HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Referring Video Object Segmentation On Ref

평가 지표

F

J

Ju0026F

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	F	J	Ju0026F	Paper Title	Repository
FindTrack	78.5	69.9	74.2	Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
DsHmp	68.1	61.7	64.9	Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
SOC	69.1	62.5	65.8	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
URVOS	56.0	47.3	51.6	URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark
HTML	65.1	59.2	62.1	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation	-
SgMg	66.0	60.6	63.3	Spectrum-guided Multi-granularity Referring Video Object Segmentation
VD-IT	72.6	66.2	69.4	Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
MUTR	71.3	64.8	68.0	Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
ReferFormer	64.1	58.1	61.1	Language as Queries for Referring Video Object Segmentation
LoSh	66.8	61.8	64.3	LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation
LBDT	-	-	54.5	Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation	-

0 of 11 row(s) selected.