We propose 3DSmoothNet, a full workflow to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers using a voxelized smoothed density value (SDV) representation. The latter is computed per interest point and aligned to the local reference frame (LRF) to achieve rotation invariance. Our compact, learned, rotation invariant 3D point cloud descriptor achieves 94.9% average recall on the 3DMatch benchmark data set, outperforming the state-of-the-art by more than 20 percent points with only 32 output dimensions. This very low output dimension allows for near realtime correspondence search with 0.1 ms per feature point on a standard PC. Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers. We show that 3DSmoothNet trained only on RGB-D indoor scenes of buildings achieves 79.0% average recall on laser scans of outdoor vegetation, more than double the performance of our closest, learning-based competitors. Code, data and pre-trained models are available online at https://github.com/zgojcic/3DSmoothNet.
Electronic Healthcare records contain large volumes of unstructured data in different forms. Free text constitutes a large portion of such data, yet this source of richly detailed information often remains under-used in practice because of a lack of suitable methodologies to extract interpretable content in a timely manner. Here we apply network-theoretical tools to the analysis of free text in Hospital Patient Incident reports in the English National Health Service, to find clusters of reports in an unsupervised manner and at different levels of resolution based directly on the free text descriptions contained within them. To do so, we combine recently developed deep neural network text-embedding methodologies based on paragraph vectors with multi-scale Markov Stability community detection applied to a similarity graph of documents obtained from sparsified text vector similarities. We showcase the approach with the analysis of incident reports submitted in Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals levels of meaning with different resolution in the topics of the dataset, as shown by relevant descriptive terms extracted from the groups of records, as well as by comparing a posteriori against hand-coded categories assigned by healthcare personnel. Our content communities exhibit good correspondence with well-defined hand-coded categories, yet our results also provide further medical detail in certain areas as well as revealing complementary descriptors of incidents beyond the external classification. We also discuss how the method can be used to monitor reports over time and across different healthcare providers, and to detect emerging trends that fall outside of pre-existing categories.
Corporate distress models typically only employ the numerical financial variables in the firms' annual reports. We develop a model that employs the unstructured textual data in the reports as well, namely the auditors' reports and managements' statements. Our model consists of a convolutional recurrent neural network which, when concatenated with the numerical financial variables, learns a descriptive representation of the text that is suited for corporate distress prediction. We find that the unstructured data provides a statistically significant enhancement of the distress prediction performance, in particular for large firms where accurate predictions are of the utmost importance. Furthermore, we find that auditors' reports are more informative than managements' statements and that a joint model including both managements' statements and auditors' reports displays no enhancement relative to a model including only auditors' reports. Our model demonstrates a direct improvement over existing state-of-the-art models.
Recognizing degraded faces from low resolution and blurred images are common yet challenging task. Local Frequency Descriptor (LFD) has been proved to be effective for this task yet it is extracted from a spatial neighborhood of a pixel of a frequency plane independently regardless of correlations between frequencies. In addition, it uses a fixed window size named single scale of short-term Frequency transform (STFT). To explore the frequency correlations and preserve low resolution and blur insensitive simultaneously, we propose Enhanced LFD in which information in space and frequency is jointly utilized so as to be more descriptive and discriminative than LFD. The multi-scale competition strategy that extracts multiple descriptors corresponding to multiple window sizes of STFT and take one corresponding to maximum confidence as the final recognition result. The experiments conducted on Yale and FERET databases demonstrate that promising results have been achieved by the proposed Enhanced LFD and multi-scale competition strategy.
We first propose a new task named Dialogue Description (Dial2Desc). Unlike other existing dialogue summarization tasks such as meeting summarization, we do not maintain the natural flow of a conversation but describe an object or an action of what people are talking about. The Dial2Desc system takes a dialogue text as input, then outputs a concise description of the object or the action involved in this conversation. After reading this short description, one can quickly extract the main topic of a conversation and build a clear picture in his mind, without reading or listening to the whole conversation. Based on the existing dialogue dataset, we build a new dataset, which has more than one hundred thousand dialogue-description pairs. As a step forward, we demonstrate that one can get more accurate and descriptive results using a new neural attentive model that exploits the interaction between utterances from different speakers, compared with other baselines.
Data of sequential nature arise in many application domains in forms of, e.g. textual data, DNA sequences, and software execution traces. Different research disciplines have developed methods to learn sequence models from such datasets: (i) in the machine learning field methods such as (hidden) Markov models and recurrent neural networks have been developed and successfully applied to a wide-range of tasks, (ii) in process mining process discovery techniques aim to generate human-interpretable descriptive models, and (iii) in the grammar inference field the focus is on finding descriptive models in the form of formal grammars. Despite their different focuses, these fields share a common goal - learning a model that accurately describes the behavior in the underlying data. Those sequence models are generative, i.e, they can predict what elements are likely to occur after a given unfinished sequence. So far, these fields have developed mainly in isolation from each other and no comparison exists. This paper presents an interdisciplinary experimental evaluation that compares sequence modeling techniques on the task of next-element prediction on four real-life sequence datasets. The results indicate that machine learning techniques that generally have no aim at interpretability in terms of accuracy outperform techniques from the process mining and grammar inference fields that aim to yield interpretable models.
Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to utilize complementary information. a sample re-weight strategy is employed for ensemble training to address the noisy label problem. Our system achieves a mean average precision (mAP@3) of 0.958, outperforming the baseline system of 0.704. Our system ranked the 1st and 4th out of 558 submissions in the public and private leaderboard of DCASE 2018 Task 2 challenge. Our codes are available at https://github.com/Cocoxili/DCASE2018Task2/.
The advancement of science as outlined by Popper and Kuhn is largely qualitative, but with bibliometric data it is possible and desirable to develop a quantitative picture of scientific progress. Furthermore it is also important to allocate finite resources to research topics that have growth potential, to accelerate the process from scientific breakthroughs to technological innovations. In this paper, we address this problem of quantitative knowledge evolution by analysing the APS publication data set from 1981 to 2010. We build the bibliographic coupling and co-citation networks, use the Louvain method to detect topical clusters (TCs) in each year, measure the similarity of TCs in consecutive years, and visualize the results as alluvial diagrams. Having the predictive features describing a given TC and its known evolution in the next year, we can train a machine learning model to predict future changes of TCs, i.e., their continuing, dissolving, merging and splitting. We found the number of papers from certain journals, the degree, closeness, and betweenness to be the most predictive features. Additionally, betweenness increases significantly for merging events, and decreases significantly for splitting events. Our results represent a first step from a descriptive understanding of the Science of Science (SciSci), towards one that is ultimately prescriptive.
Designing a logo is a long, complicated, and expensive process for any designer. However, recent advancements in generative algorithms provide models that could offer a possible solution. Logos are multi-modal, have very few categorical properties, and do not have a continuous latent space. Yet, conditional generative adversarial networks can be used to generate logos that could help designers in their creative process. We propose LoGAN: an improved auxiliary classifier Wasserstein generative adversarial neural network (with gradient penalty) that is able to generate logos conditioned on twelve different colors. In 768 generated instances (12 classes and 64 logos per class), when looking at the most prominent color, the conditional generation part of the model has an overall precision and recall of 0.8 and 0.7 respectively. LoGAN's results offer a first glance at how artificial intelligence can be used to assist designers in their creative process and open promising future directions, such as including more descriptive labels which will provide a more exhaustive and easy-to-use system.
The Information Flow Framework (IFF) is a descriptive category metatheory currently under development, which is being offered as the structural aspect of the Standard Upper Ontology (SUO). The architecture of the IFF is composed of metalevels, namespaces and meta-ontologies. The main application of the IFF is institutional: the notion of institutions and their morphisms are being axiomatized in the upper metalevels of the IFF, and the lower metalevel of the IFF has axiomatized various institutions in which semantic integration has a natural expression as the colimit of theories.
The pattern theory of Grenander is a mathematical framework where patterns are represented by probability models on random variables of algebraic structures. In this paper, we review three families of probability models, namely, the discriminative models, the descriptive models, and the generative models. A discriminative model is in the form of a classifier. It specifies the conditional probability of the class label given the input signal. A descriptive model specifies the probability distribution of the signal, based on an energy function defined on the signal. A generative model assumes that the signal is generated by some latent variables via a transformation. We shall review these models within a common framework and explore their connections. We shall also review the recent developments that take advantage of the high approximation capacities of deep neural networks.
In machine learning and data mining, Cluster analysis is one of the most widely used unsupervised learning technique. Philosophy of this algorithm is to find similar data items and group them together based on any distance function in multidimensional space. These methods are suitable for finding groups of data that behave in a coherent fashion. The perspective may vary for clustering i.e. the way we want to find similarity, some methods are based on distance such as K-Means technique and some are probability based, like GMM. Understanding prominent segment of data is always challenging as multidimension space does not allow us to have a look and feel of the distance or any visual context on the health of the clustering. While explaining data using clusters, the major problem is to tell how many cluster are good enough to explain the data. Generally basic descriptive statistics are used to estimate cluster behaviour like scree plot, dendrogram etc. We propose a novel method to understand the cluster behaviour which can be used not only to find right number of clusters but can also be used to access the difference of health between different clustering methods on same data. Our technique would also help to also eliminate the noisy variables and optimize the clustering result. keywords - Clustering, Metric, K-means, hierarchical clustering, silhoutte, clustering index, measures
From the database DBTropes.org, we have created a dataset of films and the tropes that they use, which we have called PicTropes. In this report we provide the descriptive analysis and a further discussion on the dataset PicTropes: The extracted features will help us decide the best values for a future recommendation system and content generator, whereas the analysis of the distribution functions that fit the best will help us interpret the relation between the films and the tropes that were found inside them. Additionally, we provide rankings of the top-25 tropes and films, which will help us discuss and formulate questions to guide future extensions of the PicTropes dataset.
Having the right assortment of shipping boxes in the fulfillment warehouse to pack and ship customer's online orders is an indispensable and integral part of nowadays eCommerce business, as it will not only help maintain a profitable business but also create great experiences for customers. However, it is an extremely challenging operations task to strategically select the best combination of tens of box sizes from thousands of feasible ones to be responsible for hundreds of thousands of orders daily placed on millions of inventory products. In this paper, we present a machine learning approach to tackle the task by formulating the box design problem prescriptively as a generalized version of weighted $k$-medoids clustering problem, where the parameters are estimated through a variety of descriptive analytics. We test this machine learning approach on fulfillment data collected from Walmart U.S. eCommerce, and our approach is shown to be capable of improving the box utilization rate by more than $10\%$.
Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model outperforms strong baselines improving the state-of-the-art on the recently released RotoWire dataset.
We propose a framework to automatically generate descriptive comments for source code blocks. While this problem has been studied by many researchers previously, their methods are mostly based on fixed template and achieves poor results. Our framework does not rely on any template, but makes use of a new recursive neural network called Code-RNN to extract features from the source code and embed them into one vector. When this vector representation is input to a new recurrent neural network (Code-GRU), the overall framework generates text descriptions of the code with accuracy (Rouge-2 value) significantly higher than other learning-based approaches such as sequence-to-sequence model. The Code-RNN model can also be used in other scenario where the representation of code is required.
Approaches to decision-making under uncertainty in the belief function framework are reviewed. Most methods are shown to blend criteria for decision under ignorance with the maximum expected utility principle of Bayesian decision theory. A distinction is made between methods that construct a complete preference relation among acts, and those that allow incomparability of some acts due to lack of information. Methods developed in the imprecise probability framework are applicable in the Dempster-Shafer context and are also reviewed. Shafer's constructive decision theory, which substitutes the notion of goal for that of utility, is described and contrasted with other approaches. The paper ends by pointing out the need to carry out deeper investigation of fundamental issues related to decision-making with belief functions and to assess the descriptive, normative and prescriptive values of the different approaches.
We present an efficient framework that can generate a coherent paragraph to describe a given video. Previous works on video captioning usually focus on video clips. They typically treat an entire video as a whole and generate the caption conditioned on a single embedding. On the contrary, we consider videos with rich temporal structures and aim to generate paragraph descriptions that can preserve the story flow while being coherent and concise. Towards this goal, we propose a new approach, which produces a descriptive paragraph by assembling temporally localized descriptions. Given a video, it selects a sequence of distinctive clips and generates sentences thereon in a coherent manner. Particularly, the selection of clips and the production of sentences are done jointly and progressively driven by a recurrent network -- what to describe next depends on what have been said before. Here, the recurrent network is learned via self-critical sequence training with both sentence-level and paragraph-level rewards. On the ActivityNet Captions dataset, our method demonstrated the capability of generating high-quality paragraph descriptions for videos. Compared to those by other methods, the descriptions produced by our method are often more relevant, more coherent, and more concise.
Electronic Healthcare Records contain large volumes of unstructured data, including extensive free text. Yet this source of detailed information often remains under-used because of a lack of methodologies to extract interpretable content in a timely manner. Here we apply network-theoretical tools to analyse free text in Hospital Patient Incident reports from the National Health Service, to find clusters of documents with similar content in an unsupervised manner at different levels of resolution. We combine deep neural network paragraph vector text-embedding with multiscale Markov Stability community detection applied to a sparsified similarity graph of document vectors, and showcase the approach on incident reports from Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals different levels of meaning in the topics of the dataset, as shown by descriptive terms extracted from the clusters of records. We also compare a posteriori against hand-coded categories assigned by healthcare personnel, and show that our approach outperforms LDA-based models. Our content clusters exhibit good correspondence with two levels of hand-coded categories, yet they also provide further medical detail in certain areas and reveal complementary descriptors of incidents beyond the external classification taxonomy.
Image captioning is the process of generating a natural language description of an image. Most current image captioning models, however, do not take into account the emotional aspect of an image, which is very relevant to activities and interpersonal relationships represented therein. Towards developing a model that can produce human-like captions incorporating these, we use facial expression features extracted from images including human faces, with the aim of improving the descriptive ability of the model. In this work, we present two variants of our Face-Cap model, which embed facial expression features in different ways, to generate image captions. Using all standard evaluation metrics, our Face-Cap models outperform a state-of-the-art baseline model for generating image captions when applied to an image caption dataset extracted from the standard Flickr 30K dataset, consisting of around 11K images containing faces. An analysis of the captions finds that, perhaps surprisingly, the improvement in caption quality appears to come not from the addition of adjectives linked to emotional aspects of the images, but from more variety in the actions described in the captions.