检索结果-内蒙古大学图书馆

Fast Template Matching with Partial Skipping Using Sub-template

学校读者我要写书评

暂无评论

Fast Template Matching with Partial Skipping Using Sub-templ...

International Conference on Audio, Language and Image Processing

作者： Qiao Zhang Huijie Gao Zhen Kang State Key Lab. of Multi-spectral Information Processing Technology Institute for Pattern Recognition and Artificial Intelligence School of Mathematic & Computer Science Wuhan Polytechnic University

ISBN: (纸本)9781467301732

This paper presents a new fast template matching method with partial skipping using sub-template. In this method, we use sub-template to search point by point in the current searched window, and compare every SAD with threshold, if some SAD exceeds the threshold, set the new threshold equal to this SAD value and this point is one potential optimization location, when all points in the current window are compared, we will get a minimum value and a optimization location, then skip the other points whose SAD is not the minimum value. In other words, the searching step is that template size subtracts the sub-template size, and we set the next threshold equal to the current optimization SAD value, we update the threshold and the optimal point until the end of the searched image like this, then will find the global minimum points and its SAD value. Experimental results show that the proposed method is near one hundred times faster than the conventional template match method.

关键词： Computational efficiency Prediction algorithms Search problems Accuracy Correlation Signal processing algorithms pattern recognition

Robust Text Line Detection in Equipment Nameplate Images*

学校读者我要写书评

暂无评论

Robust Text Line Detection in Equipment Nameplate Images*

IEEE International Conference on Robotics and Biomimetics

作者： Jiangyu Lai Lanqing Guo Yu Qiao Xiaolong Chen Zhengfu Zhang Canping Liu Ying Li Bin Fu Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Scene text detection for equipment nameplates in the wild is important for equipment inspection robot since it enables inspection robot to take specific actions for different equipment's. Although text detection in images has achieved great progress in recent years, the detection for equipment nameplates faces several challenges such as extreme illumination and distortion which significantly decrease the detection performance. In this paper, we propose a deep text detection model Robust Text Line Detection (RTLD) for locating word level text instances in equipment cards. Specifically, the proposed model first employs a corner detection module to determine the four corner points of each nameplate, and then a carefully designed image transformed module transforms the irregular nameplate region into a rectangular region. Finally, text detection module is introduced to locate every word level text instance in the transformed images. We conduct extensive experiments to examine our proposed methods on real equipment nameplate images. Our model achieves 91 . 2% precision and 92 . 6% recall on Equipment Nameplate Dataset. The experimental results demonstrate the effectiveness of our models.

关键词：

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

Fast Texture Synthesis via Pseudo Optimizer

学校读者我要写书评

暂无评论

Fast Texture Synthesis via Pseudo Optimizer

Conference on computer vision and pattern recognition (CVPR)

作者： Wu Shi Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Texture synthesis using deep neural networks can generate high quality and diversified textures. However, it usually requires a heavy optimization process. The following works accelerate the process by using feed-forward networks, but at the cost of scalab.lity. diversity or quality. We propose a new efficient method that aims to simulate the optimization process while retains most of the properties. Our method takes a noise image and the gradients from a descriptor network as inputs, and synthesize a refined image with respect to the target image. The proposed method can synthesize images with better quality and diversity than the other fast synthesis methods do. Moreover, our method trained on a large scale dataset can generalize to synthesize unseen textures.

关键词： Neural networks Training Transforms Scalab.lity Optimization methods Convolution

Frame attention networks for facial expression recognition in videos

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Meng, Debin Peng, Xiaojiang Wang, Kai Qiao, Yu Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen China University of Chinese Academy of Sciences Beijing China

The video-based facial expression recognition aims to classify a given video into several basic emotions. How to integrate facial features of individual frames is crucial for this task. In this paper, we propose the Frame Attention Networks (FAN)1, to automatically highlight some discriminative frames in an end-to-end framework. The network takes a video with a variable number of face images as its input and produces a fixed-dimension representation. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors. The frame attention module learns multiple attention weights which are used to adaptively aggregate the feature vectors to form a single discriminative video representation. We conduct extensive experiments on CK+ and AFEW8.0 datasets. Our proposed FAN shows superior performance compared to other CNN based methods and achieves state-of-the-art performance on CK+. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Learning Attentive Pairwise Interaction for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhuang, Peiqin Wang, Yali Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%). Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be availab.e on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Enhanced quadratic video interpolation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Yihao Xie, Liangbin Siyao, Li Sun, Wenxiu 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 SenseTime Research

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge. Codes are availab.e at https://***/lyh-18/EQVI. Copyright © 2020, The Authors. All rights reserved.

关键词： Least squares approximations

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

Med-DANet V2: A Flexible Dynamic Architecture for Efficient ...

IEEE Workshop on Applications of computer vision (WACV)

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

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. Code will be availab.e at https://***/Rubics-Xuan/Med-DANet.

关键词：