In recent years, deep convolutional neural networks (CNN) have significantly advanced face detection. In particular, lightweight CNNbased architectures have achieved great success due to their lowcomplexity structure facilitating real-time detection tasks. However, current lightweight CNN-based face detectors trading accuracy for efficiency have inadequate capability in handling insufficient feature representation, faces with unbalanced aspect ratios and occlusion. Consequently, they exhibit deteriorated performance far lagging behind the deep heavy detectors. To achieve efficient face detection without sacrificing accuracy, we design an efficient deep face detector termed EfficientFace in this study, which contains three modules for feature enhancement. To begin with, we design a novel cross-scale feature fusion strategy to facilitate bottom-up information propagation, such that fusing low-level and highlevel features is further strengthened. Besides, this is conducive to estimating the locations of faces and enhancing the descriptive power of face features. Secondly, we introduce a Receptive Field Enhancement module to consider faces with various aspect ratios. Thirdly, we add an Attention Mechanism module for improving the representational capability of occluded faces. We have evaluated EfficientFace on four public benchmarks and experimental results demonstrate the appealing performance of our method. In particular, our model respectively achieves 95.1% (Easy), 94.0% (Medium) and 90.1% (Hard) on validation set of WIDER Face dataset, which is competitive with heavyweight models with only 1/15 computational costs of the state-of-the-art MogFace detector.
Face attribute research has so far used only simple binary attributes for facial hair; e.g., beard / no beard. We have created a new, more descriptive facial hair annotation scheme and applied it to create a new facial hair attribute dataset, FH37K. Face attribute research also so far has not dealt with logical consistency and completeness. For example, in prior research, an image might be classified as both having no beard and also having a goatee (a type of beard). We show that the test accuracy of previous classification methods on facial hair attribute classification drops significantly if logical consistency of classifications is enforced. We propose a logically consistent prediction loss, LCPLoss, to aid learning of logical consistency across attributes, and also a label compensation training strategy to eliminate the problem of no positive prediction across a set of related attributes. Using an attribute classifier trained on FH37K, we investigate how facial hair affects face recognition accuracy, including variation across demographics. Results show that similarity and difference in facial hairstyle have important effects on the impostor and genuine score distributions in face recognition. The code is at https:// github.com/ HaiyuWu/ LogicalConsistency.
When designing Machine Learning (ML) enabled solutions, designers often need to simulate ML behavior through the Wizard of Oz (WoZ) approach to test the user experience before the ML model is available. Although reproducing ML errors is essential for having a good representation, they are rarely considered. We introduce Wizard of Errors (WoE), a tool for conducting WoZ studies on ML-enabled solutions that allows simulating ML errors during user experience assessment. We explored how this system can be used to simulate the behavior of a computer vision model. We tested WoE with design students to determine the importance of considering ML errors in design, the relevance of using descriptive error types instead of confusion matrix, and the suitability of manual error control in WoZ studies. Our work identifies several challenges, which prevent realistic error representation by designers in such studies. We discuss the implications of these findings for design.
Scholars who want to research a scientific topic must take time to read, extract meaning, and identify connections across many papers. As scientific literature grows, this becomes increasingly challenging. Meanwhile, authors summarize prior research in papers' related work sections, though this is scoped to support a single paper. A formative study found that while reading multiple related work paragraphs helps overview a topic, it is hard to navigate overlapping and diverging references and research foci. In this work, we design a system, Relatedly, that scaffolds exploring and reading multiple related work paragraphs on a topic, with features including dynamic re-ranking and highlighting to spotlight unexplored dissimilar information, auto-generated descriptive paragraph headings, and low-lighting of redundant information. From a within-subjects user study (n=15), we found that scholars generate more coherent, insightful, and comprehensive topic outlines using Relatedly compared to a baseline paper list.
Geological modeling currently uses various computer-based applications. Data harmonization at the semantic level by means of ontologies is essential for making these applications interoperable. Since geo-modeling is currently part of multidisciplinary projects, semantic harmonization is required to model not only geological knowledge but also to integrate other domain knowledge at a general level. For this reason, the domain ontologies used for describing geological knowledge must be based on a sound ontology background to ensure the described geological knowledge is integratable. This paper presents a domain ontology: GeoFault, resting on the Basic Formal Ontology BFO (Arp et al., 2015) and the GeoCore ontology (Garcia et al., 2020). It models the knowledge related to geological faults. Faults are essential to various industries but are complex to model. They can be described as thin deformed rock volumes or as spatial arrangements resulting from the different displacements of geological blocks. At a broader scale, faults are currently described as mere surfaces, which are the components of complex fault arrays. The reference to the BFO and GeoCore package allows assigning these various fault elements to define ontology classes and their logical linkage within a consistent ontology framework. The GeoFault ontology covers the core knowledge of faults 'strico sensu,' excluding ductile shear deformations. This considered vocabulary is essentially descriptive and related to regional to outcrop scales, excluding microscopic, orogenic, and tectonic plate structures. The ontology is molded in OWL 2, validated by competency questions with two use cases, and tested using an in-house ontology-driven data entry application. The work of GeoFault provides a solid framework for disambiguating fault knowledge and a foundation of fault data integration for the applications and the users.
Remote photoplethysmography (rPPG) is an attractive method for noninvasive, convenient and concomitant measurement of physiological vital signals. Public benchmark datasets have served a valuable role in the development of this technology and improvements in accuracy over recent years.However, there remain gaps in the public datasets.First, despite the ubiquity of cameras on mobile devices, there are few datasets recorded specifically with mobile phone cameras. Second, most datasets are relatively small and therefore are limited in diversity, both in appearance (e.g., skin tone), behaviors (e.g., motion) and environment (e.g., lighting conditions). In an effort to help the field advance, we present the Multi-domain Mobile Video Physiology Dataset (MMPD), comprising 11 hours of recordings from mobile phones of 33 subjects. The dataset is designed to capture videos with greater representation across skin tone, body motion, and lighting conditions. MMPD is comprehensive with eight descriptive labels and can be used in conjunction with the rPPG-toolbox. The reliability of the dataset is verified by mainstream unsupervised methods and neural methods. The GitHub repository of our dataset: https://github.com/THU-CS-PI/MMPD_rPPG_dataset.
Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO). Despite the success of PROTO, there still exist three main problems: (1) ignore the randomness of the sampled support sets when computing prototype vectors; (2) disregard the importance of labeled samples; (3) construct meta-tasks in a purely random manner. In this paper, we propose a Meta-Learning Siamese Network, namely, Meta-SN, to address these issues. Specifically, instead of computing prototype vectors from the sampled support sets, Meta-SN utilizes external knowledge (e.g. class names and descriptive texts) for class labels, which is encoded as the low-dimensional embeddings of prototype vectors. In addition, Meta-SN presents a novel sampling strategy for constructing meta-tasks, which gives higher sampling probabilities to hard-to-classify samples. Extensive experiments are conducted on six benchmark datasets to show the clear superiority of Meta-SN over other state-of-the-art models. For reproducibility, all the datasets and codes are provided at https://github.com/hccngu/Meta-SN.
Recent work has shown that Large Language Models (LLMs) can be incredibly effective for offline reinforcement learning (RL) by representing the traditional RL problem as a sequence modelling problem (Chen et al., 2021; Janner et al., 2021). However many of these methods only optimize for high returns, and may not extract much information from a diverse dataset of trajectories. Generalized Decision Transformers (GDTs) (Furuta et al., 2021) have shown that utilizing future trajectory information, in the form of information statistics, can help extract more information from offline trajectory data. Building upon this, we propose Skill Decision Transformer (Skill DT). Skill DT draws inspiration from hindsight relabelling (Andrychowicz et al., 2017) and skill discovery methods to discover a diverse set of primitive behaviors, or skills. We show that Skill DT can not only perform offline state-marginal matching (SMM), but can discovery descriptive behaviors that can be easily sampled. Furthermore, we show that through purely reward-free optimization, Skill DT is still competitive with supervised offline RL approaches on the D4RL benchmark. The code and videos can be found on our project page: https://github.com/shyamsn97/skill-dt
Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds for exploring the translation challenges of turning literacy into numeracy. Previous publicly-available transformer models from eighteen months prior and 1000 times smaller failed to provide basic arithmetic. The statistical analysis of four complex datasets described here combines arithmetic manipulations that cannot be memorized or encoded by simple rules. The work examines whether next-token prediction succeeds from sentence completion into the realm of actual numerical understanding. For example, the work highlights cases for descriptive statistics on in-memory datasets that the LLM initially loads from memory or generates randomly using python libraries. The resulting exploratory data analysis showcases the model's capabilities to group by or pivot categorical sums, infer feature importance, derive correlations, and predict unseen test cases using linear regression. To extend the model's testable range, the research deletes and appends random rows such that recall alone cannot explain emergent numeracy.
The main goal of machine learning (ML) is to study and improve mathematical models which can be trained with data provided by the environment to infer the future and to make decisions without necessarily having complete knowledge of all influencing elements. In this work, we describe how ML can be a powerful tool in studying climate modeling. Tree ring growth was used as an implementation in different aspects, for example, studying the history of buildings and environment. By growing and via the time, a new layer of wood to beneath its bark by the tree. After years of growing, time series can be applied via a sequence of tree ring widths. The purpose of this paper is to use ML algorithms and Extreme Value Theory in order to analyse a set of tree ring widths data from nine trees growing in Nottinghamshire. Initially, we start by exploring the data through a variety of descriptive statistical approaches. Transforming data is important at this stage to find out any problem in modelling algorithm. We then use algorithm tuning and ensemble methods to improve the k-nearest neighbors (KNN) algorithm. A comparison between the developed method in this study ad other methods are applied. Also, extreme value of the dataset will be more investigated. The results of the analysis study show that the ML algorithms in the Random Forest method would give accurate results in the analysis of tree ring widths data from nine trees growing in Nottinghamshire with the lowest Root Mean Square Error value. Also, we notice that as the assumed ARMA model parameters increased, the probability of selecting the true model also increased. In terms of the Extreme Value Theory, the Weibull distribution would be a good choice to model tree ring data.
The advancement of social media contributes to the growing amount of content they share frequently. This framework provides a sophisticated place for people to report various real-life events. Detecting these events with the help of natural language processing has received researchers' attention, and various algorithms have been developed for this goal. In this paper, we propose a Semantic Modular Model (SMM) consisting of 5 different modules, namely Distributional Denoising Autoencoder, Incremental Clustering, Semantic Denoising, Defragmentation, and Ranking and Processing. The proposed model aims to (1) cluster various documents and ignore the documents that might not contribute to the identification of events, (2) identify more important and descriptive keywords. Compared to the state-of-the-art methods, the results show that the proposed model has a higher performance in identifying events with lower ranks and extracting keywords for more important events in three English Twitter datasets: FACup, SuperTuesday, and USElection. The proposed method outperformed the best reported results in the mean keyword-precision metric by 7.9\%.
The upper limb robotic exoskeleton is an electromechanical device which use to recover a patients motor dysfunction in the rehabilitation field. It can provide repetitive, comprehensive, focused, positive, and precise training to regain the joints and muscles capability. It has been shown that existing robotic exoskeletons are generally used rigid motors and mechanical structures. Soft robotic devices can be a correct substitute for rigid ones. Soft exosuits are flexible, portable, comfortable, user-friendly, low-cost, and travel-friendly. Somehow, they need expertise or therapist to assist those devices. Also, they cannot be adaptable to different patients with non-identical physical parameters and various rehabilitation needs. For that reason, nowadays we need intelligent exoskeletons during rehabilitation which have to learn from patients previous data and act according to it with patients intention. There also has a big gap between theoretical and practical applications for using those exoskeletons. Most of the intelligent exoskeletons are prototype in manner. To solve this problem, the robotic exoskeleton should be made both criteria as ergonomic and portable. The exoskeletons have to the power of decision-making to avoid the presence of expertise. In this growing field, the present trend is to make the exoskeleton intelligent and make it more reliable to use in clinical practice.
The brain constantly turns large flows of sensory information into selective representations of the environment. It, therefore, needs to learn to process those sensory inputs that are most relevant for behaviour. It is not well understood how learning changes neural circuits in visual and decision-making brain areas to adjust and improve its visually guided decision-making. To address this question, head-fixed mice were trained to move through virtual reality environments and learn visual discrimination while neural activity was recorded with two-photon calcium imaging. Previously, descriptive models of neuronal activity were fitted to the data, which was used to compare the activity of excitatory and different inhibitory cell types. However, the previous models did not take the internal representations and learning dynamics into account. Here, I present a framework to infer a model of internal representations that are used to generate the behaviour during the task. We model the learning process from untrained mice to trained mice within the normative framework of the ideal Bayesian observer and provide a Markov model for generating the movement and licking. The framework provides a space of models where a range of hypotheses about the internal representations could be compared for a given data set.
The COVID19 pandemic has challenged universities and organizations to devise mechanisms to uplift the well-being and welfare of people and communities. In response, the design and development of an integrated package of technologies, MangngalApp -- A web-based portal and mobile responsive application for rural development served as an opportunity. It showcases different packets of technologies that were outputs of R&D in the field of fisheries and aqua-culture, innovations that were IP-protected, and technologies that harness locally available resources for post-harvest development and aiding in sustaining growth and development in the communities. This paper focused on the usability and acceptability of the MangngalApp implementing a descriptive research design using the Technology Acceptance Model or TAM and ISO 25010 software quality standards. Constrained by government health restrictions due to COVID-19, a Google form-based questionnaire was forwarded to consented participants via an email with the attached consent and evaluation form. Results revealed that the MangngalApp was found to be very acceptable and usable, and compliant to ISO 25010 software quality characteristics to the higher extent. From the results, it is concluded that the developed MangngalApp will be a usable and responsive technology that aids to rural development especially among target users: fishers, gatherers, processors, traders, and farmers. Considering compatibility and usefulness, the MangngalApp is expected to provide greater social development in the community.
Advancements in Text-to-Image synthesis over recent years have focused more on improving the quality of generated samples using datasets with descriptive prompts. However, real-world image-caption pairs present in domains such as news data do not use simple and directly descriptive captions. With captions containing information on both the image content and underlying contextual cues, they become abstractive in nature. In this paper, we launch ANNA, an Abstractive News captioNs dAtaset extracted from online news articles in a variety of different contexts. We explore the capabilities of current Text-to-Image synthesis models to generate news domain-specific images using abstractive captions by benchmarking them on ANNA, in both standard training and transfer learning settings. The generated images are judged on the basis of contextual relevance, visual quality, and perceptual similarity to ground-truth image-caption pairs. Through our experiments, we show that techniques such as transfer learning achieve limited success in understanding abstractive captions but still fail to consistently learn the relationships between content and context features. The Dataset is available at https://github.com/aashish2000/ANNA .
Although remarkable progress on the neural table-to-text methods has been made, the generalization issues hinder the applicability of these models due to the limited source tables. Large-scale pretrained language models sound like a promising solution to tackle such issues. However, how to effectively bridge the gap between the structured table and the text input by fully leveraging table information to fuel the pretrained model is still not well explored. Besides, another challenge of integrating the deliberation mechanism into the text-to-text pretrained model for solving the table-to-text task remains seldom studied. In this paper, to implement the table-to-text generation with pretrained language model, we propose a table structure understanding and text deliberating approach, namely TASD. Specifically, we devise a three-layered multi-head attention network to realize the table-structure-aware text generation model with the help of the pretrained language model. Furthermore, a multi-pass decoder framework is adopted to enhance the capability of polishing generated text for table descriptions. The empirical studies, as well as human evaluation, on two public datasets, validate that our approach can generate faithful and fluent descriptive texts for different types of tables.
Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence and video segments on a single temporal resolution, while neglecting the temporal consistency of video content in different resolutions. In this work, we propose a novel multi-resolution temporal video sentence grounding network: MRTNet, which consists of a multi-modal feature encoder, a Multi-Resolution Temporal (MRT) module, and a predictor module. MRT module is an encoder-decoder network, and output features in the decoder part are in conjunction with Transformers to predict the final start and end timestamps. Particularly, our MRT module is hot-pluggable, which means it can be seamlessly incorporated into any anchor-free models. Besides, we utilize a hybrid loss to supervise cross-modal features in MRT module for more accurate grounding in three scales: frame-level, clip-level and sequence-level. Extensive experiments on three prevalent datasets have shown the effectiveness of MRTNet.
Recently, e-scooter-involved crashes have increased significantly but little information is available about the behaviors of on-road e-scooter riders. Most existing e-scooter crash research was based on retrospectively descriptive media reports, emergency room patient records, and crash reports. This paper presents a naturalistic driving study with a focus on e-scooter and vehicle encounters. The goal is to quantitatively measure the behaviors of e-scooter riders in different encounters to help facilitate crash scenario modeling, baseline behavior modeling, and the potential future development of in-vehicle mitigation algorithms. The data was collected using an instrumented vehicle and an e-scooter rider wearable system, respectively. A three-step data analysis process is developed. First, semi-automatic data labeling extracts e-scooter rider images and non-rider human images in similar environments to train an e-scooter-rider classifier. Then, a multi-step scene reconstruction pipeline generates vehicle and e-scooter trajectories in all encounters. The final step is to model e-scooter rider behaviors and e-scooter-vehicle encounter scenarios. A total of 500 vehicle to e-scooter interactions are analyzed. The variables pertaining to the same are also discussed in this paper.
Tongue cancer is a common oral cavity malignancy that originates in the mouth and throat. Much effort has been invested in improving its diagnosis, treatment, and management. Surgical removal, chemotherapy, and radiation therapy remain the major treatment for tongue cancer. The survival of patients determines the treatment effect. Previous studies have identified certain survival and risk factors based on descriptive statistics, ignoring the complex, nonlinear relationship among clinical and demographic variables. In this study, we utilize five cutting-edge machine learning models and clinical data to predict the survival of tongue cancer patients after treatment. Five-fold cross-validation, bootstrap analysis, and permutation feature importance are applied to estimate and interpret model performance. The prognostic factors identified by our method are consistent with previous clinical studies. Our method is accurate, interpretable, and thus useable as additional evidence in tongue cancer treatment and management.
Digital platforms, including online forums and helplines, have emerged as avenues of support for caregivers suffering from postpartum mental health distress. Understanding support seekers' experiences as shared on these platforms could provide crucial insight into caregivers' needs during this vulnerable time. In the current work, we provide a descriptive analysis of the concerns, psychological states, and motivations shared by healthy and distressed postpartum support seekers on two digital platforms, a one-on-one digital helpline and a publicly available online forum. Using a combination of human annotations, dictionary models and unsupervised techniques, we find stark differences between the experiences of distressed and healthy mothers. Distressed mothers described interpersonal problems and a lack of support, with 8.60% - 14.56% reporting severe symptoms including suicidal ideation. In contrast, the majority of healthy mothers described childcare issues, such as questions about breastfeeding or sleeping, and reported no severe mental health concerns. Across the two digital platforms, we found that distressed mothers shared similar content. However, the patterns of speech and affect shared by distressed mothers differed between the helpline vs. the online forum, suggesting the design of these platforms may shape meaningful measures of their support-seeking experiences. Our results provide new insight into the experiences of caregivers suffering from postpartum mental health distress. We conclude by discussing methodological considerations for understanding content shared by support seekers and design considerations for the next generation of support tools for postpartum parents.