← Action Recognition
Papers with Code · CC BY-SA 4.0

Something-Something V1

아카이브 평가 74건 · 마지막 적재/변경

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
MSNet-R50En (8+16 ensemble, ImageNet pretrained)
Top 1 Accuracy
54.4
Top 5 Accuracy
83.8
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
2020-07-20
코드 1 · 코드 2
SELFYNet-TSM-R50 (16 frames, ImageNet pretrained)
Top 1 Accuracy
54.3
Top 5 Accuracy
82.9
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
2021-02-14
코드 1
RNL+TSM Ensemble(R50+R101, ImageNet pretrained)
Top 1 Accuracy
54.1
Top 5 Accuracy
82.2
Region-based Non-local Operation for Video Classification
2020-07-17
코드 1
RSANet-R50 (16 frames, ImageNet pretrained, a single clip)
Top 1 Accuracy
54.0
Top 5 Accuracy
81.1
Relational Self-Attention: What's Missing in Attention for Video Understanding
2021-11-02
코드 1
MVFNet-R50EN
Top 1 Accuracy
54.0
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
2020-12-13
코드 1 · 코드 2 · 코드 3
STPG (8+16frames)
Top 1 Accuracy
53.5
Spatial-Temporal Pyramid Graph Reasoning for Action Recognition
2022-08-09
연결 없음
GB + DF + LB (ResNet152, ImageNet pretrained)
Top 1 Accuracy
53.4
Action recognition with spatial-temporal discriminative filter banks
2019-08-20
연결 없음
ip-CSN-152 (IG-65M pretraining)
Top 1 Accuracy
53.3
Video Classification with Channel-Separated Convolutional Networks
2019-04-04
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
MARS+RGB+Flow (64 frames, Kinetics pretrained)
Top 1 Accuracy
53.0
MARS: Motion-Augmented RGB Stream for Action Recognition
2019-06-01
코드 1
RNL+TSM Ensemble(ResNet50, ImageNet pretrained)
Top 1 Accuracy
52.7
Top 5 Accuracy
81.5
Region-based Non-local Operation for Video Classification
2020-07-17
코드 1
VoV3D-M (32frames, Kinetics pretrained, single)
Top 1 Accuracy
52.68
Top 5 Accuracy
80.43
Param.
3.3M
GFLOPs
11.5x6
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
2020-12-01
코드 1
TSM+W3 (16 frames, ResNet50)
Top 1 Accuracy
52.6
Top 5 Accuracy
81.3
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention
2020-04-02
연결 없음
AK-Net
Top 1 Accuracy
52.5
Action Keypoint Network for Efficient Video Recognition
2022-01-17
연결 없음
MSNet-R50 (16 frames, ImageNet pretrained)
Top 1 Accuracy
52.1
Top 5 Accuracy
82.3
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
2020-07-20
코드 1 · 코드 2
ir-CSN-152 (IG-65M pretraining)
Top 1 Accuracy
52.1
Video Classification with Channel-Separated Convolutional Networks
2019-04-04
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
RSANet-R50 (8 frames, ImageNet pretrained, a single clip)
Top 1 Accuracy
51.9
Top 5 Accuracy
79.6
Relational Self-Attention: What's Missing in Attention for Video Understanding
2021-11-02
코드 1
GSM InceptionV3 (16 frames, ImageNet pretrained)
Top 1 Accuracy
51.68
Gate-Shift Networks for Video Action Recognition
2019-12-01
코드 1 · 코드 2
R(2+1)D-152 (IG-65M pretraining)
Top 1 Accuracy
51.6
Video Classification with Channel-Separated Convolutional Networks
2019-04-04
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
MSNet-R50 (8 frames, ImageNet pretrained)
Top 1 Accuracy
50.9
Top 5 Accuracy
80.3
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
2020-07-20
코드 1 · 코드 2
TSM (RGB + Flow)
Top 1 Accuracy
50.7
TSM: Temporal Shift Module for Efficient Video Understanding
2018-11-20
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13
VoV3D-L (32frames, from scratch, single)
Top 1 Accuracy
50.6
Top 5 Accuracy
78.7
Param.
5.8M
GFLOPs
20.9x6
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
2020-12-01
코드 1
ResNet50 I3D (Moments pretrained)
Top 1 Accuracy
50
Moments in Time Dataset: one million videos for event understanding
2018-01-09
코드 1 · 코드 2 · 코드 3 · 코드 4
VoV3D-M (32frames, from scratch, single)
Top 1 Accuracy
49.8
Top 5 Accuracy
78.0
Param.
3.3M
GFLOPs
11.5x6
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
2020-12-01
코드 1
TSMEn
Top 1 Accuracy
49.7
Top 5 Accuracy
78.5
TSM: Temporal Shift Module for Efficient Video Understanding
2018-11-20
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13
TRG (Inception-V3)
Top 1 Accuracy
49.7
Temporal Reasoning Graph for Activity Recognition
2019-08-27
연결 없음
TRG (ResNet-50)
Top 1 Accuracy
49.5
Top 5 Accuracy
86.1
Temporal Reasoning Graph for Activity Recognition
2019-08-27
연결 없음
VoV3D-L (16frames, from scratch, single)
Top 1 Accuracy
49.5
Top 5 Accuracy
78.0
Param.
5.8M
GFLOPs
9.3x6
Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
2020-12-01
코드 1
ir-CSN-152
Top 1 Accuracy
49.3
Video Classification with Channel-Separated Convolutional Networks
2019-04-04
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
RSTG (Kinetics pretrained)
Top 1 Accuracy
49.2
Recurrent Space-time Graph Neural Networks
2019-04-11
코드 1
ResNet50 I3D (Kinetics pretrained)
Top 1 Accuracy
48.6
Moments in Time Dataset: one million videos for event understanding
2018-01-09
코드 1 · 코드 2 · 코드 3 · 코드 4