Video Object Segmentation on DAVIS 2016

48개 결과 · ⬇ CSV · JSON

J&F

Rank	Model	J&F	F-Score	Jaccard (Mean)	mIoU	Contour Accuracy	Extra Training Data	Paper	Code	Year
1	ISVOS (BL30K, MS)	93.4	94.2	92.5	–	–		Look Before You Match: Instance Understanding Matters in Video Object Segmentation		2022
2	XMem (BL30K, MS)	93.3	94.4	92.2	–	–		XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model	hkchengrex/XMem · tianyuan168326/videosemanticcompression-pytorch	2022
3	BATMAN (val)	92.5	94.2	90.7	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
4	STCN (val)	91.6	92.5	90.8	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
5	XMem	91.5	92.7	90.4	–	–		XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model	hkchengrex/XMem · tianyuan168326/videosemanticcompression-pytorch	2022
6	MobileVOS (val)	91.4	92.6	90.3	–	–		MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation		2023
7	AOT (val)	91.1	92.1	90.1	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
8	LCM (val)	90.7	91.4	89.9	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
9	RPCMVOS (val)	90.6	94	87.1	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
10	KMN (val)	90.5	91.5	89.5	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
10	TransVOS (val)	90.5	91.2	89.8	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
12	CFBI+ (val)	89.9	91.1	88.7	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
13	ViTAE-T-Stage	89.8	90.4	89.2	–	–		ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias	ViTAE-Transformer/ViTAE-Transformer · Annbless/ViTAE	2021
14	CFBI (val)	89.4	90.5	88.3	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
15	RMN (val)	88.8	88.7	88.9	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
16	AOC-MF (val)	–	94.7	88.5	–	–		Towards Robust Video Object Segmentation with Adaptive Object Calibration	jerryx1110/robust-video-object-segmentation	2022
17	STM (val)	–	89.9	88.7	–	–		BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation		2022
18	3DC-Seg	–	84.7	84.3	–	–	✓	Making a Case for 3D Convolutions for Object Segmentation in Videos	sabarim/3DC-Seg	2020
19	DFNet	–	81.8	–	–	–		Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation		2020
20	Ours	–	–	83.4	–	–		Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation		2020