|
TTM
|
Token Turing Machines
|
28.79
|
2022-11-16
|
|
|
CTRN
|
CTRN: Class-Temporal Relational Network for Actio…
|
27.80
|
2021-10-26
|
|
|
Coarse-Fine Networks (w/ self-supervised detection pretraining)
|
Weakly-guided Self-supervised Pretraining for Tem…
|
26.95
|
2021-11-26
|
|
|
UniMD+Sync. (RGB+Flow)
|
UniMD: Towards Unifying Moment Retrieval and Temp…
|
26.53
|
2024-04-07
|
|
|
PAT
|
PAT: Position-Aware Transformer for Dense Multi-L…
|
26.50
|
2023-08-09
|
|
|
MS-TCT (RGB only)
|
MS-TCT: Multi-Scale Temporal ConvTransformer for …
|
25.40
|
2021-12-07
|
|
|
3D ResNet-50 + super-events pretrained on AViD
|
AViD Dataset: Anonymized Videos from Diverse Coun…
|
25.20
|
2020-07-10
|
|
|
Coarse-Fine Networks
|
Coarse-Fine Networks for Temporal Activity Detect…
|
25.10
|
2021-03-01
|
|
|
MLAD (RGB + Flow)
|
Modeling Multi-Label Action Dependencies for Temp…
|
23.70
|
2021-03-04
|
|
|
I3D + biGRU + VS-ST-MPNN
|
Representation Learning on Visual-Symbolic Graphs…
|
23.70
|
2019-05-17
|
|
|
3D ResNet-50 pretrained on AViD
|
AViD Dataset: Anonymized Videos from Diverse Coun…
|
23.20
|
2020-07-10
|
|
|
TGM (RGB+Flow)
|
Temporal Gaussian Mixture Layer for Videos
|
22.30
|
2018-03-16
|
|
|
Super-events (RGB+Flow)
|
Learning Latent Super-Events to Detect Multiple A…
|
19.41
|
2017-12-05
|
|
|
R-C3D
|
R-C3D: Region Convolutional 3D Network for Tempor…
|
12.40
|
2017-03-22
|
|
|
Sigurdsson et al.
|
Asynchronous Temporal Fields for Action Recogniti…
|
9.60
|
2016-12-19
|
|