Referring Video Object Segmentation 벤치마크

Referring Video Object Segmentation on Refer-YouTube-VOS

36개 결과 · ⬇ CSV · JSON

J&F

Rank	Model	J&F	J	F	Extra Training Data	Paper	Code	Year
1	FindTrack	73.7	71.8	75.7	✓	Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation	suhwan-cho/FindTrack	2025
2	GLEE-Pro	70.6	68.2	72.9	✓	General Object Foundation Model for Images and Videos at Scale	FoundationVision/GLEE	2023
3	HyperSeg	68.5	–	–	✓	HyperSeg: Towards Universal Visual Segmentation with Large Language Model	congvvc/HyperSeg	2024
4	GLEE-Plus	67.7	65.6	69.7	✓	General Object Foundation Model for Images and Videos at Scale	FoundationVision/GLEE	2023
5	HTR	67.1	65.3	68.9	✓	Temporally Consistent Referring Video Object Segmentation with Hybrid Memory	bo-miao/HTR	2024
6	SOC	66.0	64.1	67.9	✓	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation	RobertLuo1/NeurIPS2023_SOC	2023
7	SgMg	65.7	63.9	67.4	✓	Spectrum-guided Multi-granularity Referring Video Object Segmentation	bo-miao/sgmg	2023
8	VATEX	65.4	63.3	67.5		Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding	nero1342/VATEX	2024
9	VLT	63.8	61.9	65.6	✓	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation	henghuiding/Vision-Language-Transformer	2022
10	HTML-SwinL	63.4	61.5	65.3	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
10	HTML-Video-SwinB	63.4	61.5	65.2	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
12	ReferFormer (Large)	62.9	61.3	64.6	✓	Language as Queries for Referring Video Object Segmentation	wjn922/referformer	2022
13	HTML-Video-SwinS	61.4	59.9	62.9	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
14	HTML-Video-SwinT	61.2	59.5	63.0	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
15	R2VOS (Swin-T)	60.2	58.9	61.5		Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus	lxa9867/R2VOS	2022
16	HTML-ResNet101	58.5	57.3	59.8	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
17	HTML-ResNet50	57.8	56.5	59.0	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
18	CMSA	36.4	34.8	38.1	✓	Cross-Modal Self-Attention Network for Referring Image Segmentation	lwye/CMSA-Net	2019
19	FindTrack	73.7	71.8	75.7	✓	Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation	suhwan-cho/FindTrack	2025
20	GLEE-Pro	70.6	68.2	72.9	✓	General Object Foundation Model for Images and Videos at Scale	FoundationVision/GLEE	2023
21	HyperSeg	68.5	–	–	✓	HyperSeg: Towards Universal Visual Segmentation with Large Language Model	congvvc/HyperSeg	2024
22	GLEE-Plus	67.7	65.6	69.7	✓	General Object Foundation Model for Images and Videos at Scale	FoundationVision/GLEE	2023
23	HTR	67.1	65.3	68.9	✓	Temporally Consistent Referring Video Object Segmentation with Hybrid Memory	bo-miao/HTR	2024
24	SOC	66.0	64.1	67.9	✓	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation	RobertLuo1/NeurIPS2023_SOC	2023
25	SgMg	65.7	63.9	67.4	✓	Spectrum-guided Multi-granularity Referring Video Object Segmentation	bo-miao/sgmg	2023
26	VATEX	65.4	63.3	67.5		Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding	nero1342/VATEX	2024
27	VLT	63.8	61.9	65.6	✓	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation	henghuiding/Vision-Language-Transformer	2022
28	HTML-SwinL	63.4	61.5	65.3	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
28	HTML-Video-SwinB	63.4	61.5	65.2	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
30	ReferFormer (Large)	62.9	61.3	64.6	✓	Language as Queries for Referring Video Object Segmentation	wjn922/referformer	2022
31	HTML-Video-SwinS	61.4	59.9	62.9	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
32	HTML-Video-SwinT	61.2	59.5	63.0	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
33	R2VOS (Swin-T)	60.2	58.9	61.5		Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus	lxa9867/R2VOS	2022
34	HTML-ResNet101	58.5	57.3	59.8	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
35	HTML-ResNet50	57.8	56.5	59.0	✓	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation		2023
36	CMSA	36.4	34.8	38.1	✓	Cross-Modal Self-Attention Network for Referring Image Segmentation	lwye/CMSA-Net	2019