48 datasets found

The Waymo Open dataset is a large-scale video dataset used for testing object-centric video models.

A large multi-modal benchmark for UAV tracking, containing high-quality and high-definition video sequences of both RGB and IR, each annotated with bounding boxes, attributes,...

Visual object tracking, which tracks a specified target in a changing video sequence automatically, is a fundamental problem in many topics such as visual analysis, automatic...

The HOT-2023 dataset is a hyperspectral object tracking dataset, which consists of 110 training videos and 87 validation videos. The dataset includes 16, 15, and 25 bands for...

The HOT-2022 dataset is a hyperspectral object tracking dataset, which consists of 40 training videos and 35 testing videos. The dataset includes 16 bands and has a resolution...

The CDTB dataset is a color and depth visual object tracking dataset used for evaluating the performance of object tracking algorithms.

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...

The dataset used for litter detection and tracking using deep learning techniques.

The dataset used in this paper for tracking intracellular protein growth dynamics.

The STC dataset is a short-text conversation dataset collected from Sina Weibo, a Chinese social platform.

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.

The ImageNet VID dataset is a large scale benchmark for video object detection task consisting of 3,862 videos in the training set and 555 videos in the validation set. 30...

Dynamic 3D Gaussians: Tracking by persistent dynamic view synthesis.

RGB-T object tracking: benchmark and baseline