28 datasets found

The dataset used for video object segmentation task, where a first frame labelled with the foreground object mask, the goal is to find the corresponding object pixels in future...

The dataset used for video object segmentation task, where a first frame labelled with the masks of several object instances, one aims to find the corresponding masks of objects...

The dataset used for video object segmentation task, where a first frame labelled with the masks of several object instances, one aims to find the corresponding masks of objects...

A benchmark dataset for long duration video sequence.

Maritime vessel detection and tracking dataset

KITTI tracking dataset provides 21 training and 29 test sequences. The dataset provides 2D bounding box annotations for cars, pedestrians, and 6 other classes, but only the...

The dataset used for the MOT20 challenge, which consists of 8 different sequences depicting very crowded challenging scenes.

The dataset used in the paper is a collection of sequences with patterns of different shapes and speeds, and a new dataset collected with the Baxter robot in a manipulation task...

The authors proposed a large-scale benchmark for object tracking in the wild.

The authors proposed a large-scale benchmark for object tracking in the wild.

The BDD100K MOTS dataset is a subset of the BDD100K dataset, containing 154 videos with annotation for training and validation, and 37 videos for testing.

The TAO MOT dataset is a large-scale benchmark for tracking any object.

The Change Detection Dataset contains realistic, diverse set of videos with pixel-wise labeling of moving objects.

The GBOT dataset is a synthetic dataset designed for 6D object pose/tracking tasks.

The MOT16 and MOT17 datasets are used for evaluating the performance of multi-object tracking algorithms.

UAV20L is a small-scale long-term tracking dataset, consisting of 20 long videos.

VOT-ST 2021 is a visual object tracking benchmark, consisting of 20 long videos.

LVOS is a long-term video object segmentation benchmark dataset, consisting of 220 videos with a total duration of 421 minutes.

The MOTS Challenge dataset is a real-world video dataset consisting of pedestrian tracking and segmentation.

The Behave dataset contains various scenes with human-object interactions, and is used to evaluate the proposed object-level 3D semantic mapping approach.