← Referring Video Object Segmentation

Papers with Code · CC BY-SA 4.0

Refer-YouTube-VOS

아카이브 평가 18건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
FindTrack	J&F 73.7 J 71.8 F 75.7	Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation 2025-03-05	코드 1
GLEE-Pro	J&F 70.6 J 68.2 F 72.9	General Object Foundation Model for Images and Videos at Scale 2023-12-14	코드 1
HyperSeg	J&F 68.5	HyperSeg: Towards Universal Visual Segmentation with Large Language Model 2024-11-26	코드 1
GLEE-Plus	J&F 67.7 J 65.6 F 69.7	General Object Foundation Model for Images and Videos at Scale 2023-12-14	코드 1
HTR	J&F 67.1 J 65.3 F 68.9	Temporally Consistent Referring Video Object Segmentation with Hybrid Memory 2024-03-28	코드 1
SOC	J&F 66.0 J 64.1 F 67.9	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation 2023-05-26	코드 1
SgMg	J&F 65.7 J 63.9 F 67.4	Spectrum-guided Multi-granularity Referring Video Object Segmentation 2023-07-25	코드 1
VATEX	J&F 65.4 J 63.3 F 67.5	Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding 2024-04-12	코드 1
VLT	J&F 63.8 J 61.9 F 65.6	VLT: Vision-Language Transformer and Query Generation for Referring Segmentation 2022-10-28	코드 1
HTML-SwinL	J&F 63.4 J 61.5 F 65.3	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
HTML-Video-SwinB	J&F 63.4 J 61.5 F 65.2	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
ReferFormer (Large)	J&F 62.9 J 61.3 F 64.6	Language as Queries for Referring Video Object Segmentation 2022-01-03	코드 1
HTML-Video-SwinS	J&F 61.4 J 59.9 F 62.9	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
HTML-Video-SwinT	J&F 61.2 J 59.5 F 63.0	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
R2VOS (Swin-T)	J&F 60.2 J 58.9 F 61.5	Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus 2022-07-04	코드 1
HTML-ResNet101	J&F 58.5 J 57.3 F 59.8	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
HTML-ResNet50	J&F 57.8 J 56.5 F 59.0	HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation 2023-01-01	연결 없음
CMSA	J&F 36.4 J 34.8 F 38.1	Cross-Modal Self-Attention Network for Referring Image Segmentation 2019-04-09	코드 1