We present different methods for obtaining descriptive properties automatically for the 151 original Pok\'emon. We train several different word embeddings models on a crawled Pok\'emon corpus, and use them to rank automatically English adjectives based on how characteristic they are to a given Pok\'emon. Based on our experiments, it is better to train a model with domain specific data than to use a pretrained model. Word2Vec produces less noise in the results than fastText model. Furthermore, we expand the list of properties for each Pok\'emon automatically. However, none of the methods is spot on and there is a considerable amount of noise in the different semantic models. Our models have been released on Zenodo.
We use autoregressive hidden Markov models and a time-frequency approach to create meaningful quantitative descriptions of behavioral characteristics of cerebellar ataxias from wearable inertial sensor data gathered during movement. Wearable sensor data is relatively easily collected and provides direct measurements of movement that can be used to develop useful behavioral biomarkers. Sensitive and specific behavioral biomarkers for neurodegenerative diseases are critical to supporting early detection, drug development efforts, and targeted treatments. We create a flexible and descriptive set of features derived from accelerometer and gyroscope data collected from wearable sensors while participants perform clinical assessment tasks, and with them estimate disease status and severity. A short period of data collection ($<$ 5 minutes) yields enough information to effectively separate patients with ataxia from healthy controls with very high accuracy, to separate ataxia from other neurodegenerative diseases such as Parkinson's disease, and to give estimates of disease severity.
Tables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods by hierarchical indexing, as well as implicit relationships of calculation and semantics. This work presents HiTab, a free and open dataset to study question answering (QA) and natural language generation (NLG) over hierarchical tables. HiTab is a cross-domain dataset constructed from a wealth of statistical reports (analyses) and Wikipedia pages, and has unique characteristics: (1) nearly all tables are hierarchical, and (2) both target sentences for NLG and questions for QA are revised from original, meaningful, and diverse descriptive sentences authored by analysts and professions of reports. (3) to reveal complex numerical reasoning in statistical analyses, we provide fine-grained annotations of entity and quantity alignment. HiTab provides 10,686 QA pairs and descriptive sentences with well-annotated quantity and entity alignment on 3,597 tables with broad coverage of table hierarchies and numerical reasoning types. Targeting hierarchical structure, we devise a novel hierarchy-aware logical form for symbolic reasoning over tables, which shows high effectiveness. Targeting complex numerical reasoning, we propose partially supervised training given annotations of entity and quantity alignment, which helps models to largely reduce spurious predictions in the QA task. In the NLG task, we find that entity and quantity alignment also helps NLG models to generate better results in a conditional generation setting. Experiment results of state-of-the-art baselines suggest that this dataset presents a strong challenge and a valuable benchmark for future research.
The abundance and richness of Internet photos of landmarks and cities has led to significant progress in 3D vision over the past two decades, including automated 3D reconstructions of the world's landmarks from tourist photos. However, a major source of information available for these 3D-augmented collections---namely language, e.g., from image captions---has been virtually untapped. In this work, we present WikiScenes, a new, large-scale dataset of landmark photo collections that contains descriptive text in the form of captions and hierarchical category names. WikiScenes forms a new testbed for multimodal reasoning involving images, text, and 3D geometry. We demonstrate the utility of WikiScenes for learning semantic concepts over images and 3D models. Our weakly-supervised framework connects images, 3D structure, and semantics---utilizing the strong constraints provided by 3D geometry---to associate semantic concepts to image pixels and 3D points.
When interacting in unstructured human environments, occasional robot failures are inevitable. When such failures occur, everyday people, rather than trained technicians, will be the first to respond. Existing natural language explanations hand-annotate contextual information from an environment to help everyday people understand robot failures. However, this methodology lacks generalizability and scalability. In our work, we introduce a more generalizable semantic explanation framework. Our framework autonomously captures the semantic information in a scene to produce semantically descriptive explanations for everyday users. To generate failure-focused explanations that are semantically grounded, we leverages both semantic scene graphs to extract spatial relations and object attributes from an environment, as well as pairwise ranking. Our results show that these semantically descriptive explanations significantly improve everyday users' ability to both identify failures and provide assistance for recovery than the existing state-of-the-art context-based explanations.
Inspired by how the human brain employs a higher number of neural pathways when describing a highly focused subject, we show that deep attentive models used for the main vision-language task of image captioning, could be extended to achieve better performance. Image captioning bridges a gap between computer vision and natural language processing. Automated image captioning is used as a tool to eliminate the need for human agent for creating descriptive captions for unseen images.Automated image captioning is challenging and yet interesting. One reason is that AI based systems capable of generating sentences that describe an input image could be used in a wide variety of tasks beyond generating captions for unseen images found on web or uploaded to social media. For example, in biology and medical sciences, these systems could provide researchers and physicians with a brief linguistic description of relevant images, potentially expediting their work.
We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network is used to show the importance of focusing on the broader context rather than only on the 3-D segment.
Statistical analyses and descriptive characterizations are sometimes assumed to be offering information on time series forecastability. Despite the scientific interest suggested by such assumptions, the relationships between descriptive time series features (e.g., temporal dependence, entropy, seasonality, trend and linearity features) and actual time series forecastability (quantified by issuing and assessing forecasts for the past) are scarcely studied and quantified in the literature. In this work, we aim to fill in this gap by investigating such relationships, and the way that they can be exploited for understanding hydroclimatic forecastability and its patterns. To this end, we follow a systematic framework bringing together a variety of -- mostly new for hydrology -- concepts and methods, including 57 descriptive features and nine seasonal time series forecasting methods (i.e., one simple, five exponential smoothing, two state space and one automated autoregressive fractionally integrated moving average methods). We apply this framework to three global datasets originating from the larger Global Historical Climatology Network (GHCN) and Global Streamflow Indices and Metadata (GSIM) archives. As these datasets comprise over 13 000 monthly temperature, precipitation and river flow time series from several continents and hydroclimatic regimes, they allow us to provide trustable characterizations and interpretations of 12-month ahead hydroclimatic forecastability at the global scale...
Distributed dataflow systems enable the use of clusters for scalable data analytics. However, selecting appropriate cluster resources for a processing job is often not straightforward. Performance models trained on historical executions of a concrete job are helpful in such situations, yet they are usually bound to a specific job execution context (e.g. node type, software versions, job parameters) due to the few considered input parameters. Even in case of slight context changes, such supportive models need to be retrained and cannot benefit from historical execution data from related contexts. This paper presents Bellamy, a novel modeling approach that combines scale-outs, dataset sizes, and runtimes with additional descriptive properties of a dataflow job. It is thereby able to capture the context of a job execution. Moreover, Bellamy is realizing a two-step modeling approach. First, a general model is trained on all the available data for a specific scalable analytics algorithm, hereby incorporating data from different contexts. Subsequently, the general model is optimized for the specific situation at hand, based on the available data for the concrete context. We evaluate our approach on two publicly available datasets consisting of execution data from various dataflow jobs carried out in different environments, showing that Bellamy outperforms state-of-the-art methods.
Image Captioning is a task that combines computer vision and natural language processing, where it aims to generate descriptive legends for images. It is a two-fold process relying on accurate image understanding and correct language understanding both syntactically and semantically. It is becoming increasingly difficult to keep up with the latest research and findings in the field of image captioning due to the growing amount of knowledge available on the topic. There is not, however, enough coverage of those findings in the available review papers. We perform in this paper a run-through of the current techniques, datasets, benchmarks and evaluation metrics used in image captioning. The current research on the field is mostly focused on deep learning-based methods, where attention mechanisms along with deep reinforcement and adversarial learning appear to be in the forefront of this research topic. In this paper, we review recent methodologies such as UpDown, OSCAR, VIVO, Meta Learning and a model that uses conditional generative adversarial nets. Although the GAN-based model achieves the highest score, UpDown represents an important basis for image captioning and OSCAR and VIVO are more useful as they use novel object captioning. This review paper serves as a roadmap for researchers to keep up to date with the latest contributions made in the field of image caption generation.
Traffic accidents are a threat to human lives, particularly pedestrians causing premature deaths. Therefore, it is necessary to devise systems to prevent accidents in advance and respond proactively, using potential risky situations as one of the surrogate safety measurements. This study introduces a new concept of a pedestrian safety system that combines the field and the centralized processes. The system can warn of upcoming risks immediately in the field and improve the safety of risk frequent areas by assessing the safety levels of roads without actual collisions. In particular, this study focuses on the latter by introducing a new analytical framework for a crosswalk safety assessment with behaviors of vehicle/pedestrian and environmental features. We obtain these behavioral features from actual traffic video footage in the city with complete automatic processing. The proposed framework mainly analyzes these behaviors in multidimensional perspectives by constructing a data cube structure, which combines the LSTM based predictive collision risk estimation model and the on line analytical processing operations. From the PCR estimation model, we categorize the severity of risks as four levels and apply the proposed framework to assess the crosswalk safety with behavioral features. Our analytic experiments are based on two scenarios, and the various descriptive results are harvested the movement patterns of vehicles and pedestrians by road environment and the relationships between risk levels and car speeds. Thus, the proposed framework can support decision makers by providing valuable information to improve pedestrian safety for future accidents, and it can help us better understand their behaviors near crosswalks proactively. In order to confirm the feasibility and applicability of the proposed framework, we implement and apply it to actual operating CCTVs in Osan City, Korea.
Compact convolutional neural networks (CNNs) have witnessed exceptional improvements in performance in recent years. However, they still fail to provide the same predictive power as CNNs with a large number of parameters. The diverse and even abundant features captured by the layers is an important characteristic of these successful CNNs. However, differences in this characteristic between large CNNs and their compact counterparts have rarely been investigated. In compact CNNs, due to the limited number of parameters, abundant features are unlikely to be obtained, and feature diversity becomes an essential characteristic. Diverse features present in the activation maps derived from a data point during model inference may indicate the presence of a set of unique descriptors necessary to distinguish between objects of different classes. In contrast, data points with low feature diversity may not provide a sufficient amount of unique descriptors to make a valid prediction; we refer to them as random predictions. Random predictions can negatively impact the optimization process and harm the final performance. This paper proposes addressing the problem raised by random predictions by reshaping the standard cross-entropy to make it biased toward data points with a limited number of unique descriptive features. Our novel Bias Loss focuses the training on a set of valuable data points and prevents the vast number of samples with poor learning features from misleading the optimization process. Furthermore, to show the importance of diversity, we present a family of SkipNet models whose architectures are brought to boost the number of unique descriptors in the last layers. Our Skipnet-M can achieve 1% higher classification accuracy than MobileNetV3 Large.
The 3D visual perception for vehicles with the surround-view fisheye camera system is a critical and challenging task for low-cost urban autonomous driving. While existing monocular 3D object detection methods perform not well enough on the fisheye images for mass production, partly due to the lack of 3D datasets of such images. In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identification and unit assembling, etc. Particularly, we propose the concept of Multidimensional Vector to include the utilizable information generated in different dimensions and stages, instead of the descriptive approach for the bird's eye view (BEV) or a cube of eight points. The experiments of real fisheye images demonstrate that our solution achieves state-of-the-art accuracy while being real-time in practice.
We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks. Our approach is applied to realistic road networks of 17 cities from Open Street Map. While edge features are crucial to generate descriptive graph representations of road networks, graph convolutional networks usually rely on node features only. We show that the highly representative edge features can still be integrated into such networks by applying a line graph transformation. We also propose a method for neighborhood sampling based on a topological neighborhood composed of both local and global neighbors. We compare the performance of learning representations using different types of neighborhood aggregation functions in transductive and inductive tasks and in supervised and unsupervised learning. Furthermore, we propose a novel aggregation approach, Graph Attention Isomorphism Network, GAIN. Our results show that GAIN outperforms state-of-the-art methods on the road type classification problem.
This paper presents new designs of graph convolutional neural networks (GCNs) on 3D meshes for 3D object segmentation and classification. We use the faces of the mesh as basic processing units and represent a 3D mesh as a graph where each node corresponds to a face. To enhance the descriptive power of the graph, we introduce a 1-ring face neighbourhood structure to derive novel multi-dimensional spatial and structure features to represent the graph nodes. Based on this new graph representation, we then design a densely connected graph convolutional block which aggregates local and regional features as the key construction component to build effective and efficient practical GCN models for 3D object classification and segmentation. We will present experimental results to show that our new technique outperforms state of the art where our models are shown to have the smallest number of parameters and consietently achieve the highest accuracies across a number of benchmark datasets. We will also present ablation studies to demonstrate the soundness of our design principles and the effectiveness of our practical models.
We present a method for learning "spectrally descriptive" edge weights for graphs. We generalize a previously known distance measure on graphs (Graph Diffusion Distance), thereby allowing it to be tuned to minimize an arbitrary loss function. Because all steps involved in calculating this modified GDD are differentiable, we demonstrate that it is possible for a small neural network model to learn edge weights which minimize loss. GDD alone does not effectively discriminate between graphs constructed from shoot apical meristem images of wild-type vs. mutant \emph{Arabidopsis thaliana} specimens. However, training edge weights and kernel parameters with contrastive loss produces a learned distance metric with large margins between these graph categories. We demonstrate this by showing improved performance of a simple k-nearest-neighbors classifier on the learned distance matrix. We also demonstrate a further application of this method to biological image analysis: once trained, we use our model to compute the distance between the biological graphs and a set of graphs output by a cell division simulator. This allows us to identify simulation parameter regimes which are similar to each class of graph in our original dataset.
Building an interactive artificial intelligence that can ask questions about the real world is one of the biggest challenges for vision and language problems. In particular, goal-oriented visual dialogue, where the aim of the agent is to seek information by asking questions during a turn-taking dialogue, has been gaining scholarly attention recently. While several existing models based on the GuessWhat?! dataset have been proposed, the Questioner typically asks simple category-based questions or absolute spatial questions. This might be problematic for complex scenes where the objects share attributes or in cases where descriptive questions are required to distinguish objects. In this paper, we propose a novel Questioner architecture, called Unified Questioner Transformer (UniQer), for descriptive question generation with referring expressions. In addition, we build a goal-oriented visual dialogue task called CLEVR Ask. It synthesizes complex scenes that require the Questioner to generate descriptive questions. We train our model with two variants of CLEVR Ask datasets. The results of the quantitative and qualitative evaluations show that UniQer outperforms the baseline.
In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and automated document classification. Prior studies have only focused on processing text for classification, whereas technical documents often contain multimodal information. To leverage multimodal information for document classification to improve the model performance, this paper presents a novel multimodal deep learning architecture, TechDoc, which utilizes three types of information, including natural language texts and descriptive images within documents and the associations among the documents. The architecture synthesizes the convolutional neural network, recurrent neural network, and graph neural network through an integrated training process. We applied the architecture to a large multimodal technical document database and trained the model for classifying documents based on the hierarchical International Patent Classification system. Our results show that TechDoc presents a greater classification accuracy than the unimodal methods and other state-of-the-art benchmarks. The trained model can potentially be scaled to millions of real-world multimodal technical documents, which is useful for data and knowledge management in large technology companies and organizations.
In this work we propose a novel and fully automated method for extracting the yarn geometrical features in woven composites so that a direct parametrization of the textile reinforcement is achieved (e.g., FE mesh). Thus, our aim is not only to perform yarn segmentation from tomographic images but rather to provide a complete descriptive modeling of the fabric. As such, this direct approach improves on previous methods that use voxel-wise masks as intermediate representations followed by re-meshing operations (yarn envelope estimation). The proposed approach employs two deep neural network architectures (U-Net and Mask RCNN). First, we train the U-Net to generate synthetic CT images from the corresponding FE simulations. This allows to generate large quantities of annotated data without requiring costly manual annotations. This data is then used to train the Mask R-CNN, which is focused on predicting contour points around each of the yarns in the image. Experimental results show that our method is accurate and robust for performing yarn instance segmentation on CT images, this is further validated by quantitative and qualitative analyses.
Contextual Bandits find important use cases in various real-life scenarios such as online advertising, recommendation systems, healthcare, etc. However, most of the algorithms use flat feature vectors to represent context whereas, in the real world, there is a varying number of objects and relations among them to model in the context. For example, in a music recommendation system, the user context contains what music they listen to, which artists create this music, the artist albums, etc. Adding richer relational context representations also introduces a much larger context space making exploration-exploitation harder. To improve the efficiency of exploration-exploitation knowledge about the context can be infused to guide the exploration-exploitation strategy. Relational context representations allow a natural way for humans to specify knowledge owing to their descriptive nature. We propose an adaptation of Knowledge Infused Policy Gradients to the Contextual Bandit setting and a novel Knowledge Infused Policy Gradients Upper Confidence Bound algorithm and perform an experimental analysis of a simulated music recommendation dataset and various real-life datasets where expert knowledge can drastically reduce the total regret and where it cannot.