3,275 machine learning datasets
3,275 dataset results
VLM²-Bench: Benchmarking Vision-Language Models on Visual Cue Matching Description VLM²-Bench is the first comprehensive benchmark designed to evaluate vision-language models' (VLMs) ability to visually link matching cues across multi-image sequences and videos. The benchmark consists of 9 subtasks with over 3,000 test cases, focusing on fundamental visual linking capabilities that humans use daily. A key example is identifying the same person across different photos without prior knowledge of their identity.
Most existing MOT datasets are captured using pinhole cameras, which are characterized by a narrow-FoV and linear sensor motion. However, when panoramic-FoV capture devices experience even slight movements, the entire scene can change drastically, posing significant challenges for object tracking. QuadTrack addresses this challenge by providing a benchmark specifically designed to test MOT algorithms under dynamic, non-linear motion conditions. It enables evaluating algorithm robustness in tracking objects with panoramic, non-uniform motion.
3DFAW contains 23k images with 66 3D face keypoint annotations.
FERG is a database of cartoon characters with annotated facial expressions containing 55,769 annotated face images of six characters. The images for each character are grouped into 7 types of cardinal expressions, viz. anger, disgust, fear, joy, neutral, sadness and surprise.
The application-oriented license plate (AOLP) benchmark database has 2049 images of Taiwan license plates. This database is categorized into three subsets: access control (AC) with 681 samples, traffic law enforcement (LE) with 757 samples, and road patrol (RP) with 611 samples. AC refers to the cases that a vehicle passes a fixed passage with a lower speed or full stop. This is the easiest situation. The images are captured under different illuminations and different weather conditions. LE refers to the cases that a vehicle violates traffic laws and is captured by roadside camera. The background are really cluttered, with road sign and multiple plates in one image. RP refers to the cases that the camera is held on a patrolling vehicle, and the images are taken with arbitrary viewpoints and distances.
DeepLoc is a large-scale urban outdoor localization dataset. The dataset is currently comprised of one scene spanning an area of 110 x 130 m, that a robot traverses multiple times with different driving patterns. The dataset creators use a LiDAR-based SLAM system with sub-centimeter and sub-degree accuracy to compute the pose labels that provided as groundtruth. Poses in the dataset are approximately spaced by 0.5 m which is twice as dense as other relocalization datasets.
The Airport dataset is a dataset for person re-identification which consists of 39,902 images and 9,651 identities across six cameras.
APRICOT is a collection of over 1,000 annotated photographs of printed adversarial patches in public locations. The patches target several object categories for three COCO-trained detection models, and the photos represent natural variation in position, distance, lighting conditions, and viewing angle.
The ATRW Dataset contains over 8,000 video clips from 92 Amur tigers, with bounding box, pose keypoint, and tiger identity annotations.
The Cityscapes Panoptic Parts dataset introduces part-aware panoptic segmentation annotations for the Cityscapes dataset. It extends the original panoptic annotations for the Cityscapes dataset with part-level annotations for selected scene-level classes.
Cops-Ref is a dataset for visual reasoning in context of referring expression comprehension with two main features.
Under a close collaboration with an expert radiologist team of the Hospital Universitario San Cecilio, the COVIDGR-1.0 dataset of patients' anonymized X-ray images has been built. 852 images have been collected following a strict labeling protocol. They are categorized into 426 positive cases and 426 negative cases. Positive images correspond to patients who have been tested positive for COVID-19 using RT-PCR within a time span of at most 24h between the X-ray image and the test. Every image has been taken using the same type of equipment and with the same format: only the posterior-anterior view is considered.
Collects shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. The dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types.
DOTmark is a benchmark for discrete optimal transport, which is designed to serve as a neutral collection of problems, where discrete optimal transport methods can be tested, compared to one another, and brought to their limits on large-scale instances. It consists of a variety of grayscale images, in various resolutions and classes, such as several types of randomly generated images, classical test images and real data from microscopy.
Contains 446,684 images annotated by humans that cover 43 incidents across a variety of scenes.
Labeled Pedestrian in the Wild (LPW) is a pedestrian detection dataset that contains 2,731 pedestrians in three different scenes where each annotated identity is captured by from 2 to 4 cameras. The LPW features a notable scale of 7,694 tracklets with over 590,000 images as well as the cleanliness of its tracklets. It distinguishes from existing datasets in three aspects: large scale with cleanliness, automatically detected bounding boxes and far more crowded scenes with greater age span. This dataset provides a more realistic and challenging benchmark, which facilitates the further exploration of more powerful algorithms.
MeGlass is an eyeglass dataset originally designed for eyeglass face recognition evaluation. All the face images are selected and cleaned from MegaFace. Each identity has at least two face images with eyeglass and two face images without eyeglass. It contains 47,817 images from 1,710 different identities.
An open dataset of real photographs with real noise, from identical scenes captured with varying ISO values. Most images are taken with a Fujifilm X-T1 and XF18-55mm, other photographers are encouraged to contribute images for a more diverse crowdsourced effort.
OpenViDial is a large-scale open-domain dialogue dataset with visual contexts. The dialogue turns and visual contexts are extracted from movies and TV series, where each dialogue turn is paired with the corresponding visual context in which it takes place. OpenViDial contains a total number of 1.1 million dialogue turns, and thus 1.1 million visual contexts stored in images.
The RIT-18 dataset was built for the semantic segmentation of remote sensing imagery. It was collected with the Tetracam Micro-MCA6 multispectral imaging sensor flown on-board a DJI-1000 octocopter.