-
The 2018 Davis Challenge on Video Object Segmentation
The 2018 davis challenge on video object segmentation -
CobNet: Cross Attention on Object and Background
Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples. -
Catch Me if You Can: A Novel Task for CGL Detection
A novel task for detection of covert geo-locations (CGL) in images. -
Improved Object-Based Style Transfer with Single Deep Network
The proposed approach uses a single deep network of YOLOv8 for both segmentation and style transfer. -
SAM3D Dataset
The SAM3D dataset is a custom dataset created for the SAM3D paper, containing 798 training sequences, 202 validation sequences, and 150 testing sequences. -
ShapeStacks
Unsupervised multi-object segmentation using attention and soft-argmax -
ObjectsRoom
Unsupervised multi-object segmentation using attention and soft-argmax -
Fast video object segmentation by reference-guided mask propagation
The SegTrack v2 dataset is a benchmark for video object segmentation. -
Youtube-VOS: Sequence-to-sequence video object segmentation
The YouTube-VOS dataset is a benchmark for video object segmentation. -
DAVIS 2017: A Benchmark for Video Object Segmentation
The DAVIS dataset is a benchmark for video object segmentation. -
DAVIS and YouTube-VOS datasets
The DAVIS dataset comprises 60, 30 and 30 video sequences for training, validation and testing, respectively. The YouTube-VOS dataset is a larger dataset with 3471 videos for... -
Pascal Visual Object Classes (VOC) Challenge
The Pascal Visual Object Classes (VOC) challenge is a benchmark for object detection and segmentation. -
WISDOM dataset
The dataset used in the paper is a WISDOM dataset for object instance segmentation.
