HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Unsupervised Video Object Segmentation On 12

Metrics

J

Results

Performance results of various models on this benchmark

Model Name
J
Paper TitleRepository
TMO (MiT-b1)71.1Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation-
WCS-Net70.5Unsupervised Video Object Segmentation with Joint Hotspot Tracking-
TMO++ (RN-101)73.1Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation-
PDB65.5Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection-
MATNet69.0Motion-Attentive Transition for Zero-Shot Video Object Segmentation-
AGNN70.8Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks-
RTNet70.1Reciprocal Transformations for Unsupervised Video Object Segmentation
TMO (RN-101)71.5Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation-
TMO++ (MiT-b1, MS)73.5Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation-
AMP75.0Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation-
FakeFlow75.1Improving Unsupervised Video Object Segmentation via Fake Flow Generation-
DPA73.7Dual Prototype Attention for Unsupervised Video Object Segmentation-
COSNet70.5See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks-
AMC-Net71.1Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation-
AGS69.7Learning Unsupervised Video Object Segmentation Through Visual Attention-
TMO++ (MiT-b1)73.0Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation-
0 of 16 row(s) selected.
Unsupervised Video Object Segmentation On 12 | SOTA | HyperAI