HyperAI
HyperAI
Home
Console
Docs
News
Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
Terms of Service
Privacy Policy
English
HyperAI
HyperAI
Toggle Sidebar
Search the site…
⌘
K
Command Palette
Search for a command to run...
Console
Home
SOTA
Action Detection
Action Detection On Multi Thumos
Action Detection On Multi Thumos
Metrics
mAP
Results
Performance results of various models on this benchmark
Columns
Model Name
mAP
Paper Title
MLAD
51.5
Modeling Multi-Label Action Dependencies for Temporal Action Localization
CTRN
51.2
CTRN: Class-Temporal Relational Network for Action Detection
PDAN
47.6
PDAN: Pyramid Dilated Attention Network for Action Detection
TGM
46.4
Temporal Gaussian Mixture Layer for Videos
MS-TCT (RGB only)
43.1
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
I3D + our super-event
36.4
Learning Latent Super-Events to Detect Multiple Activities in Videos
Two-stream + LSTM
28.1
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
Two-stream
27.6
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
0 of 8 row(s) selected.
Previous
Next
HyperAI
HyperAI
Home
Console
Docs
News
Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
Terms of Service
Privacy Policy
English
HyperAI
HyperAI
Toggle Sidebar
Search the site…
⌘
K
Command Palette
Search for a command to run...
Console
Home
SOTA
Action Detection
Action Detection On Multi Thumos
Action Detection On Multi Thumos
Metrics
mAP
Results
Performance results of various models on this benchmark
Columns
Model Name
mAP
Paper Title
MLAD
51.5
Modeling Multi-Label Action Dependencies for Temporal Action Localization
CTRN
51.2
CTRN: Class-Temporal Relational Network for Action Detection
PDAN
47.6
PDAN: Pyramid Dilated Attention Network for Action Detection
TGM
46.4
Temporal Gaussian Mixture Layer for Videos
MS-TCT (RGB only)
43.1
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
I3D + our super-event
36.4
Learning Latent Super-Events to Detect Multiple Activities in Videos
Two-stream + LSTM
28.1
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
Two-stream
27.6
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
0 of 8 row(s) selected.
Previous
Next
Action Detection On Multi Thumos | SOTA | HyperAI