HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Unsupervised Video Object Segmentation On 11

Metrics

J

Results

Performance results of various models on this benchmark

Model Name
J
Paper TitleRepository
TMO (MiT-b1)80.0Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation-
TMO++ (MiT-b1)83.2Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation-
MATNet76.1Motion-Attentive Transition for Zero-Shot Video Object Segmentation-
GSANet83.1Guided Slot Attention for Unsupervised Video Object Segmentation-
TransportNet78.7Deep Transport Network for Unsupervised Video Object Segmentation-
IMP77.5Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier-
TMO++ (RN-101)81.2Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation-
PDB74.0Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection-
AMC-Net76.5Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation-
COSNet75.6See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks-
DPA83.4Dual Prototype Attention for Unsupervised Video Object Segmentation-
F2Net77.5F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation-
FakeFlow84.7Improving Unsupervised Video Object Segmentation via Fake Flow Generation-
TMO (RN-101)79.9Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation-
PMN77.7Unsupervised Video Object Segmentation via Prototype Memory Network-
0 of 15 row(s) selected.
Unsupervised Video Object Segmentation On 11 | SOTA | HyperAI