19,997 machine learning datasets
19,997 dataset results
This dataset contains 500K high photo-real rendered images of 10 real head models with (yaw, pitch, roll) head pose labels. Each head is rendered with a different pose and environmental lighting.
The UMAD is a virtual-scene dataset made by AirSim, which is a simulator built on Unreal Engine. In order to ensure the simulation data is as close to real as possible, on the one hand, we use a realistic city scene model which comes from Kirill Sibiriakov, on the other hand, we collect the vehicle motion data and camera data separately to enable the frequency and quality, which is derived from the method in the paper. In comparison to urban datasets which are created by using the oblique aerial photography technique, our dataset has higher fidelity when it comes to the texture details
STDW is a diverse large-scale dataset for table detection with more than seven thousand samples containing a wide variety of table structures collected from many diverse sources.
WildQA is a video understanding dataset of videos recorded in outside settings. The dataset can be used to evaluate models for video question answering.
In this dataset two robots, Baxter and UR5, perform 8 behaviors (look, grasp, pick, hold, shake, lower, drop, and push) on 95 objects that vary by 5 color (blue, green, red, white, and yellow), 6 contents (wooden button, plastic dices, glass marbles, nuts & bolts, pasta, and rice), and 4 weights (empty, 50g, 100g, and 150g). There are 90 objects with contents (5 colors x 3 weights x 6 contents) and 5 objects without any content that only vary by 5 colors. Both robots perform 5 trials on each object, resulting in 7,600 interactions (2 robots x 8 behaviors x 95 objects x 5 trials
UTSig (University of Tehran Persian Signature) dataset is freely available at MLCM lab website: http://mlcm.ut.ac.ir/Datasets.html Persian offline signature dataset, UTSig. This rich dataset consists of significant numbers of classes and samples, where aforementioned variables are considered during signature collection procedure. UTSig provides the research community with the opportunity to train, test, and compare different Persian offline SVSs, and to evaluate different culture-independent classifiers on a rich dataset by using its proposed standard experimental setups.
We present CSL, a large-scale Chinese Scientific Literature dataset, which contains the titles, abstracts, keywords and academic fields of 396,209 papers. To our knowledge, CSL is the first scientific document dataset in Chinese.
Dataset outline This repository contains a novel time-series dataset for impact detection and localization on a plastic thin-plate, towards Structural Health Monitoring applications, using ceramic piezoelectric transducers (PZTs) connected to an Internet of Things (IoT) device. The dataset was collected from an experimental procedure of low-velocity, low-energy impact events that includes at least 3 repetitions for each unique experiment, while the input measurements come from 4 PZT sensors placed at the corners of the plate. For each repetition and sensor, 5000 values are stored with 100 KHz sampling rate. The system is excited with a steel ball, and the height from which it is released varies from 10 cm to 20 cm.
The FEIDEGGER (fashion images and descriptions in German) dataset is a new multi-modal corpus that focuses specifically on the domain of fashion items and their visual descriptions in German. The dataset was created as part of ongoing research at Zalando into text-image multi-modality in the area of fashion.
This dataset is useful for doing research in the field of mars surface monocular depth estimation. The dataset is composed of 250k patches where each patch is a 3-channels 512 x 512 raster. The first two channels are respectively left and right images of the stereo pair while the third channel is the DTM. Because DTMs are saved with absolute values you have to preprocess in case you want to predict relative values. The Dataset size is 800 GB.
The ArtFID dataset contains around 250k labeled artworks.
We present the first fine-grained dataset of 1,497 3D VR sketch and 3D shape pairs for 1,005 chair shapes with large shapes diversity from the ShapeNetCore dataset from 50 participants.
KArSL (KFUPM Arabic Sign Language) is an Arabic sign language (ArSL) database collected using Microsoft Kinect V2. The database consists of 502 sign words constituting the sign words of eleven chapters of ArSL dictionary (Letters, Numbers, Health, Common verbs, Family, Characteristics, Directions and places, Social relationships, In house, Religion, and Jobs and professions). Each sign of the database is performed by three professional signers. The signers involved in this database are all male and their age is between 30 and 40 years. Each signer repeated each sign 50 times which resulted in a total of 75,300 samples of the whole database (502 x 3 x 50) as shown in the table below.
High-resolution thermal infrared face database with extensive manual annotations, introduced by Kopaczka et al, 2018. Useful for training algoeithms for image processing tasks as well as facial expression recognition. The full database itself, all annotations and the complete source code are freely available from the authors for research purposes at https://github.com/marcinkopaczka/thermalfaceproject.
Data used for the paper Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices.
Inspired by OpenAI dexterous in-hand manipulation, we collected a synthetic RGB-D dataset of a Shadow Hand robot manipulating a cube towards arbitrary goal configurations. This dataset consists of about 10000 videos, each video including 25 RGB-D frames. DexHand is challenging as the robot has 24 degrees of freedom, and there can be a significant amount of motion and occlusion between consecutive frames.
Omnipush is a dataset with high variety of planar pushing behavior. The dataset contains 250 pushes for each of 250 objects, all recorded with RGB-D and high precision state tracking. The objects are constructed to explore key factors that affect pushing --the shape of the object and its mass distribution-- which have not been broadly explored in previous datasets and allow to study generalization in model learning.
To explore the nascent area of sustainable venture capital, a review of related research was conducted and social entrepreneurs & investors interviewed to construct a questionnaire assessing the interests and intentions of current & future ecosystem participants. Analysis of 114 responses received via several sampling methods revealed statistically significant relationships between investing preferences and genders, generations, sophistication, and other variables, all the way down to the level of individual UN Sustainable Development Goals (SDGs).
ViPhy leverages two datasets: Visual Genome (Krishna et al., 2017), and ADE20K (Zhou et al., 2017). The dense captions in Visual Genome provide a broad coverage of object classes, making it a suitable resource for collecting subtype candidates. For extracting hyponyms from knowledge base, we acquire "is-a" relations from ConceptNet (Speer et al., 2017), and augment the subtype candidate set. We extract spatial relations from ADE20K, as it provides images categorised by scene type – primarily indoor environments with high object density: {bedroom, bathroom, kitchen, living room, office}.
WikiDes is a dataset for generating descriptions of Wikidata from Wikipedia paragraphs.