检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

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

Methods and Applications for Distance Based ANN Training

学校读者我要写书评

暂无评论

Methods and Applications for Distance Based ANN Training

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 available 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

Saliency-guided selective magnification for company logo detection

学校读者我要写书评

暂无评论

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

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

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

学校读者我要写书评

暂无评论

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

Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Harzig, Philipp Zecha, Dan Lienhart, Rainer Kaiser, Carolin Schallner, René Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg86159 Germany GfK Verein Nuremberg90419 Germany

Automatically generating descriptive captions for images is a well-researched area in computer vision. However, existing evaluation approaches focus on measuring the similarity between two sentences disregarding fine-grained semantics of the captions. In our setting of images depicting persons interacting with branded products, the subject, predicate, object and the name of the branded product are important evaluation criteria of the generated captions. Generating image captions with these constraints is a new challenge, which we tackle in this work. By simultaneously predicting integer-valued ratings that describe attributes of the human-product interaction, we optimize a deep neural network architecture in a multi-task learning setting, which considerably improves the caption quality. Furthermore, we introduce a novel metric that allows us to assess whether the generated captions meet our requirements (i.e., subject, predicate, object, and product name) and describe a series of experiments on caption quality and how to address annotator disagreements for the image ratings with an approach called soft targets. We also show that our novel clause-focused metrics are also applicable to other image captioning datasets, such as the popular MSCOCO dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Integer programming

Multimodal image captioning for marketing analysis

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Harzig, Philipp Brehm, Stephan Lienhart, Rainer Kaiser, Carolin Schallner, René Multimedia Computing and Computer Vision Lab University of Augsburg Augsburg86159 Germany GfK Verein Nuremberg90419 Germany

Automatically captioning images with natural language sentences is an important research topic. State of the art models are able to produce human-like sentences. These models typically describe the depicted scene as a whole and do not target specific objects of interest or emotional relationships between these objects in the image. However, marketing companies require to describe these important attributes of a given scene. In our case, objects of interest are consumer goods, which are usually identifiable by a product logo and are associated with certain brands. From a marketing point of view, it is desirable to also evaluate the emotional context of a trademarked product, i.e., whether it appears in a positive or a negative *** address the problem of finding brands in images and deriving corresponding captions by introducing a modified image captioning network. We also add a third output modality, which simultaneously produces real-valued image ratings. Our network is trained using a classificationaware loss function in order to stimulate the generation of sentences with an emphasis on words identifying the brand of a product. We evaluate our model on a dataset of images depicting interactions between humans and branded products. The introduced network improves mean class accuracy by 24.5 percent. Thanks to adding the third output modality, it also considerably improves the quality of generated captions for images depicting branded products. Copyright © 2018, The Authors. All rights reserved.

关键词： Image enhancement

Addressing data bias problems for chest X-ray image report generation

学校读者我要写书评

暂无评论

arXiv 2019年

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. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

Active Learning for Efficient Sampling of Control Models of Collectives

学校读者我要写书评

暂无评论

Active Learning for Efficient Sampling of Control Models of ...

International Conference on Self-Adaptive and Self-Organizing Systems (SASO)

作者： Alexander Schiendorfer Christoph Lassner Gerrit Anders Wolfgang Reif Rainer Lienhart Institute for Software & Systems Engineering University of Augsburg Germany Perceiving Systems Department Max Planck Institute for Intelligent Systems Germany Multimedia Computing and Computer Vision Lab University of Augsburg Germany

Many large-scale systems benefit from an organizational structure to provide for problem decomposition. A pivotal problem solving setting is given by hierarchical control systems familiar from hierarchical task networks. If these structures can be modified autonomously by, e.g., Coalition formation and reconfiguration, adequate decisions on higher levels require a faithful abstracted model of a collective of agents. An illustrative example is found in calculating schedules for a set of power plants organized in a hierarchy of Autonomous Virtual Power Plants. Functional dependencies over the combinatorial domain, such as the joint costs or rates of change of power production, are approximated by repeatedly sampling input-output pairs and substituting the actual functions by piecewise linear functions. However, if the sampled data points are weakly informative, the resulting abstracted high-level optimization introduces severe errors. Furthermore, obtaining additional point labels amounts to solving computationally hard optimization problems. Building on prior work, we propose to apply techniques from active learning to maximize the information gained by each additional point. Our results show that significantly better allocations in terms of cost-efficiency (up to 33.7 % reduction in costs in our case study) can be found with fewer but carefully selected sampling points using Decision Forests.

关键词： Power generation Production Cost function Schedules Robots Switches