1,720,976 research outputs found
Exploring Object-Centric and Scene-Centric CNN Features and their Complementarity for Human Rights Violations Recognition in Images
Full text linkIdentifying potential abuses of human rights through imagery is a novel and challenging task in the field of computer vision, that will enable to expose human rights violations over large-scale data that may otherwise be impossible. While standard databases for object and scene categorisation contain hundreds of different classes, the largest available dataset of human rights violations contains only 4 classes. Here, we introduce the ‘Human Rights Archive Database’ (HRA), a verified-by-experts repository of 3050 human rights violations photographs, labelled with human rights semantic categories, comprising a list of the types of human rights abuses encountered at present. With the HRA dataset and a two-phase transfer learning scheme, we fine-tuned the state-of-the-art deep convolutional neural networks (CNNs) to provide human rights violations classification CNNs (HRA-CNNs). We also present extensive experiments refined to evaluate how well object-centric and scene-centric CNN features can be combined for the task of recognising human rights abuses. With this, we show that HRA database poses a challenge at a higher level for the well studied representation learning methods, and provide a benchmark in the task of human rights violations recognition in visual context. We expect this dataset can help to open up new horizons on creating systems able of recognising rich information about human rights violations
MAT-CNN-SOPC: Motionless Analysis of Traffic Using Convolutional Neural Networks on System-On-a-Programmable-Chip
Full text linkIntelligent Transportation Systems (ITS) have become an important pillar in modern 'smart city' framework which demands intelligent involvement of machines. Traffic load recognition can be categorized as an important and challenging issue for such systems. Recently, Convolutional Neural Network (CNN) models have drawn considerable amount of interest in many areas such as weather classification, human rights violation detection through images, due to its accurate prediction capabilities. This work tackles real-life traffic load recognition problem on System-On-a-Programmable-Chip (SOPC) platform and coin it as MAT-CNN-SOPC, which uses an intelligent retraining mechanism of the CNN with known environments. The proposed methodology is capable of enhancing the efficacy of the approach by 2.44x in comparison to the state-of-art and proven through experimental analysis. We have also introduced a mathematical equation, which is capable of quantifying the suitability of using different CNN models over the other for a particular application based implementation
Detection of Human Rights Violations in Images: Can Convolutional Neural Networks Help?
Full text linkAfter setting the performance benchmarks for image, video, speech and audio processing, deep convolutional networks have been core to the greatest advances in image recognition tasks in recent times. This raises the question of whether there are any benefit in targeting these remarkable deep architectures with the unattempted task of recognising human rights violations through digital images. Under this perspective, we introduce a new, well-sampled human rights-centric dataset called Human Rights Understanding (HRUN). We conduct a rigorous evaluation on a common ground by combining this dataset with different state-of-the-art deep convolutional architectures in order to achieve recognition of human rights violations. Experimental results on the HRUN dataset have shown that the best performing CNN architectures can achieve up to 88.10% mean average precision. Additionally, our experiments demonstrate that increasing the size of the training samples is crucial for achieving an improvement on mean average precision principally when utilising very deep networks
Material classification in the wild: Do synthesized training data generalise better than real-world training data?
Full text linkWe question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03% mean average precision when classifying materials in cross-dataset scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from ∼ 5% to ∼ 19% across three widely used material databases of real-world images
Evaluating Deep Convolutional Neural Networks for Material Classification
Full text linkDetermining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising Convolutional Neural Networks (CNNs), we empirically study material classification of everyday objects employing these techniques. More specifically, we conduct a rigorous evaluation of how state-of-the art CNN architectures compare on a common ground over widely used material databases. Experimental results on three challenging material databases show that the best performing CNN architectures can achieve up to 94.99% mean average precision when classifying materials
Visual Recognition of Human Rights Violations
Full text linkThis thesis is concerned with the automation of human rights violation recognition in images. Solving this problem is extremely beneficial to human rights organisations and investigators, who are often interested in identifying and documenting potential violations of human rights within images. It will allow them to avoid the overwhelming task of analysing large volumes of images manually. However, visual recognition of human rights violations is challenging and previously unattempted. Through the use of computer vision, the notion of visual recognition of human rights violations is forged in this thesis, whilst this area is addressed by strongly considering the constraints related to the usability and flexibility of a real practice. Firstly, image datasets of human rights violations which are suitable for training and testing modern visual representations, such as convolutional neural networks (CNNs) are introduced for the first time ever. Secondly, we develop and apply transfer learning models specific to the human rights violation recognition problem. Various fusion methods are proposed for performing an equivalence and complementarity analysis of object-centric and scene-centric deep image representations for the task of human rights violation recognition. Additionally, a web demo for predicting human rights violations that may be used directly by human rights advocates and analysts is developed. Next, the problem of recognising displaced people from still images is considered. To solve this, a novel mechanism centred around the level of control each person feels of the situation is developed. By leveraging this mechanism, typical image classification turns into a uniform framework that infers potential displaced people from images. Finally, a human-centric approach for recognising rich information about two emotional states is proposed. The derived global emotional traits are harnessed alongside a data-driven CNN classifier to efficiently infer two of the most widespread modern abuses against human rights, child labour and displaced populations
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
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
Image based Monument Recognition using Graph based Visual Saliency
Full text linkThis article presents an image-based application aiming at simple image classification of well-known monuments in the area of Heraklion, Crete, Greece. This classification takes place by utilizing Graph Based Visual Saliency (GBVS) and employing Scale Invariant Feature Transform (SIFT) or Speeded Up RobustFeatures (SURF). For this purpose, images taken at various places of interest are being compared to an existing database containing images of these places at different angles and zoom. The time required for the matching progress in such application is an important element. To this goal, the images have been previously processed according to the Graph Based Visual Saliency model in order to keep either SIFT or SURF features corresponding to the actual monuments while the background “noise” is minimized. The application is then able to classify these images, helping the user to better understand what he/she sees and in which area the image has been taken. Experiments are performed to verify that the proposed approach improves the time needed for the classification without affecting the correctness of the results
- …
