Papers with Code · CC BY-SA 4.0

A2D Sentences

아카이브 평가 27건 · 마지막 적재/변경 2026-10-30

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
SgMg (Video-Swin-B)	Precision@0.5 0.843 Precision@0.9 0.259 IoU overall 0.799 IoU mean 0.720 Precision@0.6 0.822 Precision@0.7 0.767 Precision@0.8 0.617 AP 0.585	Spectrum-guided Multi-granularity Referring Video Object Segmentation 2023-07-25	코드 1
SOC (Video-Swin-B)	Precision@0.5 0.851 Precision@0.9 0.252 IoU overall 0.807 IoU mean 0.725 Precision@0.6 0.827 Precision@0.7 0.765 Precision@0.8 0.607 AP 0.573	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation 2023-05-26	코드 1
ReferFormer (Video-Swin-B)	Precision@0.5 0.831 Precision@0.9 0.212 IoU overall 0.786 IoU mean 0.703 Precision@0.6 0.804 Precision@0.7 0.741 Precision@0.8 0.579 AP 0.550	Language as Queries for Referring Video Object Segmentation 2022-01-03	코드 1
SOC (Video-Swin-T)	Precision@0.5 0.79 Precision@0.9 0.195 IoU overall 0.747 IoU mean 0.669 Precision@0.6 0.756 Precision@0.7 0.687 Precision@0.8 0.535 AP 0.504	SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation 2023-05-26	코드 1
MANET	Precision@0.5 0.734 Precision@0.9 0.132 IoU overall 0.726 IoU mean 0.632 Precision@0.6 0.682 Precision@0.7 0.579 Precision@0.8 0.389 AP 0.471	Multi-Attention Network for Compressed Video Referring Object Segmentation 2022-07-26	코드 1
VLIDE	Precision@0.5 0.702 Precision@0.9 0.151 IoU overall 0.714 IoU mean 0.598 Precision@0.6 0.663 Precision@0.7 0.585 Precision@0.8 0.428 AP 0.469	Deeply Interleaved Two-Stream Encoder for Referring Video Segmentation 2022-03-30	연결 없음
Locater	Precision@0.5 0.709 Precision@0.9 0.101 IoU overall 0.69 IoU mean 0.597 Precision@0.6 0.64 Precision@0.7 0.525 Precision@0.8 0.351 AP 0.465	Local-Global Context Aware Transformer for Language-Guided Video Segmentation 2022-03-18	코드 1
MTTR (w=10)	Precision@0.5 0.754 Precision@0.9 0.169 IoU overall 0.72 IoU mean 0.64 Precision@0.6 0.712 Precision@0.7 0.638 Precision@0.8 0.485 AP 0.461	End-to-End Referring Video Object Segmentation with Multimodal Transformers 2021-11-29	코드 1 · 코드 2
MTTR (w=8)	Precision@0.5 0.721 Precision@0.9 0.164 IoU overall 0.702 IoU mean 0.618 Precision@0.6 0.684 Precision@0.7 0.607 Precision@0.8 0.456 AP 0.447	End-to-End Referring Video Object Segmentation with Multimodal Transformers 2021-11-29	코드 1 · 코드 2
mmmmtbvs	Precision@0.5 0.645 Precision@0.9 0.13 IoU overall 0.673 IoU mean 0.558 Precision@0.6 0.597 Precision@0.7 0.523 Precision@0.8 0.375 AP 0.419	Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation 2022-04-06	코드 1
CMPC-V (I3D)	Precision@0.5 0.655 Precision@0.9 0.098 IoU overall 0.653 IoU mean 0.573 Precision@0.6 0.592 Precision@0.7 0.506 Precision@0.8 0.342 AP 0.404	Cross-Modal Progressive Comprehension for Referring Segmentation 2021-05-15	코드 1
Hui et al.	Precision@0.5 0.654 Precision@0.9 0.091 IoU overall 0.662 IoU mean 0.561 Precision@0.6 0.589 Precision@0.7 0.497 Precision@0.8 0.333 AP 0.399	Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation 2021-05-14	연결 없음
AAMN	Precision@0.5 0.681 Precision@0.9 0.029 IoU overall 0.617 IoU mean 0.552 Precision@0.6 0.629 Precision@0.7 0.523 Precision@0.8 0.296 AP 0.396	Actor and Action Modular Network for Text-based Video Segmentation 2020-11-02	연결 없음
PRPE	Precision@0.5 0.634 Precision@0.9 0.083 IoU overall 0.661 IoU mean 0.529 Precision@0.6 0.579 Precision@0.7 0.483 Precision@0.8 0.322 AP 0.388	Polar Relative Positional Encoding for Video-Language Segmentation 2020-07-20	연결 없음
CMPC-V (R2D)	Precision@0.5 0.590 Precision@0.9 0.068 IoU overall 0.649 IoU mean 0.515 Precision@0.6 0.527 Precision@0.7 0.434 Precision@0.8 0.284 AP 0.351	Cross-Modal Progressive Comprehension for Referring Segmentation 2021-05-15	코드 1
CMDy	Precision@0.5 0.607 Precision@0.9 0.045 IoU overall 0.623 IoU mean 0.531 Precision@0.6 0.525 Precision@0.7 0.405 Precision@0.8 0.235 AP 0.333	Context Modulated Dynamic Networks for Actor and Action Video Segmentation with Language Queries 2020-04-03	연결 없음
VT-Capsule	Precision@0.5 0.526 Precision@0.9 0.036 IoU overall 0.568 IoU mean 0.460 Precision@0.6 0.450 Precision@0.7 0.345 Precision@0.8 0.207 AP 0.303	Visual-Textual Capsule Routing for Text-Based Video Segmentation 2020-06-01	연결 없음
ACGA	Precision@0.5 0.557 Precision@0.9 0.02 IoU overall 0.601 IoU mean 0.490 Precision@0.6 0.459 Precision@0.7 0.319 Precision@0.8 0.16 AP 0.274	Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query 2019-10-01	코드 1
Gavriluyk el al. (Optical flow)	Precision@0.5 0.5 Precision@0.9 0.004 IoU overall 0.551 IoU mean 0.426 Precision@0.6 0.376 Precision@0.7 0.231 Precision@0.8 0.094 AP 0.215	Actor and Action Video Segmentation from a Sentence 2018-03-20	코드 1
Gavriluyk el al.	Precision@0.5 0.475 Precision@0.9 0.002 IoU overall 0.536 IoU mean 0.421 Precision@0.6 0.347 Precision@0.7 0.211 Precision@0.8 0.08 AP 0.198	Actor and Action Video Segmentation from a Sentence 2018-03-20	코드 1
Li et al.	Precision@0.5 0.387 Precision@0.9 0.001 IoU overall 0.515 IoU mean 0.354 Precision@0.6 0.290 Precision@0.7 0.175 Precision@0.8 0.066 AP 0.163	Tracking by Natural Language Specification 2017-07-01	연결 없음
Hu et al.	Precision@0.5 0.348 Precision@0.9 0.000 IoU overall 0.474 IoU mean 0.350 Precision@0.6 0.236 Precision@0.7 0.133 Precision@0.8 0.033 AP 0.132	Segmentation from Natural Language Expressions 2016-03-20	코드 1 · 코드 2 · 코드 3 · 코드 4
HINet	Precision@0.5 0.611 Precision@0.9 0.12 IoU overall 0.679 IoU mean 0.529 Precision@0.6 0.559 Precision@0.7 0.486 Precision@0.8 0.342	Hierarchical interaction network for video object segmentation from referring expressions 2021-11-22	연결 없음
RefVOS	Precision@0.5 0.578 Precision@0.9 0.093 IoU overall 0.672 IoU mean 0.497 Precision@0.6 0.534 Precision@0.7 0.456 Precision@0.8 0.311	Hierarchical interaction network for video object segmentation from referring expressions 2021-11-22	연결 없음
ClawCraneNet	Precision@0.5 0.704 Precision@0.9 0.171 IoU overall 0.644 IoU mean 0.655 Precision@0.6 0.677 Precision@0.7 0.617 Precision@0.8 0.489	ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation 2021-03-19	연결 없음
CMSA+CFSA	Precision@0.5 0.487 Precision@0.9 0.052 IoU overall 0.618 IoU mean 0.432 Precision@0.6 0.431 Precision@0.7 0.358 Precision@0.8 0.231	Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network 2021-02-09	연결 없음
RefVOS	Precision@0.5 0.495 Precision@0.9 0.064 IoU overall 0.599 IoU mean 0.599	RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation 2020-10-01	코드 1 · 코드 2