Pixel-wise image segmentation is a highly demanding task in medical image analysis. In practice, it is difficult to find annotated medical images with corresponding segmentation masks. In this paper, we present  Kvasir-SEG: an open-access dataset of gastrointestinal polyp images and corresponding segmentation masks, manually annotated and verified by an experienced gastroenterologist. We demonstrate the use of our dataset with a traditional segmentation approach and a modern deep learning based CNN approach. This work will be valuable for researchers to reproduce results and compare their methods in the future. By adding segmentation masks to the Kvasir dataset, which until today only consisted of framewise annotations, we enable multimedia and computer vision researchers to contribute in the field of polyp segmentation and automatic analysis of colonoscopy videos.  

Segmentation of findings in the gastrointestinal tract is a challenging but also an important task which is an important building stone for sufficient automatic decision support systems. In this work, we present our solution for the Medico 2020 task, which focused on the problem of colon polyp segmentation. We present our simple but efficient idea of using an augmentation method that uses grids in a pyramid-like manner (large to small) for segmentation. Our results show that the proposed methods work as indented and can also lead to comparable results when competing with other methods.

Recent technological advances are adapted in sports to improve performance, avoid injuries, and make advantageous decisions. In this paper, we describe our ongoing efforts to develop and deploy PMSys, our smartphone-based athlete monitoring and reporting system. We describe our first attempts to gain insight into some of the data we have collected. Experiences so far are promising, both on the technical side and for athlete performance development. Our initial application of artificial-intelligence methods for prediction is encouraging and indicative.

The BioMedia 2019 ACM Multimedia Grand Challenge is the first in a series of competitions focusing on the use of multimedia for different medical use-cases. In this year’s challenge, the participants are asked to develop efficient algorithms which automatically detect a variety of findings commonly identified in the gastrointestinal (GI) tract (a part of the human digestive system). The purpose of this task is to develop methods to aid medical doctors performing routine endoscopy inspections of the GI tract. In this paper, we give a detailed description of the four different tasks of this year’s challenge, present the datasets used for training and testing, and discuss how each submission is evaluated both qualitatively and quantitatively.

In this paper, we present a two-step deep learning method that is used to predict sperm motility and morphology based on video recordings of human spermatozoa. First, we use an autoencoder to extract temporal features from a given semen video and plot these into image-space, which we call feature-images. Second, these feature-images are used to perform transfer learning to predict the motility and morphology values of human sperm. The presented method shows it's capability to extract temporal information into spatial domain feature-images which can be used with traditional convolutional neural networks. Furthermore, the accuracy of the predicted motility of a given semen sample shows that a deep learning-based model can capture the temporal information of microscopic recordings of human semen.

Deep learning using neural networks is becoming more and more popular. It is frequently used in areas like video analysis, image retrieval, traffic forecast and speech recognition. In this respect, the learning and training process usually requires a lot of data. However, in many areas, data is scarce which is definitely the case in our medical application scenario, i.e., polyp detection in the gastrointestinal tract. Here, colorectal cancer is on the list of most common cancer types, and often, the cancer arises from benign, adenomatous polyps containing dysplastic cells. Detection and removal of polyps can therefore prevent the development of cancer. Due to high cost, time consumption, patient discomfort and in-accuracy of existing procedures, researchers have started to explore systems for automatic polyp detection to assist and automate current examination procedures. Following the current gained traction for neural networks, and the typical lack of medical data, we explore how data enhancements affect the training and evaluation of the networks in terms of polyp detection accuracy and particularly if it can be used to increase the detection rate. We also experiment with how various training techniques can be used to increase performance. Our experimental results show how data enhancement and training optimization can be used to increase different aspects of the performance, but we also point out mechanisms that have no and even a negative effect.

Accurate computer-aided polyp detection and segmentation during colonoscopy examinations can help endoscopists resect abnormal tissue and thereby decrease chances of polyps growing into cancer. Towards developing a fully automated model for pixel-wise polyp segmentation, we propose ResUNet++, which is an improved ResUNet architecture for colonoscopic image segmentation. Our experimental evaluations show that the suggested architecture produces good segmentation results on publicly available datasets. Furthermore, ResUNet++ significantly outperforms U-Net and ResUNet, two key state-of-the-art deep learning architectures, by achieving high evaluation scores with a dice coefficient of 81.33%, and a mean Intersection over Union (mIoU) of 79.27% for the Kvasir-SEG dataset and a dice coefficient of 79.55%, and a mIoU of 79.62% with CVC-612 dataset.

We are today overwhelmed with information, of which an important part is news. Sports news, in particular, has become very popular, where soccer makes up a big part of this coverage. For sports fans, it can be a time consuming and tedious to keep up with the news that they really care about. In this paper, we present different machine learning methods applied to soccer news from a Norwegian newspaper and a TV station's news site to summarize the content in a short and digestible manner. We present a system to collect, index, label, analyze, and present the collected news articles based on the content. We perform a thorough comparison between deep learning and traditional machine learning algorithms on text classification. Furthermore, we present a dataset of soccer news which was collected from two different Norwegian news sites and shared online.

That video and computer games have reached the masses is a well known fact. Furthermore, game streaming and watching other people play video games is another phenomenon that has outgrown its small beginning by far, and game streams, be it live or recorded, are today viewed by millions. E-sports is the result of organized leagues and tournaments in which players can compete in controlled environments and viewers can experience the matches, discuss and criticize, just like in physical sports.  However, as traditional sports, e-sports matches may be long and contain less interesting parts, introducing the challenge of producing well directed summaries and highlights. In this paper, we describe our efforts to approach the game streaming and e-sports phenomena from a multimedia research point of view. We focus on the challenge of summarizing matches from specific relevant game, Counter-Strike: Global Offensive (CS:GO). We survey related work, describe the rules and structure of the game and identify the main challenges for summarizing e-sports matches. With this contribution, we aim to foster multimedia research in the area of e-sports and game streaming.

In this paper, we present the approach of team Jmag to solve this year's Medico Multimedia Task as part of the MediaEval 2019 Benchmark. This year, the task focuses on automatically determining quality characteristics of human sperm through the analysis of microscopic videos of human semen and associated patient data. Our approach is based on deep convolutional neural networks (CNNs) of varying sizes and dimensions. Here, we aim to analyze both the spatial and temporal information present in the videos. The results show that the method holds promise for predicting the motility of sperm, but predicting morphology appears to be more difficult.

360 panorama video displayed through Virtual reality (VR) glasses or large screens o®ers immersive user experiences, but as such technology becomes commonplace, the need for e±cient streaming methods of such high-bitrate videos arises. In this respect, the attention that 360panorama video has received lately is huge. Many methods have already been proposed, and in this paper, we shed more light on the di®erent trade-o®s in order to save bandwidth while preserving the video quality in the user's ̄eld-of-view (FoV). Using 360 VR content delivered to a Gear VR head-mounted display with a Samsung Galaxy S7 and to a Huawei Q22 set-top- box, we have tested various tiling schemes analyzing the tile layout, the tiling and encoding overheads, mechanisms for faster quality switching beyond the DASH segment boundaries and quality selection con ̄gurations. In this paper, we present an e±cient end-to-end design and real-world implementation of such a 360 streaming system. Furthermore, in addition to researching an on-demand system, we also go beyond the existing on-demand solutions and present a live streaming system which strikes a trade-o® between bandwidth usage and the video quality in the user's FoV. We have created an architecture that combines RTP and DASH, and our system multiplexes a single HEVC hardware decoder to provide faster quality switching than at the traditional GOP boundaries. We demonstrate the performance and illustrate the trade-o®s through real-world experiments where we can report comparable bandwidth savings to existing on-demand approaches, but with faster quality switches when the FoV changes.

Methods for automatic analysis of clinical data are usually targeted towards a specific modality and do not make use of all relevant data available. In the field of male human reproduction, clinical and biological data
are not used to its fullest potential. Manual evaluation of a semen sample using a microscope is time-consuming and requires extensive training. Furthermore, the validity of manual semen analysis has been questioned due to limited reproducibility, and often high inter-personnel variation. The existing computer-aided sperm analyzer systems are not recommended for routine clinical use due to methodological challenges caused by the consistency of the semen sample. Thus, there is a need for an improved methodology.
We use modern and classical machine learning techniques together with a dataset consisting of 85 videos of human semen samples and related participant data to automatically predict sperm motility. Used techniques include simple linear regression and more sophisticated methods using convolutional neural networks. Our results indicate that sperm motility prediction based on deep learning using sperm motility videos is rapid to perform and consistent. The algorithms performed worse when participant data was added. In conclusion, machine learning-based automatic analysis may become a valuable tool in male infertility investigation and research.

This paper presents the method proposed by team UTAOS for MediaEval 2018 Multimedia Satellite Task: Emergency Response for Flooding Events. In the first challenge, we mainly rely on object and scene level features extracted through multiple deep models pre-trained on the ImageNet and Places datasets. The object and scene-level features are combined using early, late and double fusion techniques achieving an average F1-score of 65.03%, 60.59% and 63.58%, respectively. For the second challenge, we rely on a convolutional neural networks (CNNs) and a transfer learning-based classification approach achieving an average F1-score of 62.30% and 61.02% for run 1 and run 2, respectively.

With 360◦ panorama video technology becoming commonplace, the need for efficient streaming methods for such videos arises. We go beyond the existing on-demand solutions and present a live streaming system which strikes a trade-off between bandwidth usage and the video quality in the user’s field-of-view. We have created an architecture that combines RTP and DASH to deliver 360◦ VR content to a Huawei set-top-box and a Samsung Galaxy S7. Our system multiplexes a single HEVC hardware decoder to provide faster quality switching than at the traditional GOP boundaries. We demonstrate the performance and illustrate the trade-offs through real-world experiments where we can report comparable bandwidth savings to existing on-demand approaches, but with faster quality switches when the field-of- view changes. 

That video games have reached the masses is well known. Moreover, game streaming and watching other people play video games is a phenomenon that has outgrown its small beginnings. Game video streams, be it live or recorded, are viewed by millions. E-sports is the result of organized leagues and tournaments in which players can compete in controlled environments and viewers can experience the matches, discuss and criticize, just like in physical sports. In the GameStory task, taking place the first time in 2018, we approach the game streaming and e-sports phenomena from a multimedia research side. We focus on the task of summarizing matches using a specific relevant game, Counter-Strike: Global Offensive, as a case study. With the help of ZNIPE.tv, we provide a data set of high quality data and meta data from competitive tournaments and aim to foster research in the area of e-sports and game streaming.

This paper describes the approach of the organizers' team for a submission to the GameStory task at MediaEval 2018. Goal of the task is to provide a summary of a  match of Counter Strike: Global Offensive (CS:GO), a popular e-sports game, that boils down a long game to it's most important events and delivers a story on the progress of the match. Our approach was to provide match statistics and overlay them with events and highlights of the game. We focused on ends of critical rounds, i.e. the rounds where one team took the lead over the other one, and kill streaks, where one player eliminated a substantial number of other players in short time. 

Multimedia research is becoming more and more important for the medical domain, where an increasing number of videos and images are integrated in the daily routine of surgical and diagnostic work. While the collection of medical multimedia data is not an issue, appropriate tools for efficient use of this data are missing. This includes management and inspection of the data, visual analytics, as well as learning relevant semantics and using recognition results for optimizing surgical and diagnostic processes. The characteristics and requirements in this interesting but challenging field are different than the ones in classic multimedia domains. Therefore, this tutorial gives a general introduction to the field, provides a broad overview of specific requirements and challenges, discusses existing work and open challenges, and elaborates in detail how machine learning approaches can help in multimedia-related fields to improve the performance of surgeons/clinicians.

The interest in neural networks has increased sig- nificantly, and the application of this type of machine learning is vast, ranging from natural image classification to medical image segmentation. However, many users of neural networks tend to use them as a black box tool. They do not access all of the possible variations, nor take into account the respective classification accuracies and costs. In our work, we focus on multiclass image classification, and in this research, we shed light on the trade-offs between systems using a single multiclass classification and multiple binary classifiers, respectively. We have tested the these classifiers on several modern neural network architectures, including DenseNet, Inception v3, Inception ResNet v2, Xception, NASNet and MobileNet. We have compared several aspects of the performance of these architectures during training and testing using both classification styles. We have compared classification speed and several classification accuracy metrics. Here, we present the results from experiments on a total of 99 networks: 11 multiclass and 88 individual binary networks, for an 8-class classification of medical images. In short, using multiple binary classification networks resulted in a 7% increase in the average F1 score, a 1% increase in average accuracy, a 1% increase in precision, and a 4% increase in average recall. However, on average, such a multi-network style performed the classification 7.6 times slower compared to a single network multiclass implementation. These collective findings show that both approaches can be applied to modern neural network structures. Several binary networks will often give increased classification accuracy, but at the cost of classification speed and resource consumption.