检索结果-内蒙古大学图书馆

IEEE International Conference on multimedia and Expo Workshops (ICMEW)

作者： Katja Ludwig Moritz Einfalt Rainer Lienhart Multimedia Computing and Computer Vision Lab University of Augsburg

ISBN: (数字)9781728114859

ISBN: (纸本)9781728114866

This paper presents a model that robustly estimates important flight parameters for ski jumpers during their flight phase based on several camera views from the side along the jumpers' typical flight trajectories. A convolutional neural network for pose estimation, but also trained to detect skis, serves as a base model. It identifies 98.0% of the relevant flight parameters correctly within an angle threshold of 5 degrees, improving by 11.6% over previous work. In postprocessing, a pose checker first removes all wrong poses by using comparisons of distances and relative positions of the detected keypoints. A second step executes two RANSAC variants. One robustly estimates the average pose and another one the average pose angles. This model lifts the detection performance to 99.3% of the relevant flight parameters within a threshold of 5 degrees.

关键词： Cameras Computational modeling Hip Pose estimation Videos Principal component analysis Head

来源：评论

学校读者我要写书评

暂无评论

End-to-end, single-stream temporal action detection in untrimmed videos 28

End-to-end, single-stream temporal action detection in untri...

引用

28th British Machine vision Conference, BMVC 2017

作者： Buch, Shyamal Escorcia, Victor Ghanem, Bernard Fei-Fei, Li Niebles, Juan Carlos Stanford Vision and Learning Lab. Dept. of Computer Science Stanford University United States Image and Video Understanding Lab. Visual Computing Center KAUST Saudi Arabia

ISBN: (纸本)190172560X

In this work, we present a new intuitive, end-to-end approach for temporal action detection in untrimmed videos. We introduce our new architecture for Single-Stream Temporal Action Detection (SS-TAD), which effectively integrates joint action detection with its semantic sub-tasks in a single unifying end-to-end framework. We develop a method for training our deep recurrent architecture based on enforcing semantic constraints on intermediate modules that are gradually relaxed as learning progresses. We find that such a dynamic learning scheme enables SS-TAD to achieve higher overall detection performance, with fewer training epochs. By design, our single-pass network is very efficient and can operate at 701 frames per second, while simultaneously outperforming the state-of-the-art methods for temporal action detection on THUMOS’14. © 2017. The copyright of this document resides with its authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Addressing data bias problems for chest x-ray image report generation 30

Addressing data bias problems for chest x-ray image report g...

引用

30th British Machine vision Conference, BMVC 2019

作者： Harzig, Philipp Chen, Yan-Ying Chen, Francine Lienhart, Rainer Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg Germany FX Palo Alto Laboratory 3174 Porter Drive Palo AltoCA United States

Automatic medical report generation from chest X-ray images is one possibility for assisting doctors to reduce their workload. However, the different patterns and data distribution of normal and abnormal cases can bias machine learning models. Previous attempts did not focus on isolating the generation of the abnormal and normal sentences in order to increase the variability of generated paragraphs. To address this, we propose to separate abnormal and normal sentence generation by using a dual word LSTM in a hierarchical LSTM model. In addition, we conduct an analysis on the distinctiveness of generated sentences compared to the BLEU score, which increases when less distinct reports are generated. Together with this analysis, we propose a way of selecting a model that generates more distinctive sentences. We hope our findings will help to encourage the development of new metrics to better verify methods of automatic medical report generation. © 2019. The copyright of this document resides with its authors.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming

arXiv

引用

arXiv 2018年

作者： Einfalt, Moritz Zecha, Dan Lienhart, Rainer Multimedia Computing and Computer Vision Lab University of Augsburg Germany

In this paper we consider the problem of human pose estimation in real-world videos of swimmers. Swimming channels allow filming swimmers simultaneously above and below the water surface with a single stationary camera. These recordings can be used to quantitatively assess the athletes’ performance. The quantitative evaluation, so far, requires manual annotations of body parts in each video frame. We therefore apply the concept of CNNs in order to automatically infer the required pose information. Starting with an off-the-shelf architecture, we develop extensions to leverage activity information – in our case the swimming style of an athlete – and the continuous nature of the video recordings. Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos. With these additions we achieve reliable pose estimates with up to +16% more correct body joint detections compared to the baseline architecture. Copyright © 2018, 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

Fisher vector encoding of micro color features for (real world) jigsaw puzzles

Fisher vector encoding of micro color features for (real wor...

引用

International Conference on Document Analysis and Recognition

作者： Fabian Richter Christian Eggert Rainer Lienhart Multimedia Computing and Computer Vision Lab University of Augsburg Germany

In this work we propose a computationally efficient yet effective color encoding scheme for the purpose of jigsaw puzzle solving. Our contribution is twofold: (i) First of all, we show that a Fisher vector encoding gives superior performance over the commonly used compatibility descriptor of stacked color values. (ii) Furthermore, we show experimentally on synthetic and real-world data that our proposed color encoding is more robust in the presence of noise, as compared to three widely used features. Due to the robustness of our proposed descriptor we also anticipate its use to yield performance improvements in other applications, e.g., for the virtual reconstruction of hand-torn documents and archaeological findings.

关键词： Mixture models World Wide Web Silicon computers

来源：评论

学校读者我要写书评

暂无评论

Image retrieval by appearance 97

Image retrieval by appearance

引用

20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

作者： Ravela, S Manmatha, R Computer Vision Lab. Multimedia Indexing and Retrieval Group Center for Intelligent Information Retrieval University of Massachusetts at Amherst Multimedia Indexing and Retrieval Group Center for Intelligent Information Retrieval University of Massachusetts at Amherst

ISBN: (纸本)0897918363

A system to retrieve images using a syntactic description of appearance is presented. A multi-scale invariant vector representation is obtained by first filtering images in the database with Gaussian derivative filters at several scales and then computing low order differential invariants. The multi-scale representation is indexed for rapid retrieval. Queries are designed by the users from an example image by selecting appropriate regions. The invariant vectors corresponding to these regions are matched with those in the database both in feature space as well as in coordinate space and a match score is obtained for each image. The results are then displayed to the user sorted by the match score. From experiments conducted with over 1500 images it is shown that images similar in appearance and whose viewpoint is within 25 degrees of the query image can be retrieved with an average precision of 57%.

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

Methods and Applications for Distance Based ANN Training

Methods and Applications for Distance Based ANN Training

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Christoph Lassner Rainer Lienhart Multimedia Computing and Computer Vision Lab Augsburg University Augsburg Germany

ISBN: (纸本)9781479941551

Feature learning has the aim to take away the hassle of hand-designing features for machine learning tasks. Since the feature design process is tedious and requires a lot of experience, an automated solution is of great interest. However, an important problem in this field is that usually no objective values are availab.e to fit a feature learning function to. Artificial Neural Networks are a sufficiently flexible tool for function approximation to be able to avoid this problem. We show how the error function of an ANN can be modified such that it works solely with objective distances instead of objective values. We derive the adjusted rules for back propagation through networks with arbitrary depths and include practical considerations that must be taken into account to apply difference based learning successfully. On all three benchmark datasets we use, linear SVMs trained on automatically learned ANN features outperform RBF kernel SVMs trained on the raw data. This can be achieved in a feature space with up to only a tenth of dimensions of the number of original data dimensions. We conclude our work with two experiments on distance based ANN training in two further fields: data visualization and outlier detection.

关键词： Kernel Training Artificial neural networks Support vector machines Principal component analysis Data visualization

来源：评论

学校读者我要写书评

暂无评论

Saliency-guided selective magnification for company logo detection

Saliency-guided selective magnification for company logo det...

引用

International Conference on Pattern Recognition

作者： Christian Eggert Anton Winschel Dan Zecha Rainer Lienhart Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg Germany

ISBN: (纸本)9781509048489

Fast R-CNN is a well-known approach to object detection which is generally reported to be robust to scale changes. In this paper we examine the influence of scale within the detection pipeline in the case of company logo detection. We demonstrate that Fast R-CNN encounters problems when handling objects which are significantly smaller than the receptive field of the utilized network. In order to overcome these difficulties, we propose a saliency-guided multiscale approach that does not rely on building a full image pyramid. We use the feature representation computed by Fast R-CNN to directly classify large objects while at the same time predicting salient regions which contain small objects with high probability. Only selected regions are magnified and a new feature representation for these enlarged regions is calculated. Feature representations from both scales are used for classification, improving the detection quality of small objects while keeping the computational overhead low. Compared to a naive magnification strategy we are able to retain 79% of the performance gain while only spending 36% of the computation time.

关键词： Proposals Object detection Companies Feature extraction Neurons Support vector machines Neural networks

来源：评论

学校读者我要写书评

暂无评论

Extended Self-Critical Pipeline for Transforming Videos to Text (VTT Task 2021) – Team: MMCUniAugsburg

arXiv

引用

arXiv 2021年

作者： Harzig, Philipp Einfalt, Moritz Ludwig, Katja Lienhart, Rainer Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg Germany

The multimedia and computer vision lab.of the University of Augsburg participated in the VTT task only. We use the VATEX [1] and TRECVID-VTT [2] datasets for training our VTT models. We base our model on the Transformer [3] approach for both of our submitted runs, i.e., for run 2021-01 . For our second model (2021-02), we adapt the X-Linear Attention Networks for Image Captioning [4] which does not yield the desired bump in scores. For both models, we train on the complete VATEX dataset and 90% of the TRECVID-VTT dataset for pretraining while using the remaining 10% for validation. We finetune both models with self-critical sequence training [5], which boosts the validation performance significantly. Overall, we find that training a Video-to-Text system on traditional Image Captioning pipelines [6] delivers very poor performance. When switching to a Transformer-based architecture our results greatly improve and the generated captions match better with the corresponding video (see Figure 3). Copyright © 2021, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Investigating gesture typing for indirect touch

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2019年第3期3卷 1-22页

作者： Yang, Zhican Yu, Chun Yi, Xin Shi, Yuanchun Key Laboratory of Pervasive Computing Ministry of Education Beijing Key Lab. of Networked Multimedia Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100084 China

With the development of ubiquitous computing, entering text on HMDs and smart TVs using handheld touchscreen devices (e.g., smartphone and controller) is becoming more and more attractive. In these indirect touch scenarios, the touch input surface is decoupled from the visual display. Compared with direct touch input, entering text using a keyboard in indirect touch is more challenging because before the finger touch, no visual feedback is availab.e for locating the touch finger. Aiming at this problem, in this paper, we investigate the feasibility of gesture typing for indirect touch since keeping the finger in touch with the screen during typing makes it possible to provide continuous visual feedback, which is beneficial for increasing the input performance. We first examine users' gesture typing ability in terms of the appropriate keyboard size and location in motor space and then compare the typing performance in direct and indirect touch mode. We then propose an improved design to address the uncertainty and inaccuracy of the first touch. Our evaluation result shows that users can quickly acquire indirect gesture typing, and type 22.3 words per minute after 30 phases, which significantly outperforms previous numbers in literature. Our work provides the empirical support for leveraging gesture typing for indirect touch. © 2019 Association for computing Machinery.

关键词： Touch screens

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：