检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Xiang Wang Shiwei Zhang Zhiwu Qing Yuanjie Shao Zhengrong Zuo Changxin Gao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

ISBN: (纸本)9781665428132

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global inter-actions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR.

关键词： Training Visualization Recurrent neural networks Streaming media Transformers Encoding Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

A pushing-grasping collaborative method based on deep q-network algorithm in dual perspectives

arXiv

引用

arXiv 2021年

作者： Gang, Peng Jinhu, Liao Shangbin, Guan Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can’t recognize objects accurately in cluster scenes from a single perspective and the manipulators can’t make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q-network algorithm, with an RGB-D camera to obtain the information of objects’ RGB images and point cloud from two perspectives, and combines the pushing and grasping actions, so that the trained manipulator can make the scenes better for grasping, so that it can perform well in more complicated grasping scenes. What’s more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it drew a conclusion that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Text-based Person Re-Identification

Weakly Supervised Text-based Person Re-Identification

引用

International Conference on Computer Vision (ICCV)

作者： Shizhen Zhao Changxin Gao Yuanjie Shao Wei-Shi Zheng Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Sun Yat-sen University

ISBN: (纸本)9781665428132

The conventional text-based person re-identification methods heavily rely on identity annotations. However, this labeling process is costly and time-consuming. In this paper, we consider a more practical setting called weakly supervised text-based person re-identification, where only the text-image pairs are available without the requirement of annotating identities during the training phase. To this end, we propose a Cross-Modal Mutual Training (CMMT) framework. Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances. To further re-fine the clustering results, CMMT provides a Mutual Pseudo Label Refinement module, which leverages the clustering results in one modality to refine that in the other modality constrained by the text-image pairwise relationship. Mean-while, CMMT introduces a Text-IoU Guided Cross-Modal Projection Matching loss to resolve the cross-modal matching ambiguity problem. A Text-IoU Guided Hard Sample Mining method is also proposed for learning discriminative textual-visual joint embeddings. We conduct extensive experiments to demonstrate the effectiveness of the proposed CMMT, and the results show that CMMT performs favorably against existing text-based person re-identification methods. Our code will be available at https://***/X-BrainLab/WS_Text-ReID.

关键词： Training Visualization Computer vision Codes Annotations Computational modeling Clustering methods

来源：评论

学校读者我要写书评

暂无评论

BoostTree and BoostForest for Ensemble Learning

Research Square

引用

Research Square 2021年

作者： Zhao, Changming Wu, Dongrui Huang, Jian Yuan, Ye Zhang, Hai-Tao Peng, Ruimin Shi, Zhenhua Guo, Chenfeng Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This article proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It achieves high randomness (diversity) by sampling its parameters randomly from a parameter pool, and selecting a subset of features randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 34 classification and regression datasets. Remarkably, BoostForest has only one hyper-parameter (the number of BoostTrees), which can be easily specified. Our code is publicly available, and the proposed ensemble learning framework can also be used to combine many other base learners. © 2021, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Exploring Stronger Feature for Temporal Action Localization

arXiv

引用

arXiv 2021年

作者： Qing, Zhiwu Wang, Xiang Huang, Ziyuan Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection performance. In this technical report, we explored classic convolution-based backbones and the recent surge of transformer-based backbones. We found that the transformer-based methods can achieve better classification performance than convolution-based, but they cannot generate accuracy action proposals. In addition, extracting features with larger frame resolution to reduce the loss of spatial information can also effectively improve the performance of temporal action localization. Finally, we achieve 42.42% in terms of mAP on validation set with a single SlowFast [9] feature by a simple combination: BMN [16]+TCANet [19], which is 1.87% higher than the result of 2020 [20]’s multi-model ensemble. Finally, we achieve Rank 1st on the CVPR2021 HACS supervised Temporal Action Localization Challenge. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Active Learning for Simultaneous Emotion Classification and Regression

Multi-Task Active Learning for Simultaneous Emotion Classifi...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xue Jiang Lubin Meng Dongrui Wu Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665442084

Emotion recognition, which aims to identify an individual’s emotional state from the acquired physiological or body signals, is very important in affective computing. Emotions have two common representations: categorical, e.g., happy, sad, etc., and dimensional (continuous), e.g., valence, arousal and dominance. Training a good emotion classification or regression model usually requires a large number of labeled data. However, the labeling process is very difficult. As emotions are subtle and uncertain, it usually requires multiple assessors to label each emotional instance to obtain the groundtruth categorical label or dimensional values. In this paper, we propose a multi-task active learning (MTAL) framework to query the most useful samples for labeling, which enables the efficient training of an emotion classification model and multiple emotion regression models simultaneously. This is novel and challenging, as all previous research considered only emotion classification or regression alone, but not simultaneously. Experimental results on the IEMOCAP dataset demonstrated that MTAL outperformed random selection and several state-of-the-art single task active learning approaches, i.e., with the same number of labeled samples, MTAL can obtain better emotion classification and regression models simultaneously.

关键词： Training Emotion recognition Conferences Multitasking Physiology Data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Construction of Three-Dimensional Nickel-Vanadium Hydrotalcite with Ball-Flower Architecture for Screen-Printed Asymmetric Supercapacitor

SSRN

引用

SSRN 2022年

作者： Tu, Qian Zhang, Qiang Sun, Xinyu Wang, Jinglu Lin, Baoying Liu, Jin Liu, Zhonghua Chen, Liangzhe School of Electronic Information Engineering Jingchu University of Technology Jingmen448000 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Wuhan430074 China

As a promising energy storage matter, two-dimensional (2D) layered double hydroxides (LDHs) suffer from a lower specific capacitance and poor retention. Morphology engineering is deemed to be an effective means. Herein, three-dimensional (3D) nickel-vanadium hydrotalcite (NiV-LDHs) with ball-flower structure are synthesized successfully via a facile dynamic-refluxing route, such a green strategy dispenses with template and high pressure and generates a specific surface area as high as 61.6 m 2 /g. Then, the screen-printed inks with outstanding rheological performances are formulated and the resulting electrodes display superior hydrophilic performance. Benefitted from the 3D architecture and shear flow process, the NiV-LDHs electrode can deliver an enhanced specific capacitance of 1069 F/g at 1 A/g with cycling stability of ~68.0% after 1500 cycles at 20 A/g, in contrast with that of NiV-LDHs prepared by coprecipitation (848 F/g and ~5.1%). Furthermore, an asymmetric NiV-LDHs//activated carbon supercapacitor (ASC) is assembled, which can yield a remarkable energy density of 75.8 μWh/cm2 at a power density of 0.80 mW/cm2, and two ASCs in series can illuminate a red light (2.5 V) for more than 270 s. Therefore, this study proposes a facile and economic strategy to prepare 3D nanomaterial for advanced and flexible printable energy storage devices. © 2022, The Authors. All rights reserved.

关键词： Screen printing

来源：评论

学校读者我要写书评

暂无评论

Proposal relation network for temporal action detection

arXiv

引用

arXiv 2021年

作者： Wang, Xiang Qing, Zhiwu Huang, Ziyuan Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The crucial challenge of the task comes from that the temporal duration of action varies dramatically, and the target actions are typically embedded in a background of irrelevant activities. Our solution builds on BMN [10], and mainly contains three steps: 1) action classification and feature encoding by Slowfast [6], CSN [13] and ViViT [1];2) proposal generation. We improve BMN by embedding the proposed Proposal Relation Network (PRN), by which we can generate proposals of high quality;3) action detection. We calculate the detection results by assigning the proposals with corresponding classification results. Finally, we ensemble the results under different settings and achieve 44.7% on the test set, which improves the champion result in ActivityNet 2020 [17] by 1.9% in terms of average mAP. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fast Candidate Region Extraction for SAR Ship Target

Fast Candidate Region Extraction for SAR Ship Target

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Panpan Zhang Haibo Luo Zheng Xu Miao He Shenyang Institute of Automation Shenyang China Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Shenyang China The Key Lab of Image Understanding and Computer Vision Shenyang China

ISBN: (纸本)9781665465373

At present, deep learning technology is widely used in ship target detection in synthetic aperture radar (SAR) images. However, high-resolution remote sensing SAR images cover a larger area and have larger image sizes. To be able to use the deep learning model for training and testing, the image needs to be cropped to the appropriate size. In a high-resolution SAR ship image, the ship target usually takes only a small part of the whole image. As a result, only part of the cropped image contains the target, and most of the rest are background regions. This will cause a lot of computational redundancy in the model inference stage. To solve this problem, a fast candidate region extraction algorithm is proposed in this paper for ship target extraction. The algorithm consists of three parts: firstly, extract the saliency map of the SAR ship image, secondly, perform median filtering on the segmented image, and thirdly, extract candidate regions. The superiority of the algorithm was demonstrated by experiments on the AIR-SARShip-1.0 dataset.

关键词： Deep learning Training Redundancy Radar polarimetry Inference algorithms Indexes Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

TransView: Inside, Outside, and Across the Cropping View Boundaries

TransView: Inside, Outside, and Across the Cropping View Bou...

引用

International Conference on Computer Vision (ICCV)

作者： Zhiyu Pan Zhiguo Cao Kewei Wang Hao Lu Weicai Zhong Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Huawei CBG

ISBN: (纸本)9781665428132

We show that relation modeling between visual elements matters in cropping view recommendation. Cropping view recommendation addresses the problem of image recomposition conditioned on the composition quality and the ranking of views (cropped sub-regions). This task is challenging because the visual difference is subtle when a visual element is reserved or removed. Existing methods represent visual elements by extracting region-based convolutional features inside and outside the cropping view boundaries, without probing a fundamental question: why some visual elements are of interest or of discard? In this work, we observe that the relation between different visual elements significantly affects their relative positions to the desired cropping view, and such relation can be characterized by the attraction inside/outside the cropping view boundaries and the repulsion across the boundaries. By instantiating a transformer-based solution that represents visual elements as visual words and that models the dependencies between visual words, we report not only state-of-the-art performance on public benchmarks, but also interesting visualizations that depict the attraction and repulsion between visual elements, which may shed light on what makes for effective cropping view recommendation.

关键词： Visualization Computer vision Computational modeling Benchmark testing Feature extraction Transformers Decoding

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：