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
Temporal Action Localization
Temporal Action Localization On Thumos14
Temporal Action Localization On Thumos14
Metrics
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
Results
Performance results of various models on this benchmark
Columns
Model Name
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
Paper Title
AdaTAD (VideoMAEv2-giant)
-
-
89.7
86.7
80.9
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
RDFA-S6 (InternVideo2-6B)
-
-
88.7
84.6
78.2
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
ActionMamba(InternVideo2-6B)
-
-
86.89
83.09
76.90
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
TriDet (VideoMAE v2-g feature)
-
-
84.8
80.0
73.3
Temporal Action Localization with Enhanced Instant Discriminability
ActionFormer (VideoMAE V2-g features)
-
-
84.0
79.6
73.0
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
TriDet (I3D features)
-
-
83.6
80.1
72.9
TriDet: Temporal Action Detection with Relative Boundary Modeling
TemporalMaxer (I3D features)
-
-
82.8
78.9
71.8
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization
ASL(I3D features)
-
-
83.1
79.0
71.7
Action Sensitivity Learning for Temporal Action Localization
ActionFormer (I3D features)
-
-
82.1
77.8
71.0
ActionFormer: Localizing Moments of Actions with Transformers
DualDETR (I3D features)
-
-
82.9
78.0
70.4
Dual DETRs for Multi-Label Temporal Action Detection
BasicTAD (160,6,192,R50-SlowOnly)
-
-
75.5
70.8
63.5
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
TadML(two-stream)
-
-
73.29
69.73
62.53
TadML: A fast temporal action detection with Mechanics-MLP
TadTR
-
-
74.8
69.1
60.1
End-to-end Temporal Action Detection with Transformer
BasicTAD (112,3,96,R50-SlowOnly)
-
-
68.4
65.0
58.6
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
ReAct (TSN features)
-
-
69.2
65.0
57.1
ReAct: Temporal Action Detection with Relational Queries
AVFusion
-
-
70.1
64.9
57.1
Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
TAGS (I3D)
-
-
68.6
63.8
57.0
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
MUSES
-
-
68.9
64.0
56.9
Multi-shot Temporal Event Localization: a Benchmark
TadML(rgb-only)
-
-
68.78
64.66
56.61
TadML: A fast temporal action detection with Mechanics-MLP
E2E-TAD (SlowFast R50+TadTR)
-
-
69.4
64.3
56.0
An Empirical Study of End-to-End Temporal Action Detection
0 of 42 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
Temporal Action Localization
Temporal Action Localization On Thumos14
Temporal Action Localization On Thumos14
Metrics
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
Results
Performance results of various models on this benchmark
Columns
Model Name
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
mAP
[email protected]
Paper Title
AdaTAD (VideoMAEv2-giant)
-
-
89.7
86.7
80.9
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
RDFA-S6 (InternVideo2-6B)
-
-
88.7
84.6
78.2
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
ActionMamba(InternVideo2-6B)
-
-
86.89
83.09
76.90
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
TriDet (VideoMAE v2-g feature)
-
-
84.8
80.0
73.3
Temporal Action Localization with Enhanced Instant Discriminability
ActionFormer (VideoMAE V2-g features)
-
-
84.0
79.6
73.0
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
TriDet (I3D features)
-
-
83.6
80.1
72.9
TriDet: Temporal Action Detection with Relative Boundary Modeling
TemporalMaxer (I3D features)
-
-
82.8
78.9
71.8
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization
ASL(I3D features)
-
-
83.1
79.0
71.7
Action Sensitivity Learning for Temporal Action Localization
ActionFormer (I3D features)
-
-
82.1
77.8
71.0
ActionFormer: Localizing Moments of Actions with Transformers
DualDETR (I3D features)
-
-
82.9
78.0
70.4
Dual DETRs for Multi-Label Temporal Action Detection
BasicTAD (160,6,192,R50-SlowOnly)
-
-
75.5
70.8
63.5
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
TadML(two-stream)
-
-
73.29
69.73
62.53
TadML: A fast temporal action detection with Mechanics-MLP
TadTR
-
-
74.8
69.1
60.1
End-to-end Temporal Action Detection with Transformer
BasicTAD (112,3,96,R50-SlowOnly)
-
-
68.4
65.0
58.6
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
ReAct (TSN features)
-
-
69.2
65.0
57.1
ReAct: Temporal Action Detection with Relational Queries
AVFusion
-
-
70.1
64.9
57.1
Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
TAGS (I3D)
-
-
68.6
63.8
57.0
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
MUSES
-
-
68.9
64.0
56.9
Multi-shot Temporal Event Localization: a Benchmark
TadML(rgb-only)
-
-
68.78
64.66
56.61
TadML: A fast temporal action detection with Mechanics-MLP
E2E-TAD (SlowFast R50+TadTR)
-
-
69.4
64.3
56.0
An Empirical Study of End-to-End Temporal Action Detection
0 of 42 row(s) selected.
Previous
Next
Temporal Action Localization On Thumos14 | SOTA | HyperAI