Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Referring Video Object Segmentation On Refer

Métriques

F

J

Ju0026F

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	F	J	Ju0026F	Paper Title	Repository
HTML-Video-SwinT	63.0	59.5	61.2	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
HTR	68.9	65.3	67.1	Temporally Consistent Referring Video Object Segmentation with Hybrid Memory
VLT	65.6	61.9	63.8	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
GLEE-Plus	69.7	65.6	67.7	General Object Foundation Model for Images and Videos at Scale
HTML-SwinL	65.3	61.5	63.4	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
ReferFormer (Large)	64.6	61.3	62.9	Language as Queries for Referring Video Object Segmentation
SOC	67.9	64.1	66.0	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
HTML-Video-SwinB	65.2	61.5	63.4	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
HTML-ResNet101	59.8	57.3	58.5	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
HTML-ResNet50	59.0	56.5	57.8	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
VATEX	67.5	63.3	65.4	Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
CMSA	38.1	34.8	36.4	Cross-Modal Self-Attention Network for Referring Image Segmentation
SgMg	67.4	63.9	65.7	Spectrum-guided Multi-granularity Referring Video Object Segmentation
GLEE-Pro	72.9	68.2	70.6	General Object Foundation Model for Images and Videos at Scale
FindTrack	72.0	68.6	70.3	Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
HyperSeg	-	-	68.5	HyperSeg: Towards Universal Visual Segmentation with Large Language Model
R2VOS (Swin-T)	61.5	58.9	60.2	Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus
HTML-Video-SwinS	62.9	59.9	61.4	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-

0 of 18 row(s) selected.