检索结果-内蒙古大学图书馆

2016 ieee conference on computer vision and pattern recognition (cvpr)

作者： Koller, Oscar Ney, Hermann Bowden, Richard Rhein Westfal TH Aachen Human Language Technol & Pattern Recog Aachen Germany Univ Surrey Ctr Vis Speech & Signal Proc Guildford Surrey England

ISBN: (纸本)9781467388511

this work presents a new approach to learning a frame-based classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm. this allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos. Although we demonstrate this in the context of hand shape recognition, the approach has wider application to any video recognition task where frame level labelling is not available. the iterative EM algorithm leverages the discriminative ability of the CNN to iteratively refine the frame level annotation and subsequent training of the CNN. By embedding the classifier within an EM framework the CNN can easily be trained on 1 million hand images. We demonstrate that the final classifier generalises over both individuals and data sets. the algorithm is evaluated on over 3000 manually labelled hand shape images of 60 different classes which will be released to the community. Furthermore, we demonstrate its use in continuous sign language recognition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin. To our knowledge no previous work has explored expectation maximization without Gaussian mixture models to exploit weak sequence labels for sign language recognition.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

ER3: A Unified Framework for Event Retrieval, recognition and Recounting 30

ER3: A Unified Framework for Event Retrieval, Recognition an...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Gao, Zhanning Hua, Gang Zhang, Dongqing Jojic, Nebojsa Wang, Le Xue, Jianru Zheng, Nanning Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Shaanxi Peoples R China Microsoft Res Redmond WA USA

ISBN: (纸本)9781538604571

We develop a unified framework for complex event retrieval, recognition and recounting. the framework is based on a compact video representation that exploits the temporal correlations in image features. Our feature alignment procedure identifies and removes the feature redundancies across frames and outputs an intermediate tensor representation we call video imprint. the video imprint is then fed into a reasoning network, whose attention mechanism parallels that of memory networks used in language modeling. the reasoning network simultaneously recognizes the event category and locates the key pieces of evidence for event recounting. In event retrieval tasks, we show that the compact video representation aggregated from the video imprint achieves significantly better retrieval accuracy compared with existing methods. We also set new state of the art results in event recognition tasks with an additional benefit: the latent structure in our reasoning network highlights the areas of the video imprint and can be directly used for event recounting. As video imprint maps back to locations in the video frames, the network allows not only the identification of key frames but also specific areas inside each frame which are most influential to the decision process.

关键词： Feature extraction Cognition pattern recognition Neural networks Layout computer vision

来源：评论

学校读者我要写书评

暂无评论

A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning 30

A Gift from Knowledge Distillation: Fast Optimization, Netwo...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Yim, Junho Joo, Donggyu Bae, Jihoon Kim, Junmo Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea Elect & Telecommun Res Inst Daejeon South Korea

ISBN: (纸本)9781538604571

We introduce a novel technique for knowledge transfer, where knowledge from a pretrained deep neural network (DNN) is distilled and transferred to another DNN. As the DNN maps from the input space to the output space through many layers sequentially, we define the distilled knowledge to be transferred in terms of flow between layers, which is calculated by computing the inner product between features from two layers. When we compare the student DNN and the original network with the same size as the student DNN but trained without a teacher network, the proposed method of transferring the distilled knowledge as the flow between two layers exhibits three important phenomena: (1) the student DNN that learns the distilled knowledge is optimized much faster than the original model;(2) the student DNN outperforms the original DNN;and (3) the student DNN can learn the distilled knowledge from a teacher DNN that is trained at a different task, and the student DNN outperforms the original DNN that is trained from scratch.

关键词： Training Optimization Knowledge engineering Feature extraction Knowledge transfer computer vision Transfer (Psychology) Knowledge based engineering images computer vision Feature extraction Students TWO-LAYER Functional training Epistemology Training

来源：评论

学校读者我要写书评

暂无评论

A Low Power, Fully Event-Based Gesture recognition System 30

A Low Power, Fully Event-Based Gesture Recognition System

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Amir, Arnon Taba, Brian Berg, David Melano, Timothy McKinstry, Jeffrey Di Nolfo, Carmelo Nayak, Tapan Andreopoulos, Alexander Garreau, Guillaume Mendoza, Marcela Kusnitz, Jeff Debole, Michael Esser, Steve Delbruck, Tobi Flickner, Myron Modha, Dharmendra IBM Res Yorktown Hts NY 10598 USA Univ Calif San Diego San Diego CA USA UZH ETH Zurich Zurich Switzerland IniLabs GmbH Zurich Switzerland

ISBN: (纸本)9781538604571

We present the first gesture recognition system implemented end-to-end on event-based hardware, using a TrueNorth neurosynaptic processor to recognize hand gestures in real-time at low power from events streamed live by a Dynamic vision Sensor (DVS). the biologically inspired DVS transmits data only when a pixel detects a change, unlike traditional frame-based cameras which sample every pixel at a fixed frame rate. this sparse, asynchronous data representation lets event-based cameras operate at much lower power than frame-based cameras. However, much of the energy efficiency is lost if, as in previous work, the event stream is interpreted by conventional synchronous processors. Here, for the first time, we process a live DVS event stream using TrueNorth, a natively event-based processor with 1 million spiking neurons. Configured here as a convolutional neural network (CNN), the TrueNorth chip identifies the onset of a gesture with a latency of 105 ms while consuming less than 200mW. the CNN achieves 96.5% out-of-sample accuracy on a newly collected DVS dataset (DvsGesture) comprising 11 hand gesture categories from 29 subjects under 3 illumination conditions.

关键词： Event-based Gestures LOW POWER Daphne virus S Gesture recognition Energy efficiency pixel end-to-end Cameras PROCESSOR recognition system Latency

来源：评论

学校读者我要写书评

暂无评论

Instance-aware Image and Sentence Matching with Selective Multimodal LSTM 30

Instance-aware Image and Sentence Matching with Selective Mu...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Huang, Yan Wang, Wei Wang, Liang Natl Lab Pattern Recognit Ctr Res Intelligent Percept & Comp CRIPAC Beijing Peoples R China Chinese Acad Sci CASIA Ctr Excellence Brain Sci & Intelligence Tech Inst Automat Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781538604571

Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we propose a selective multimodal Long Short-Term Memory network (sm-LSTM) for instance-aware image and sentence matching. the sm-LSTM includes a multimodal context-modulated attention scheme at each timestep that can selectively attend to a pair of instances of image and sentence, by predicting pairwise instance-aware saliency maps for image and sentence. For selected pairwise instances, their representations are obtained based on the predicted saliency maps, and then compared to measure their local similarity. By similarly measuring multiple local similarities within a few timesteps, the sm-LSTM sequentially aggregates them with hidden states to obtain a final matching score as the desired global similarity. Extensive experiments show that our model can well match image and sentence with complex content, and achieve the state-of-the-art results on two public benchmark datasets.

关键词： Dogs Roads Image color analysis Aggregates Detectors pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Online Multi-Camera Tracking with Memory-Efficient Accumulated Appearance Features and Trajectory Validation

Efficient Online Multi-Camera Tracking with Memory-Efficient...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lap Quoc Tran Huan Duc Vi Asilla Tokyo Japan

ISBN: (纸本)9798350365474

Multi-camera tracking (MCT) plays a crucial role in various computer vision applications. However, accurate tracking of individuals across multiple cameras faces challenges, particularly with identity switches. In this paper, we present an efficient online MCT system that tackles these challenges through online processing. Our system leverages memory-efficient accumulated appearance features to provide stable representations of individuals across cameras and time. By incorporating trajectory validation using hierarchical agglomerative clustering (HAC) in overlapping regions, ID transfers are identified and rectified. Evaluation on the 2024 AI City Challenge Track 1 dataset [39] demonstrates the competitive performance of our system, achieving accurate tracking in both overlapping and non-overlapping camera networks. With a 40.3% HOTA score [29], our system ranked 9th in the challenge. the integration of trajectory validation enhances performance by 8% over the baseline, and the accumulated appearance features further contribute to a 17% improvement.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Novel Tensor-based Video Rain Streaks Removal Approach via Utilizing Discriminatively Intrinsic Priors 30

A Novel Tensor-based Video Rain Streaks Removal Approach via...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Jiang, Tai-Xiang Huang, Ting-Zhu Zhao, Xi-Le Deng, Liang-Jian Wang, Yao Univ Elect Sci & Technol China Sch Math Sci Chengdu Sichuan Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian Shaanxi Peoples R China

ISBN: (纸本)9781538604571

Rain streaks removal is an important issue of the outdoor vision system and has been recently investigated extensively. In this paper, we propose a novel tensor based video rain streaks removal approach by fully considering the discriminatively intrinsic characteristics of rain streaks and clean videos, which needs neither rain detection nor time-consuming dictionary learning stage. In specific, on the one hand, rain streaks are sparse and smooth along the raindrops' direction, and on the other hand, the clean videos possess smoothness along the rain-perpendicular direction and global and local correlation along time direction. We use the l(1) norm to enhance the sparsity of the underlying rain streaks, two unidirectional Total Variation (TV) regularizers to guarantee the different discriminative smoothness, and a tensor nuclear norm and a time directional difference operator to characterize the exclusive correlation of the clean video along time. Alternation direction method of multipliers (ADMM) is employed to solve the proposed concise tensor based convex model. Experiments implemented on synthetic and real data substantiate the effectiveness and efficiency of the proposed method. Under comprehensive quantitative performance measures, our approach outperforms other state-of-the-art methods.

关键词： rain Streak Videotapes computer vision difference operator Smoothness

来源：评论

学校读者我要写书评

暂无评论

OSKDet: Orientation-sensitive Keypoint Localization for Rotated Object Detection

OSKDet: Orientation-sensitive Keypoint Localization for Rota...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lu, Dongchen Li, Dongmei Li, Yali Wang, Shengjin Tsinghua Univ Dept Elect Engn Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Rotated object detection is a challenging issue in computer vision field. Inadequate rotated representation and the confusion of parametric regression have been the bottleneck for high performance rotated detection. In this paper, we propose an orientation-sensitive keypoint based rotated detector OSKDet. First, we adopt a set of keypoints to represent the target and predict the keypoint heatmap on ROI to get the rotated box. By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results. Second, we explore a new unordered keypoint representation paradigm, which could avoid the confusion of keypoint regression caused by rule based ordering. Furthermore, we propose a localization quality uncertainty module to better predict the classification score by the distribution uncertainty of keypoints heatmap. Experimental results on several public benchmarks show the state-of-the-art performance of OSKDet. Specifically, we achieve an AP of 80.91% on DOTA, 89.98% on HRSC2016, 97.27% on UCAS-AOD, and a F-measure of 92.18% on ICDAR2015, 81.43% on ICDAR2017, respectively.

关键词： Location awareness Heating systems computer vision Uncertainty Shape Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

A Global Hypothesis Verification Framework for 3D Object recognition in Clutter

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1383-1396页

作者： Aldoma, Aitor Tombari, Federico Di Stefano, Luigi Vincze, Markus Vienna Univ Technol Grp ACIN Vision4Robot A-1060 Vienna Austria Univ Bologna CVLAB Grp DISI Bologna Italy

Pipelines to recognize 3D objects despite clutter and occlusions usually end up with a final verification stage whereby recognition hypotheses are validated or dismissed based on how well they explain sensor measurements. Unlike previous work, we propose a Global Hypothesis Verification (GHV) approach which regards all hypotheses jointly so as to account for mutual interactions. GHV provides a principled framework to tackle the complexity of our visual world by leveraging on a plurality of recognition paradigms and cues. Accordingly, we present a 3D object recognition pipeline deploying both global and local 3D features as well as shape and color. thereby, and facilitated by the robustness of the verification process, diverse object hypotheses can be gathered and weak hypotheses need not be suppressed too early to trade sensitivity for specificity. Experiments demonstrate the effectiveness of our proposal, which significantly improves over the state-of-art and attains ideal performance (no false negatives, no false positives) on three out of the six most relevant and challenging benchmark datasets.

关键词： 3D object recognition hypothesis verification correspondence grouping scene understanding

来源：评论

学校读者我要写书评

暂无评论

A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection 30

A Deep Regression Architecture with Two-Stage Re-initializat...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lv, Jiangjing Shao, Xiaohu Xing, Junliang Cheng, Cheng Zhou, Xi Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China

ISBN: (纸本)9781538604571

Regression based facial landmark detection methods usually learns a series of regression functions to update the landmark positions from an initial estimation. Most of existing approaches focus on learning effective mapping functions with robust image features to improve performance. the approach to dealing with the initialization issue, however, receives relatively fewer attentions. In this paper, we present a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem. At the global stage, given an image with a rough face detection result, the full face region is firstly re-initialized by a supervised spatial transformer network to a canonical shape state and then trained to regress a coarse landmark estimation. At the local stage, different face parts are further separately re-initialized to their own canonical shape states, followed by another regression subnetwork to get the final estimation. Our proposed deep architecture is trained from end to end and obtains promising results using different kinds of unstable initialization. It also achieves superior performances over many competing algorithms.

关键词： Face Shape computer architecture Robustness Detectors Machine 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：