← Natural Language Moment Retrieval

Papers with Code · CC BY-SA 4.0

MAD

아카이브 평가 8건 · 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
ReVisionLLM	R@1,IoU=0.1 17.3 R@1,IoU=0.3 12.7 R@1,IoU=0.5 6.7	ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos 2024-11-22	코드 1
DeCafNet	R@1,IoU=0.1 13.25 R@5,IoU=0.1 27.73 R@1,IoU=0.3 10.96 R@5,IoU=0.3 23.68 R@1,IoU=0.5 7.06 R@5,IoU=0.5 16.13	DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos 2025-05-22	코드 1
RGNet	R@1,IoU=0.1 12.43 R@5,IoU=0.1 25.12 R@1,IoU=0.3 9.48 R@5,IoU=0.3 18.72 R@1,IoU=0.5 5.61 R@5,IoU=0.5 10.86	RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos 2023-12-11	코드 1 · 코드 2
Zero-Shot CLIP + Guidance Model	R@1,IoU=0.1 9.3 R@5,IoU=0.1 18.96 R@10,IoU=0.1 24.30 R@50,IoU=0.1 39.79 R@100,IoU=0.1 47.35 R@1,IoU=0.3 4.65 R@5,IoU=0.3 13.06 R@10,IoU=0.3 17.73 R@50,IoU=0.3 32.23 R@100,IoU=0.3 39.58 R@1,IoU=0.5 2.16 R@5,IoU=0.5 7.4 R@10,IoU=0.5 11.09 R@50,IoU=0.5 23.21 R@100,IoU=0.5 29.68	Localizing Moments in Long Video Via Multimodal Guidance 2023-02-26	코드 1
CLIP	R@1,IoU=0.1 6.57 R@5,IoU=0.1 15.05 R@10,IoU=0.1 20.26 R@50,IoU=0.1 37.92 R@100,IoU=0.1 47.73 R@1,IoU=0.3 3.13 R@5,IoU=0.3 9.85 R@10,IoU=0.3 14.13 R@50,IoU=0.3 28.71 R@100,IoU=0.3 36.98 R@1,IoU=0.5 1.39 R@5,IoU=0.5 5.44 R@10,IoU=0.5 8.38 R@50,IoU=0.5 18.80 R@100,IoU=0.5 24.99	MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions 2021-12-01	코드 1
VLG-Net + Guidance Model	R@1,IoU=0.1 5.60 R@5,IoU=0.1 16.07 R@10,IoU=0.1 23.64 R@50,IoU=0.1 45.35 R@100,IoU=0.1 55.59 R@1,IoU=0.3 4.28 R@10,IoU=0.3 19.86 R@50,IoU=0.3 39.77 R@100,IoU=0.3 49.38 R@1,IoU=0.5 2.48 R@5,IoU=0.5 8.78 R@10,IoU=0.5 13.72 R@50,IoU=0.5 30.22 R@100,IoU=0.5 39.12	Localizing Moments in Long Video Via Multimodal Guidance 2023-02-26	코드 1
VLG-Net	R@1,IoU=0.1 3.50 R@5,IoU=0.1 11.74 R@10,IoU=0.1 18.32 R@50,IoU=0.1 38.41 R@100,IoU=0.1 49.65 R@1,IoU=0.3 2.63 R@5,IoU=0.3 9.49 R@10,IoU=0.3 15.2 R@50,IoU=0.3 33.68 R@100,IoU=0.3 43.95 R@1,IoU=0.5 1.61 R@5,IoU=0.5 6.23 R@10,IoU=0.5 10.18 R@50,IoU=0.5 25.33 R@100,IoU=0.5 34.18	MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions 2021-12-01	코드 1
Random Chance	R@1,IoU=0.1 0.09 R@5,IoU=0.1 0.44 R@10,IoU=0.1 0.88 R@50,IoU=0.1 4.33 R@100,IoU=0.1 8.47 R@1,IoU=0.3 0.04 R@5,IoU=0.3 0.19 R@10,IoU=0.3 0.39 R@50,IoU=0.3 1.92 R@100,IoU=0.3 3.80 R@1,IoU=0.5 0.01 R@5,IoU=0.5 0.07 R@10,IoU=0.5 0.14 R@50,IoU=0.5 0.71 R@100,IoU=0.5 1.40	MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions 2021-12-01	코드 1