71 datasets found

The Davis dataset is a benchmark for video object segmentation. It contains 30 videos with 40 frames each.

Ref-Youtube-VOS is an extensive referring video object segmentation dataset that comprises approximately 15,000 referring expressions associated with more than 3,900 videos.

The Associating Objects with Transformers for video object segmentation.

The Feature Aligned Memory Network for video object segmentation.

Video object segmentation is a fundamental task in many important areas such as autonomous driving, robotic manipulation, video surveillance, and video editing.

Video segmentation by tracking many figure-ground segments.

The FBMS dataset contains 29 training videos and 30 test videos.

A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation.

URVOS: Unified referring video object segmentation network with a large-scale benchmark.

RefVOS: a closer look at referring expressions for video object segmentation.

The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video.

The DAVIS dataset is a widely used dataset for video-related tasks, consisting of approximately 2000 frames from 26 human-centric scenarios.

A benchmark dataset and evaluation methodology for video object segmentation.

Unsupervised video object segmentation has made significant progress in recent years, but the manual annotation of video mask datasets is expensive and limits the diversity of...

Video object segmentation is a crucial task in computer vision that involves segmenting primary objects in a video sequence.

Unsupervised video object segmentation has made significant progress in recent years, but the manual annotation of video mask datasets is expensive and limits the diversity of...

This paper proposes a novel and efficient approach for video object segmentation by associating objects with transformers.

The YouTube-VOS 2018 dataset is a large-scale benchmark for video object segmentation.

Semi-supervised video object segmentation (VOS) aims to track the designated objects present in the initial frame of a video at the pixel level.

The DAVIS-2017 TrainVal dataset contains 90 video clips with diverse scenes and complex motions.