25 datasets found

Particle track reconstruction based on deep learning methods

A roadside LiDAR-based detection and tracking approach for pedestrians and vehicles

The dataset used in this paper is a proprietary administrative data from Statistics Netherlands on all students that take the standardized end-of-primary education test in the...

PETA dataset is a large-scale person re-identification dataset that contains binary and multi-class attribute annotations.

The dataset used in this paper is a set of ray-tracing based evaluations at the 26 GHz NR band, containing measurements of ToA, TDoA, and AoA.

The MeEM tracker uses multiple experts to track objects.

The Visual Tracking Benchmark (VTB) is a collection of 50 videos.

The online tracking benchmark (OTB) is a collection of 50 videos.

The proposed Siamese Instance Search Tracker, SINT, tracks the target by matching the initial target in the first frame with candidates in a new frame and returns the most...

PointOdyssey is a large-scale synthetic dataset for long-term point tracking, providing pixel-perfect annotation of point trajectories across long continuous videos.

The VisDrone-SOT2019 dataset is a large-scale drone benchmark for single object tracking.

Object detection on Unmanned Aerial Vehicles (UAVs) is still a challenging task. The recordings are mostly sparse and contain only small objects.

A multi-camera HD dataset for dense unscripted pedestrian detection

The DTB70 dataset is a large-scale benchmark for drone object detection and tracking.

The image object detection track on VisDrone2018 provides a dataset of 10,209 images, with 10 categories of pedestrians, vehicles, and other traffic objects annotated.

Object permanence is the concept that objects in a physical world continue to exist despite the observers inability to sense them. This can result in temporally unstable...

BEHAVE: Dataset and method for tracking human object interactions.

An experimental study for tracking ability of deep q-network.

The BEHAVE dataset is annotated with text descriptions for 3D human-object interactions.

The SoBiR dataset is used for soft biometric retrieval. It contains 8 camera views, 100 persons, and categorical annotations.