A TSM-based multimodal ensemble with pretraining, SWA, ensemble, and TTA reports 99% Top-1 and 100% Top-5 accuracy on the ICPR 2024 RGB-TIR-depth action recognition leaderboard.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Effective End-to-End Solution for Multimodal Action Recognition
A TSM-based multimodal ensemble with pretraining, SWA, ensemble, and TTA reports 99% Top-1 and 100% Top-5 accuracy on the ICPR 2024 RGB-TIR-depth action recognition leaderboard.