronyms, abbreviations, shortened or slang words etc. Such data cannot be used directly for analyzing sentiments. Hence, a lexicon based preprocessing algorithm is proposed for noise reduction. A novel idea based on Cosine Similarity measure is proposed for classifying the sentiment expressed by a user's comment into a five point scale of -2 (highly negative) to +2 (highly positive). The performance of the proposed strategy is compared with some of the well-known machine learning algorithms namely, Naive Bayes, Maximum Entropy and SVM. The proposed Cosine Similarity based classifier gives 82.09% accuracy for the 2-class problem of identifying positive and negative sentiments. It outperforms all other classifiers by a considerable margin in the 5-class sentiment classification problem with an accuracy of 71.5%. The same strategy is also used for categorizing each user comment into six different Telecom specific categories.

关键词： Accuracy Sentiment analysis Frequency conversion Dictionaries Support vector machines Training Telecommunications

PPT Fusion: Pyramid Patch Transformer for a Case Study in Image Fusion

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fu, Yu Xu, Tianyang Wu, Xiao-Jun Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection. These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues. Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

SSRBC 2016: Sclera Segmentation and recognition Benchmarking Competition

学校读者我要写书评

暂无评论

SSRBC 2016: Sclera Segmentation and Recognition Benchmarking...

IAPR International Conference on Biometrics (ICB)

作者： Abhijit Das Umapada Pal Miguel A. Ferrer Michael Blumenstein Institute for Integrated and Intelligent Systems Griffith University Queensland Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC University of Las Palmas de Gran Canaria Las Palmas Spain School of Software University of Technology Sydney Australia

ISBN: (纸本)9781509018703

This article reports and summarizes the results of a competition on sclera segmentation and recognition benchmarking, called Sclera Segmentation and recognition Benchmarking Competition 2016 (SSRBC 2016). It was organized in the context of the 9th IAPR International Conference on Biometrics (ICB 2016). The goal of this competition was to record the recent developments in sclera segmentation and recognition, and also to gain the attention of researchers on this subject of biometrics. In this regard, we have used a multi-angle sclera dataset (MASD version 1). It is comprised of 2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82*2) different eyes. We have prepared a manual segmentation mask of these images to create the baseline for both tasks. We have, furthermore, adopted precision and recall based statistical measures to evaluate the effectiveness of the segmentation and the ranks of the competing algorithms. The recognition accuracy measure has been employed to measure the recognition task. To summarize, twelve participants registered for the competition, and among them, three participants submitted their algorithms/ systems for the segmentation task and two their recognition algorithm. The results produced by these algorithms reflect developments in the literature of sclera segmentation and recognition, employing cutting edge segmentation techniques. Along with the algorithms of three competing teams and their results, the MASD version 1 dataset will also be freely available for research purposes from the organizer's website. The competition also demonstrates the recent interests of researchers from academia as well as industry on this subject of biometrics.

关键词： Image segmentation Clustering algorithms Iris recognition Manuals Feature extraction

Multi-angle based lively sclera biometrics at a distance

学校读者我要写书评

暂无评论

Multi-angle based lively sclera biometrics at a distance

IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM)

作者： Abhijit Das Umapada Pal Miguel Angel Ferrer Ballester Michael Blumenstein Institute for Integrated and Intelligent Systems Griffith University Queensland Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC Universidad de Las Palmas de Gran Canaria Las Palmas de Gran Canaria Islas Canarias ES

This piece of work proposes a liveliness based sclera eye biometric, validation and recognition technique at a distance. The images in this work are acquired by a digital camera in the visible spectrum at varying distance of about 1 meter from the individual. Each individual during registration as well as validation is asked to look straight and move their eye ball up, left and right keeping their face straight to incorporate liveliness of the data. At first the image is divided vertically into two halves and the eyes are detected in each half of the face image that is captured, by locating the eye ball by a Circular Hough Transform. Then the eye image is cropped out automatically using the radius of the iris. Next a C-means-based segmentation is used for sclera segmentation followed by vessel enhancement by the adaptive histogram equalization and Haar filtering. The feature extraction was performed by patch-based Dense-LDP (Linear Directive pattern). Furthermore each training image is used to form a bag of features, which is used to produce the training model. Each of the images of the different poses is combined at the feature level and the image level to obtain higher accuracy and to incorporate liveliness. The fusion that produces the best result is considered. Support Vector Machines (SVMs) are used for classification. Here images from 82 individuals (both left and right eye i.e. 164 different eyes) are used and an appreciable Equal Error Rate of 0.52% is achieved in this work.

关键词： Iris recognition Image segmentation Feature extraction Training Histograms Adaptive equalizers

IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Zhou, Donghao Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Chinese University of Hong Kong Hong Kong

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, and it requires only static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two main reasons: 1) on the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) on the model side, existing single-shot FAS models are infeasible to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, a large binocular NIR image dataset (BNI-FAS) is constructed and published, which contains more than 300,000 real face and plane attack images, and an Interpretable FAS Transformer (IFAST) is proposed that requires only weak supervision to produce interpretable predictions. Our IFAST can produce pixel-wise disparity maps by the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) block. Besides, a well-designed confidence map generator is adopted to cooperate with the proposed dual-teacher distillation module to obtain the final discriminant results. The comprehensive experiments show that our IFAST can achieve state-of-the-art results on BNI-FAS, proving the effectiveness of the single-shot FAS based on binocular NIR images. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tang, Zhangyong Xu, Tianyang Li, Hui Wu, Xiao-Jun Zhu, XueFeng Kittler, Josef Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China The Center for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and decision-level fusion. Specifically, different from the existing methods, paradigm of image fusion task is heeded for fusion at pixel level. Feature-level fusion is fulfilled by attention mechanism with channels excited optionally. Besides, at decision level, a novel fusion strategy is put forward since an effortless averaging configuration has shown the superiority. The effectiveness of the proposed decision-level fusion strategy owes to a number of innovative contributions, including a dynamic weighting of the RGB and TIR contributions and a linear template update operation. A variant of which produced the winning tracker at the Visual Object Tracking Challenge 2020 (VOT-RGBT2020). The concurrent exploration of innovative pixel- and feature-level fusion strategies highlights the advantages of the proposed decision-level fusion method. Extensive experimental results on three challenging datasets, i.e., GTOT, VOT-RGBT2019, and VOT-RGBT2020, demonstrate the effectiveness and robustness of the proposed method, compared to the state-of-the-art approaches. Code will be shared at https://***/Zhangyong-Tang/DFAT. © 2022, CC BY.

关键词： Pixels

A new unified method for detecting text from marathon runners and sports players in video

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Nag, Sauradip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Blumenstein, Michael Kalyani Government Engineering College Kalyani Kolkata India 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 Sydney Australia

Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures of human bodies or actions. This paper presents a new unified method for tackling the above challenges. The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions. Candidate regions are used for determining the number of temporal frame clusters obtained by K-means clustering on frame differences. This process in turn detects key frames. The proposed method explores Bayesian probability for skin portions using color values at both pixel and component levels of temporal frames, which provides fused images with skin components. Based on skin information, the proposed method then detects faces and torsos by finding structural and spatial coherences between them. We further propose adaptive pixels linking a deep learning model for text detection from torso regions. The proposed method is tested on our own dataset collected from marathon/sports video and three standard datasets, namely, RBNR, MMM and R-ID of marathon images, to evaluate the performance. In addition, the proposed method is also tested on the standard natural scene datasets, namely, CTW1500 and MS-COCO text datasets, to show the objectiveness of the proposed method. A comparative study with the state-of-the-art methods on bib number/text detection of different datasets shows that the proposed method outperforms the existing methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels