51 datasets found

A new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, the objective is to simultaneously segment and track...

The TrackingNet dataset is a benchmark for visual tracking, containing 511 video sequences with varying difficulties.

Deep Neural Networks (DNNs) are universal function approximators providing state-of-the-art solutions on wide range of applications. Common perceptual tasks such as speech...

The TrackFormer dataset is a large-scale object tracking dataset, containing 10K frames and 100 object categories.

The GOT-10K dataset is a large-scale object tracking dataset, containing 10K frames and 100 object categories.

OTB2015 is a pioneering testing set for single object tracking that consists of 100 challenging frames collected from YouTube.

The LaSOT dataset is a large-scale benchmark for visual tracking, containing 1400 video sequences with varying difficulties.

The UAV123 dataset is a benchmark for visual tracking, containing 123 video sequences with varying difficulties.

The VOT2018 dataset contains 60 videos and 100 frames for visual object tracking.

The OTB100 dataset contains 100 videos and 60 frames for visual object tracking.

The dataset is a collection of 3D point clouds for object tracking.