Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
Zero-Shot Learning
/
FineAction
Zero-Shot Learning on FineAction
Metric: mAP (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide augmentations
Export CSV
Sort:
mAP (best first)
mAP (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
mAP
▼
Augmentations
Paper
Date
↕
Code
1
RDFA-S6 (InternVideo2-6B)
29.6
No
Enhancing Temporal Action Localization: Advanced...
2024-07-18
Code
2
ActionMamba(InternVideo2-6B)
29.04
No
Video Mamba Suite: State Space Model as a Versat...
2024-03-14
Code
3
InternVideo2-6B
27.7
No
InternVideo2: Scaling Foundation Models for Mult...
2024-03-22
Code
4
DyFADet (VideoMAE v2-g)
23.8
No
DyFADet: Dynamic Feature Aggregation for Tempora...
2024-07-03
Code
5
VideoMAE V2-g
18.24
Yes
VideoMAE V2: Scaling Video Masked Autoencoders w...
2023-03-29
Code
6
InternVideo
17.57
No
InternVideo: General Video Foundation Models via...
2022-12-06
Code
7
BMN (i3d feaure)
9.25
No
BMN: Boundary-Matching Network for Temporal Acti...
2019-07-23
Code
8
G-TAD (i3d feature)
9.06
No
G-TAD: Sub-Graph Localization for Temporal Actio...
2019-11-26
Code
9
DBG (i3d feature)
6.75
No
Fast Learning of Temporal Action Proposal via De...
2019-11-11
Code
10
HAAN
4.1
No
Weakly-Supervised Temporal Action Detection for ...
2022-07-24
Code
11
W-TALC
3.45
No
W-TALC: Weakly-supervised Temporal Activity Loca...
2018-07-27
Code
12
D2-Net
3.35
No
D2-Net: Weakly-Supervised Action Localization vi...
2020-12-11
Code
13
ASL
3.3
No
Weakly Supervised Action Selection Learning in V...
2021-05-06
Code
#1
RDFA-S6 (InternVideo2-6B)
SOTA
29.6
mAP
· 2024-07-18
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
Code
#2
ActionMamba(InternVideo2-6B)
SOTA
29.04
mAP
· 2024-03-14
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
Code
#3
InternVideo2-6B
27.7
mAP
· 2024-03-22
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
Code
#4
DyFADet (VideoMAE v2-g)
23.8
mAP
· 2024-07-03
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
Code
#5
VideoMAE V2-g
SOTA
18.24
mAP
· Augmentations
· 2023-03-29
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Code
#6
InternVideo
SOTA
17.57
mAP
· 2022-12-06
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Code
#7
BMN (i3d feaure)
SOTA
9.25
mAP
· 2019-07-23
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
Code
#8
G-TAD (i3d feature)
9.06
mAP
· 2019-11-26
G-TAD: Sub-Graph Localization for Temporal Action Detection
Code
#9
DBG (i3d feature)
6.75
mAP
· 2019-11-11
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
Code
#10
HAAN
4.1
mAP
· 2022-07-24
Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions
Code
#11
W-TALC
SOTA
3.45
mAP
· 2018-07-27
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Code
#12
D2-Net
3.35
mAP
· 2020-12-11
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Code
#13
ASL
3.3
mAP
· 2021-05-06
Weakly Supervised Action Selection Learning in Video
Code