1,720,990 research outputs found
Unsupervised Semantic Discovery Through Visual Patterns Detection
Full text linkWe propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a visual pattern in an image, we introduce the notion of “semantic levels" and devise a conceptual framework along with measures and a dedicated benchmark dataset for future comparisons. Our algorithm is composed by two phases. A filtering phase, which selects semantical hotsposts by means of an accumulator space, then a clustering phase which propagates the semantic properties of the hotspots on a superpixels basis. We provide both qualitative and quantitative experimental validation, achieving optimal results in terms of robustness to noise and semantic consistency. We also made code and dataset publicly available
On the Application of a Common Theoretical Explainability Framework in Information Retrieval
Full text linkMost of the current state-of-the-art models used to solve the search and ranking tasks in Information Retrieval (IR) are considered “black boxes” due to the enormous number of parameters employed, which makes it difficult for humans to understand the relation between input and output. Thus, in the current literature, several approaches are proposed to explain their outputs, trying to make the models more explainable while maintaining the high level of effectiveness achieved. Even though many methods have been developed, there is still a lack of a common way of describing and evaluating the models and methods of the Explainabile IR (ExIR) field. This work shows how a common theoretical framework for explainability (previously presented in the biomedical field) can be applied to IR. We first describe the general framework and then focus on specific explanation techniques in the IR field, focusing on core IR tasks: search and ranking. We show how well-known methods in ExIR fit into the framework and how specific IR explainability evaluation metrics can be described using this new setting
Cylinders extraction in non-oriented point clouds as a clustering problem
Full text linkFinding geometric primitives in 3D point clouds is a fundamental task in many engineering applications such as robotics, autonomous-vehicles and automated industrial inspection. Among all solid shapes, cylinders are frequently found in a variety of scenes, comprising natural or man-made objects. Despite their ubiquitous presence, automated extraction and fitting can become challenging if performed ”in-the-wild”, when the number of primitives is unknown or the point cloud is noisy and not oriented. In this paper we pose the problem of extracting multiple cylinders in a scene by means of a Game-Theoretic inlier selection process exploiting the geometrical relations between pairs of axis candidates. First, we formulate the similarity between two possible cylinders considering the rigid motion aligning the two axes to the same line. This motion is represented with a unitary dual-quaternion so that the distance between two cylinders is induced by the length of the shortest geodesic path in SE(3). Then, a Game-Theoretical process exploits such similarity function to extract sets of primitives maximizing their inner mutual consensus. The outcome of the evolutionary process consists in a probability distribution over the sets of candidates (ie axes), which in turn is used to directly estimate the final cylinder parameters. An extensive experimental section shows that the proposed algorithm offers a high resilience to noise, since the process inherently discards inconsistent data. Compared to other methods, it does not need point normals and does not require a fine tuning of multiple parameters
A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision
No full textA significant amount of Deep Learning research deals with the reduction of network complexity. In most scenarios the preservation of very high performance has priority over size reduction. However, when dealing with embedded systems, the limited amount of resources forces a switch in perspective. In fact, being able to dramatically reduce complexity could be a stronger requisite for overall feasibility than excellent performance. In this paper we propose a simple to implement yet effective method to largely reduce the size of Convolutional Neural Networks with minimal impact on their performance. The key idea is to assess the relevance of each kernel with respect to a representative dataset by computing the output of its activation function and to trim them accordingly. The resulting network becomes small enough to be adopted on embedded hardware, such as smart cameras or lightweight edge processing units. In order to assess the capability of our method with respect to real-world scenarios, we adopted it to shrink two different pre-trained networks to be hosted on general purpose low-end FPGA hardware to be found in embedded cameras. Our experiments demonstrated both the overall feasibility of the method and its superior performance when compared with similar size-reducing techniques introduced in recent literature
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
A Survey on Text Classification Algorithms: From Text to Predictions
Full text linkIn recent years, the exponential growth of digital documents has been met by rapid progress in text classification techniques. Newly proposed machine learning algorithms leverage the latest advancements in deep learning methods, allowing for the automatic extraction of expressive features. The swift development of these methods has led to a plethora of strategies to encode natural language into machine-interpretable data. The latest language modelling algorithms are used in conjunction with ad hoc preprocessing procedures, of which the description is often omitted in favour of a more detailed explanation of the classification step. This paper offers a concise review of recent text classification models, with emphasis on the flow of data, from raw text to output labels. We highlight the differences between earlier methods and more recent, deep learning-based methods in both their functioning and in how they transform input data. To give a better perspective on the text classification landscape, we provide an overview of datasets for the English language, as well as supplying instructions for the synthesis of two new multilabel datasets, which we found to be particularly scarce in this setting. Finally, we provide an outline of new experimental results and discuss the open research challenges posed by deep learning-based language models
Recommendation Systems: An Insight Into Current Development and Future Research Challenges
Full text linkResearch on recommendation systems is swiftly producing an abundance of novel methods, constantly challenging the current state-of-the-art. Inspired by advancements in many related fields, like Natural Language Processing and Computer Vision, many hybrid approaches based on deep learning are being proposed, making solid improvements over traditional methods. On the downside, this flurry of research activity, often focused on improving over a small number of baselines, makes it hard to identify reference methods and standardized evaluation protocols. Furthermore, the traditional categorization of recommendation systems into content-based, collaborative filtering and hybrid systems lacks the informativeness it once had. With this work, we provide a gentle introduction to recommendation systems, describing the task they are designed to solve and the challenges faced in research. Building on previous work, an extension to the standard taxonomy is presented, to better reflect the latest research trends, including the diverse use of content and temporal information. To ease the approach toward the technical methodologies recently proposed in this field, we review several representative methods selected primarily from top conferences and systematically describe their goals and novelty. We formalize the main evaluation metrics adopted by researchers and identify the most commonly used benchmarks. Lastly, we discuss issues in current research practices by analyzing experimental results reported on three popular datasets
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
