23 datasets found

The TC-128 dataset is a benchmark for visual tracking, containing 128 videos with 128 frames each.

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

The source code will be made available to the public.

The CVPR2013 tracking benchmark dataset and code library, which includes 29 trackers and 50 fully-annotated videos (more than 29,000 frames).

The OTB-100 and OTB-50 datasets are used in the experiments to evaluate the performance of the Convolutional Regression framework for visual tracking.

The Convolutional Regression framework for visual tracking is proposed in this paper. The framework uses a single convolution layer to learn a regression model for visual tracking.

The VOT2015/VOT2017 datasets are used for visual tracking evaluation.

The OTB-2013/OTB-2015 datasets are used for visual tracking evaluation.

Visual tracking is one of the most fundamental topics in computer vision. It has great demands in many public occasions such as surveillance system, self-driving cars, etc.

High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and...

The visual object tracking vot2016 challenge results

The visual object tracking vot2015 challenge results

The OTB100 dataset is an extension of the OTB50 dataset, containing 100 videos with 1000 frames each.

Visual object tracking is a fundamental problem in many aspects such as visual analysis, automatic driving, pose tracking, robotics, and more.

The dataset used in the paper is the OTB100, VOT2016 and VOT2017 datasets for visual tracking.

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

The NFS30 dataset contains 100 videos and a length of 380K frames in total.

The proposed SiamCorners method for visual tracking, which detects a target as a pair of corners. A common Siamese network is used to integrate target-specific information into...

The dataset used for tracking the air-hockey puck using an event-based camera.

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