19,997 machine learning datasets
19,997 dataset results
Dialog System Technology Challenges 8 (DSTC) Track 2 builds on the success of DSTC 7 Track 1 (NOESIS: Noetic End-to-End Response Selection Challenge). It proposes an extension of the task, incorporating new elements that are vital for the creation of a deployed task-oriented dialogue system. Specifically, three new dimensions are added to the challenge:
BABEL is a multilingual corpus of conversational telephone speech from IARPA, which includes Asian and African languages.
Reflectance measurements of Bidirectional Texture Functions (BTFs)
MAEC is a new, large-scale multi-modal, text-audio paired, earnings-call dataset named MAEC, based on S&P 1500 companies.
The RSNA Pulmonary Embolism CT (RSPECT) Dataset is composed of CT pulmonary angiogram images and annotations related to pulmonary embolism. It's part of the 2020 RSNA Pulmonary Embolism Detection Challenge which invited researchers to develop machine-learning algorithms to detect and characterize instances of pulmonary embolism (PE) on chest CT studies. The competition, conducted in collaboration with the Society of Thoracic Radiology (STR), involved creating the largest publicly available annotated PE dataset, comprised of more than 12,000 CT studies. Imaging data was contributed by five international research centers and labeled with detailed clinical annotations by a group of more than 80 expert thoracic radiologists. For the first time in an RSNA data challenge, the rules required competitors to submit and run their code in a standard shared environment, producing simpler, more readily usable models.
FluencyBank is a shared database for the study of fluency development. Participants include typically-developing monolingual and bilingual children, children and adults who stutter (C/AWS) or who clutter (C/AWC), and second language learners.
The Unsplash Dataset is created by over 200,000 contributing photographers and billions of searches across thousands of applications, uses, and contexts. It contains over 2M Unsplash images.
The L1000 dataset consists of ~1,400,000 gene-expression profiles on the responses of ~50 human cell lines to one of ~20,000 compounds across a range of concentrations. The L1000 dataset and its normalization versions10 were recently widely used in drug repurposing and discovery.
A great number of situational comedies (sitcoms) are being regularly made and the task of adding laughter tracks to these is a critical task. Providing an ability to be able to predict whether something will be humorous to the audience is also crucial. In this project, we aim to automate this task. Towards doing so, we annotate an existing sitcom (Big Bang Theory') and use the laughter cues present to obtain a manual annotation for this show. We provide detailed analysis for the dataset design and further evaluate various state of the art baselines for solving this task. We observe that existing LSTM and BERT based networks on the text alone do not perform as well as joint text and video or only video-based networks. Moreover, it is challenging to ascertain that the words attended to while predicting laughter are indeed humorous. Our dataset and analysis provided through this paper is a valuable resource towards solving this interesting semantic and practical task. As an additional con
In an active e-commerce environment, customers process a large number of reviews when deciding on whether to buy a product or not. Abstractive Multi-Review Summarization aims to assist users to efficiently consume the reviews that are the most relevant to them. We propose the first large-scale abstractive multi-review summarization dataset that leverages more than 17.9 billion raw reviews and uses novel aspect-alignment techniques based on aspect annotations. Furthermore, we demonstrate that one can generate higher-quality review summaries by using a novel aspect-alignment-based model. Results from both automatic and human evaluation show that the proposed dataset plus the innovative aspect-alignment model can generate high-quality and trustful review summaries.
UFO Cherry Tree Point Clouds consists of a collection of 82 scanned Upright Fruiting Offshoot (UFO) cherry tree point clouds.
This dataset is a hash that uses as key the normalized movie name (for instance, {\sf TheAvengers} and as value an array of all the tropes used in that specific movie, as reported by TVTropes.org users.
Current approaches to context-aware MT rely on a set of surface heuristics to translate pronouns, which break down when translations require real reasoning. We create a new template test set ContraCAT to assess the ability of Machine Translation to handle the specific steps necessary for successful pronoun translation.
SynD is a synthetic energy dataset with a focus on residential buildings. This dataset is the result of a custom simulation process that relies on power traces of household appliances. The output of simulations is the power consumption of 21 household appliances as well as the household-wide consumption (i.e. mains). Therefore, SynD's can be used for Non-Intrusive Load Monitoring, also referred to as Energy Disaggregation.
we propose the augmented KITTI dataset with fog for both camera and LiDAR sensors with different visibility ranges from 20 to 80 meters to best match realistic fog environment.
A dog face dataset for dog face verification and recognition/identification.
The Follicular-Segmentation dataset consists of 6900 cropped typical image patches of 1024x1024 pixels containing: follicular areas, colloid areas, and the other blank background areas.
Toronto NeuroFace Dataset: A New Dataset for Facial Motion Analysis in Individuals with Neurological Disorders