PK PyTorchKR Papers
← Temporal Sentence Grounding
Papers with Code · CC BY-SA 4.0

Charades-STA

아카이브 평가 13건 · 마지막 적재/변경

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
모델원본 지표·값논문구현
DeCafNet
R1@0.5
68.79
R1@0.7
47.55
R5@0.7
72.96
R5@0.5
91.53
 DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
2025-05-22		 코드 1
AdaFocus (Full, MViT-Charades-Pretrain-feature, MMN model)
R1@0.5
62.4
R1@0.7
38.6
R5@0.7
66.4
R5@0.5
89.4
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
AdaFocus (Full, I3D-Charades-Pretrain-feature, MMN model)
R1@0.5
56.7
R1@0.7
35.6
R5@0.7
65.0
R5@0.5
87.9
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
55.2
R1@0.7
32.2
R5@0.7
62.7
R5@0.5
88.3
 Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
2021-09-10		 코드 1 · 코드 2
MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
49.4
R1@0.7
29.8
R5@0.7
60.5
R5@0.5
85.8
 Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
2021-09-10		 코드 1 · 코드 2
AdaFocus (Weak, MViT-Charades-Pretrain-feature, CPL model)
R1@0.5
51.7
R1@0.7
23.2
R5@0.7
52.6
R5@0.5
85.2
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
AdaFocus (Weak, I3D-Charades-Pretrain-feature, CPL model)
R1@0.5
49.1
R1@0.7
22.4
R5@0.7
51.8
R5@0.5
84.2
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
AdaFocus (Semi-weak, MViT-Charades-Pretrain-feature, D3G model)
R1@0.5
50.1
R1@0.7
21.8
R5@0.7
54.6
R5@0.5
86.1
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
CPL (Weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
47.8
R1@0.7
21.8
R5@0.7
50.4
R5@0.5
84.6
 Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning
2022-01-01		 코드 1
AdaFocus (Semi-weak, I3D-Charades-Pretrain-feature, D3G model)
R1@0.5
46.9
R1@0.7
21.1
R5@0.7
49.2
R5@0.5
79.3
 Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
2023-11-28		 연결 없음
D3G (Semi-weak, MViT-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
46.0
R1@0.7
20.2
R5@0.7
50.2
R5@0.5
83.1
 D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation
2023-08-08		 코드 1
D3G (Semi-weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
41.7
R1@0.7
18.8
R5@0.7
48.0
R5@0.5
78.2
 D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation
2023-08-08		 코드 1
CPL (Weak, I3D-K400-Pretrain-feature, evaluated by AdaFocus)
R1@0.5
39.6
R1@0.7
18.6
R5@0.7
49.2
R5@0.5
81.4
 Weakly Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning
2022-01-01		 코드 1