HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Temporal Action Localization On Hacs

Metrics

Average-mAP
mAP@0.5
mAP@0.75
mAP@0.95

Results

Performance results of various models on this benchmark

Paper TitleRepository
RDFA-S6 (InternVideo2-6B)45.866.447.214.3Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
ActionMamba(InternVideo2-6B)44.5664.0245.7113.34Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
DyFADet(VideoMAEv2)44.364.044.814.1DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
InternVideo2-6B43.3---InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
TriDet (VideoMAEv2)43.162.444.113.1Temporal Action Localization with Enhanced Instant Discriminability
InternVideo2-1B42.4---InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
InternVideo41.55---InternVideo: General Video Foundation Models via Generative and Discriminative Learning
TriDet (SlowFast)38.656.739.311.7TriDet: Temporal Action Detection with Relative Boundary Modeling
TriDet (I3D RGB)36.854.536.811.5TriDet: Temporal Action Detection with Relative Boundary Modeling
TadTr (I3D RGB)32.0947.1432.1110.94End-to-end Temporal Action Detection with Transformer
LoFi+G-TAD (RGB, RN18)24.6437.7824.407.29Low-Fidelity Video Encoder Optimization for Temporal Action Localization-
SSN18.9728.8218.805.32HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
0 of 12 row(s) selected.
Temporal Action Localization On Hacs | SOTA | HyperAI