Unsupervised Video Object Segmentation On 12

Results

Performance results of various models on this benchmark

		Paper Title
FakeFlow	75.1	Improving Unsupervised Video Object Segmentation via Fake Flow Generation
AMP	75.0	Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation
DPA	73.7	Dual Prototype Attention for Unsupervised Video Object Segmentation
TMO++ (MiT-b1, MS)	73.5	Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
TMO++ (RN-101)	73.1	Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
TMO++ (MiT-b1)	73.0	Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
TMO (RN-101)	71.5	Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
TMO (MiT-b1)	71.1	Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
AMC-Net	71.1	Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation
AGNN	70.8	Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
WCS-Net	70.5	Unsupervised Video Object Segmentation with Joint Hotspot Tracking
COSNet	70.5	See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
RTNet	70.1	Reciprocal Transformations for Unsupervised Video Object Segmentation
AGS	69.7	Learning Unsupervised Video Object Segmentation Through Visual Attention
MATNet	69.0	Motion-Attentive Transition for Zero-Shot Video Object Segmentation
PDB	65.5	Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection

0 of 16 row(s) selected.