Cow lameness is a severe condition that affects the life cycle and life quality of dairy cows and results in considerable economic losses. Early lameness detection helps farmers address illnesses early and avoid negative effects caused by the degeneration of cows' condition. We collected a dataset of short clips of cows passing through a hallway exiting a milking station and annotated the degree of lameness of the cows. This paper explores the resulting dataset and provides a detailed description of the data collection process. Additionally, we proposed a lameness detection method that leverages pre-trained neural networks to extract discriminative features from videos and assign a binary score to each cow indicating its condition: "healthy" or "lame." We improve this approach by forcing the model to focus on the structure of the cow, which we achieve by substituting the RGB videos with binary segmentation masks predicted with a trained segmentation model. This work aims to encourage research and provide insights into the applicability of computer vision models for cow lameness detection on farms.

A study to based on a large childrens health dataset that is complete in terms of quality and quantityA comparison of machine learning methods using structured and unstruc-tured data for this task,...

This paper investigates methods for user and pseudo relevance feedback in video event retrieval. Existing feedback methods achieve strong performance but adjust the ranking based on few individual examples. We propose a relevance feedback algorithm (ARF) derived from the Rocchio method, which is a theoretically founded algorithm in textual retrieval. ARF updates the weights in the ranking function based on the centroids of the relevant and non-relevant examples. Additionally, relevance feedback algorithms are often only evaluated by a single feedback mode (user feedback or pseudo feedback). Hence, a minor contribution of this paper is to evaluate feedback algorithms using a larger number of feedback modes. Our experiments use TRECVID Multimedia Event Detection collections. We show that ARF performs significantly better in terms of Mean Average Precision, robustness, subjective user evaluation, and run time compared to the state-of-the-art.

Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the results for general (e.g., future, unknown) users. In practice however, most evaluation scenarios only allow us to conclusively determine the relevance towards the particular assessor that provided the judgments. A factor that cannot be ignored when extending conclusions made from assessors towards users, is the possible disagreement on relevance, assuming that a single gold truth label does not exist. This paper presents and analyzes the predicted relevance model (PRM), which allows predicting a particular result's relevance for a random user, based on an observed assessment and knowledge on the average disagreement between assessors. With the PRM, existing evaluation metrics designed to measure binary assessor relevance, can be transformed into more robust and effectively graded measures that evaluate relevance towards a random user. It also leads to a principled way of quantifying multiple graded or categorical relevance levels for use as gains in established graded relevance measures, such as normalized discounted cumulative gain, which nowadays often use heuristic and data-independent gain values. Given a set of test topics with graded relevance judgments, the PRM allows evaluating systems on different scenarios, such as their capability of retrieving top results, or how well they are able to filter out non-relevant ones. Its use in actual evaluation scenarios is illustrated on several information retrieval test collections.

Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called 'video hyperlinking'), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multi-modality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.

This document describes the two-stage approach in Big Data training developed at Statistics Netherlands. The first stage is following a Masterclass on Big Data. This class provides the theoretical basis and consists of a one-day set of lectures on big data-related topics. The second stage is a DataCamp which enables participants a 'hands on' expertise through five days of practical work. This ensures a 'learning-by-doing' approach which is considered essential for Big Data training. Both stages and the results obtained in the 2015 DataCamp are included in this document.

Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking George Awad, Jonathan Fiscus, David Joy, Martial Michel, Alan Smeaton, Wessel Kraaij, Maria Eskevich, Robin Aly, Roeland Ordelman, Marc Ritter, et al.

Individual tasks carried out within benchmarking initiatives, or campaigns, enable direct comparison of alternative approaches to tackling shared research challenges and ideally promote new research ideas and foster communities of researchers interested in common or related scientific topics. When a task has a clear predefined use case, it might straightforwardly adopt a well established framework and methodology. For example, an ad hoc information retrieval task adopting the standard Cranfield paradigm. On the other hand, in cases of new and emerging tasks which pose more complex challenges in terms of use scenarios or dataset design, the development of a new task is far from a straightforward process. This letter summarises our reections on our experiences as task organisers of the Search and Hyperlinking task from its origins as a Brave New Task at the MediaEval benchmarking campaign (2011-2014) to its current instantiation as a task at the NIST TRECVid benchmark (since 2015). We highlight the challenges encountered in the development of the task over a number of annual iterations, the solutions found so far, and our process for maintaining a vision for the ongoing advancement of the task's ambition.

This paper overviews ongoing work that aims to support end-users in conveniently exploring and exploiting large audiovisual archives by deploying multiple multimodal linking approaches. We present ongoing work on multimodal video hyperlinking, from a perspective of unconstrained link anchor identification and based on the identification of named entities, and recent attempts to implement and validate the concept of outside-in linking that relates current events to archive content. Although these concepts are not new, current work is revealing novel insights, more mature technology, development of benchmark evaluations and emergence of dedicated workshops which are opening many interesting research questions on various levels that require closer collaboration between research communities.

The Search and Anchoring in Video Archives (SAVA) task at MediaEval 2015 consists of two sub-tasks: (i) search for multimedia content within a video archive using multimodal queries referring to information contained in the audio and visual streams/content, and (ii) automatic selection of video segments within a list of videos that can be used as anchors for further hyperlinking within the archive. The task used a collection of roughly 2700 hours of the BBC broadcast TV material for the former sub-task, and about 70 les taken from this collection for the latter sub-task. The search sub-task is based on an ad-hoc retrieval scenario, and is evaluated using a pooling procedure across participants submissions with crowdsourcing relevance assessment using Amazon Mechanical Turk (MTurk). The evaluation used metrics that are variations of MAP adjusted for this task. For the anchor selection sub-task overlapping regions of interest across participants submissions were assessed using MTurk workers, and mean reciprocal rank (MRR), precision and recall were calculated for evaluation.

Multimedia hyperlinking is an emerging research topic in the context of digital libraries and (cultural heritage) archives. We have been studying the concept of video-to-video hyperlinking from a video search perspective in the context of the MediaEval evaluation benchmark for several years. Our task considers a use case of exploring large quantities of video content via an automatically created hyperlink structure at the media fragment level. In this paper we report on our findings, examine the features of the definition of video hyperlinking based on results, and discuss lessons learned with respect to evaluation of hyperlinking in real-life use scenarios.

Today, the over $2 trillion US healthcare system is ravaged by fraud, waste, and abuse, with an estimated one-third of all these costs frivolously spent in such ways. Sun Tzu wrote, “Every battle is won or lost before it's ever fought.” To combat healthcare fraud, we must understand it and the forms it takes. In this paper, we systematically evaluate published literature using Webster and Watson's concept matrix technique. From the applicable published literature, we provide a categorization and description of the documented types of fraud in healthcare.

We present the Predicted Relevance Model (PRM): it allows moving from binary evaluation measures that reflect a single assessor’s judgments, towards graded measures that represent the relevance towards random users.

Approaches to multimedia search often evolve from existing approaches with strong average precision. However, work on search evaluation shows that average precision does not always capture effectiveness in terms of satisfying user needs because it ignores the diversity of search results. This paper investigates whether search approaches with diverse results have been neglected within the multimedia retrieval research agenda due the fact that they are overshadowed by search approaches with strong average precision. To this end, we compare 361 search approaches applied on the TrecVid benchmarks between 2005 and 2007. We motivate two criteria based on measure correlation and statistical equivalence to estimate whether search approaches with diverse results have been neglected. We show that hypothesized effect indeed occurs in the above examined collections. As a consequence, the research community would benefit from reconsidering existing approaches in the light of diversity.

State-of-the-art score normalization methods use generative models that rely on sometimes unrealistic assumptions. We propose a novel parameter estimation method for score normalization based on logistic regression, using the expected parameters from past queries. Experiments on the Gov2 and CluewebA collection indicate that our method is consistently more precise in predicting the number of relevant documents in the top-n ranks compared to a state-of-the-art generative approach and another parameter estimate for logistic regression.

Semantic linking has a potential to enrich the audiovisual experience for users of television or radio broadcast archives. Recently, automatic semantic linking, has received increased attention, especially as second screen applications for television broadcasts are emerging. Semantic linking for radio broadcasts can enrich radio listening experience in a similar manner in combination with second screen-like applications. While the development of such applications is gaining popularity, little is known about the information in a radio program that may be interesting for link creation from a user perspective. We conducted a user study on semantic linking for radio broadcasts in order to know what information users regard as suitable anchors and what kind of information they like as targets. We found that users often regard topic and person as the best link anchors in the program. Additionally, we found that frequency and timing of information elements in a radio program do not dominate the users' selection of anchors. Furthermore, we found that there is a low agreement among users on regarding certain information elements as anchors. For practical reasons the study is conducted with 10 minutes of radio broadcast material of a particular program type, and with a total of 22 participants. The insights gained in the user study will help the understanding of user perspectives on semantic linking in the audio domain.

To express a more nuanced notion of relevance as compared to binary judgments, graded relevance levels can be used for the evaluation of search results. Especially in Web search, users strongly prefer top results over less relevant results, and yet they often disagree on which are the top results for a given information need. Whereas previous works have generally considered disagreement as a negative effect, this paper proposes a method to exploit this user disagreement by integrating it into the evaluation procedure. First, we present experiments that investigate the user disagreement. We argue that, with a high disagreement, lower relevance levels might need to be promoted more than in the case where there is global consensus on the top results. This is formalized by introducing the User Disagreement Model, resulting in a weighting of the relevance levels with a probabilistic interpretation. A validity analysis is given, and we explain how to integrate the model with well-established evaluation metrics. Finally, we discuss a specific application of the model, in the estimation of suitable weights for the combined relevance of Web search snippets and pages.