检索结果-内蒙古大学图书馆

International Conference on computer vision Workshops (ICCV Workshops)

作者： Matteo Zanotto Diego Sona Vittorio Murino Francesco Papaleo Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova Italy Neuroscience and Brain Technologies Istituto Italiano di Tecnologia Italy

Automatic analysis of rodents behaviour has received growing attention in recent years as rodents are the reference species for large scale pharmacological and genetic screenings. In this paper we propose a new method to identify prototypical high-level behavioural patterns which go beyond simple atomic actions. The method is embedded in a data mining pipeline thought to support behavioural scientists in exploratory data analysis and hypothesis formulation. A case study is presented where the method is capable of learning high-level behavioural prototypes which help discriminating between two strains of mouse having known differences in their behaviour.

关键词： Mice Prototypes Data mining Pipelines Strain computer vision Histograms

来源：评论

学校读者我要写书评

暂无评论

Learning how to teach from “Videolectures”: automatic prediction of lecture ratings based on teacher's nonverbal behavior

Learning how to teach from “Videolectures”: automatic pred...

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Pietro Salvagnini Hugues Salamin Marco Cristani Alessandro Vinciarelli Vittorio Murino Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia Genova Italy Department of Computer Science University of Glasgow UK Idiap Research Institute Martigny Switzerland

Large repositories of presentation recordings (e.g., “Videolectures” and “Academic Earth”) often provide their users with rating facilities. The rating of a presentation certainly depends on the content, but the way the content is delivered is likely to play a role as well. This paper focuses on the latter aspect and shows that nonverbal behavior (in particular arms movement and prosody) allows one to predict whether a presentation is rated as low or high in terms of quality. The experiments have been performed over 100 presentations collected from “Videolectures” and the accuracy is up to 66% depending on the techniques adopted. In other words, nonverbal communication actually influences the ratings assigned to a presentation.

关键词： Feature extraction Optical imaging Vectors Media Accuracy Estimation Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cdhn: Cross-Domain Hallucination Network for 3d Keypoints Estimation

SSRN

引用

SSRN 2023年

作者： Zohaib, Mohammad Padalkar, Milind Gajanan Morerio, Pietro Taiana, Matteo Del Bue, Alessio Pattern Analysis & Computer Vision Italian Institute of Technology Genoa Italy Department of Marine Electrical Electronic and Telecommunications Engineering University of Genoa Italy

This paper presents a novel method to estimate 3D keypoints from single-view RGB images. Our network is trained in two steps using a knowledge distillation framework. In the first step, the teacher is trained to extract 3D features from point cloud data, which are used in combination with 2D features to estimate the 3D keypoints. In the second step, the teacher teaches the student module to hallucinate the 3D features from RGB images that are similar to those extracted from the point clouds. This procedure helps the network during inference to extract 2D and 3D features directly from images, without requiring point clouds as input. Moreover, the network also predicts a confidence score for every keypoint, which is used to select the valid ones from a set of N predicted keypoints. This allows the prediction of different number of keypoints depending on the object’s geometry. We use the estimated keypoints for computing the relative pose between two views of an object. The results are compared with those of KP-Net[1] and StarMap [2], which are the state-of-the-art for estimating 3D keypoints from a single-view RGB image. The average angular distance error of our approach (5.94[[EQUATION]]) is 8.46[[EQUATION]] and 55.26[[EQUATION]] lower than that of KP-Net (14.40[[EQUATION]]) and StarMap (61.20[[EQUATION]]), respectively. © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Fisher Kernels for Handwritten Word-spotting

Fisher Kernels for Handwritten Word-spotting

引用

International Conference on Document analysis and Recognition

作者： Florent Perronnin Jose A. Rodriguez-Serrano Textual and Visual Pattern Analysis Xerox Research Centre Europe France Computer Vision Centre Universitat Authnòma de Barcelona Spain

The Fisher kernel is a generic framework which combines the benefits of generative and discriminative approaches to pattern classification. In this contribution, we propose to apply this framework to handwritten word-spotting. Given a word image and a keyword generative model, the idea is to generate a vector which describes how the parameters of the keyword model should be modified to best fit the word *** vector can then be used as the input of a discriminative classifier. We compare the performance of the proposed approach with that of a generative baseline on a challenging real-world dataset of customer letters. When the kernel used by the classifier is linear, the performance improvement is marginal but the proposed system is approximately 15 times faster than the baseline. If we use a non-linear kernel devised for this task, we obtain a 15% relative reduction of the error but the detector is approximately 15 times slower.

关键词： Kernel Hidden Markov models pattern classification pattern analysis Europe Text analysis Handwriting recognition pattern recognition computer vision Vectors

来源：评论

学校读者我要写书评

暂无评论

Generative Pseudo-label Refinement for Unsupervised Domain Adaptation

arXiv

引用

arXiv 2020年

作者： Morerio, Pietro Volpi, Riccardo Ragonesi, Ruggero Murino, Vittorio Pattern Analysis & Computer Vision - Istituto Italiano di Tecnologia Computer Science Department Università di Verona Italy Huawei Technologies Ltd. Ireland Research Center

We investigate and characterize the inherent resilience of conditional Generative Adversarial Networks (cGANs) against noise in their conditioning labels, and exploit this fact in the context of Unsupervised Domain Adaptation (UDA). In UDA, a classifier trained on the labelled source set can be used to infer pseudo-labels on the unlabelled target set. However, this will result in a significant amount of misclassified examples (due to the well-known domain shift issue), which can be interpreted as noise injection in the ground-truth labels for the target set. We show that cGANs are, to some extent, robust against such "shift noise". Indeed, cGANs trained with noisy pseudo-labels, are able to filter such noise and generate cleaner target samples. We exploit this finding in an iterative procedure where a generative model and a classifier are jointly trained: in turn, the generator allows to sample cleaner data from the target distribution, and the classifier allows to associate better labels to target samples, progressively refining target pseudo-labels. Results on common benchmarks show that our method performs better or comparably with the unsupervised domain adaptation state of the art. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Compact CNN Structure Learning by Knowledge Distillation

Compact CNN Structure Learning by Knowledge Distillation

引用

International Conference on pattern Recognition

作者： Waqar Ahmed Andrea Zunino Pietro Morerio Vittorio Murino University of Genova Italy Dublin Ireland Pattern Analysis & Computer Vision (PAVIS) Istituto Italiano di Tecnologia Genova Italy University of Verona Italy

The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in inference accuracy in computer vision tasks. To address such a drawback, we propose a framework that leverages knowledge distillation along with customizable block-wise optimization to learn a lightweight CNN structure while preserving better control over the compression-performance tradeoff. Considering specific resource constraints, e.g., floating-point operations per inference (FLOPs) or model-parameters, our method results in a state of the art network compression while being capable of achieving better inference accuracy. In a comprehensive evaluation, we demonstrate that our method is effective, robust, and consistent with results over a variety of network architectures and datasets, at negligible training overhead. In particular, for the already compact network MobileNet_v2, our method offers up to 2× and 5.2× better model compression in terms of FLOPs and model-parameters, respectively, while getting 1.05% better model performance than the baseline network.

关键词： Training Learning systems Knowledge engineering computer vision Network architecture Predictive models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PERSON RE-IDENTIFICATION USING SPARSE REPRESENTATION WITH MANIFOLD CONSTRAINTS

PERSON RE-IDENTIFICATION USING SPARSE REPRESENTATION WITH MA...

引用

IEEE International Conference on Image Processing

作者： Behzad Mirmahboub Hamed Kiani Amran Bhuiyan Alessandro Perina Baochang Zhang Alessio Del Bue Vittorio Murino Pattern Analysis and Computer Vision (PAVIS) Italian Institute of Technology Genova Italy School of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (纸本)9781467399623

Human re-identification is still a challenging task due to the human pose and illumination variations. Nowadays, surveillance cameras with high frame rate are capable of capturing several consecutive frames from each person. Multi-shot images provide richer information of the target person compared to a single-shot image. They, however, produce a high cost of information redundancy which may degrade the performance of re-identification systems. In this paper, we propose a novel framework that combines sparse coding and manifold constraints to extract discriminative information from multi-shot images of one pedestrian for person re-identification across a set of non-overlapped surveillance cameras. The evaluation over two standard multi-shot datasets shows very competitive accuracy of our framework against the state-of-the-art.

关键词： Manifolds Cameras Training Dictionaries Brightness Lighting Redundancy

来源：评论

学校读者我要写书评

暂无评论

Passive underwater imaging through optimized planar arrays of hydrophones

Passive underwater imaging through optimized planar arrays o...

引用

OCEANS

作者： Andrea Trucco Samuele Martelli Marco Crocco Dept. of Electrical University of Genoa Genova Italy Pattern Analysis & Computer Vision (PAVIS) Istituto Italiano di Tecnologia (IIT) Genova Italy

Planar arrays of acoustic sensors represent a critical component for a 3-D wideband passive imaging system. Recently, a method has been proposed for the design of planar microphone arrays that are superdirective (to provide good performance at low frequencies) and aperiodic (to avoid grating lobes at high frequencies). Robustness against dispersion in the sensor characteristics is achieved by exploiting the probability density functions of such errors. Here, such a method is used to demonstrate that 36 low-cost poorly-matched hydrophones are sufficient to populate a square aperture with a side length of 60 cm used as sensor array for an underwater passive system working from 1.5 kHz to 12 kHz.

关键词： Array signal processing Planar arrays Sonar equipment Finite impulse response filters Transducers Layout Robustness

来源：评论

学校读者我要写书评

暂无评论

Efficient pooling of image based CNN features for action recognition in videos

Efficient pooling of image based CNN features for action rec...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Biplab Banerjee Vittorio Murino Department of Computer Sc. & Engg. Indian Institute of Technology Roorkee India Pattern Analysis & Computer vision (PAVIS) Istituto Italiano di Tecnologia Genova Italy

ISBN: (纸本)9781509041183

In this paper, we propose a new video representation incorporating image based deep features and an efficient pooling strategy for the purpose of action recognition. The Convolutional Neural Network (CNN) based features have very recently emerged as the new state of the art for image classification. Several attempts have been made to extend such CNN models for videos by explicitly focusing on the temporal evolution of the frames. Feature pooling is one such approach which represents video sequences in terms of some statistical properties of the feature dimensions over the frames. However, traditional pooling strategies including max or average pooling explicitly fail to capture the temporal progression of the frame-level contents. In contrast to previous pooling techniques, we propose a two-level video representation which separately focuses on the entire video as well as a number of video sub-volumes. In both levels, we introduce a generic time series pooling on the frame-level deep CNN features efficiently. Further, a self-tuning spectral clustering is considered to highlight video snippets which are highly probable to contain significant sub-action sequences. We validate the proposed feature encoding on the challenging KTH-actions and UCF-50 datasets and find that the proposed encoding outperforms traditional pooling based feature representations by substantial margin.

关键词： Action recognition Convolutional Neural Network Spectral Clustering

来源：评论

学校读者我要写书评

暂无评论

Organ Segmentation with Recursive Data Augmentation for Deep Models 25th

Organ Segmentation with Recursive Data Augmentation for Deep...

引用

25th International Conference on pattern Recognition Workshops, ICPR 2020

作者： Akbar, Muhammad Usman Yamin, Muhammad Abubakar Murino, Vittorio Sona, Diego Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova Italy Department of Electrical Electronics and Telecommunication Engineering Università di Genova Genova Italy Huawei Technologies Ltd. Ireland Research Center Dublin Ireland Department of Computer Science Università di Verona Verona Italy Neuroinformatics Laboratory Fondazione Bruno Kessler Trento Italy

ISBN: (纸本)9783030687625

The precise segmentation of organs from computed tomography is a fundamental and pivotal task for correct diagnosis and proper treatment of diseases. Neural network models are widely explored for their promising performance in the segmentation of medical images. However, the small dimension of available datasets is affecting the biomedical imaging domain significantly and has a huge impact in training of deep learning models. In this paper we try to address this issue by iteratively augmenting the dataset with auxiliary task-based information. This is obtained by introducing a recursive training approach, where a new set of segmented images is generated at each iteration and then concatenated with the original input data as organ attention maps. In the experimental evaluation two different datasets were tested and the results produced from the proposed approach have shown significant improvements in organ segmentation as compared to a standard non-recursive approach. © 2021, Springer Nature Switzerland AG.

关键词： Deep learning

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：