A low-parameter, biologically inspired 3D pyramidal network with a linear-SVM feature-fusion extension matches or exceeds several prior video-classification baselines on Weizmann, KTH, YUPENN, and Maryland datasets.
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
REJECT 1representative citing papers
citing papers explorer
-
3DPyranet Features Fusion for Spatio-temporal Feature Learning
A low-parameter, biologically inspired 3D pyramidal network with a linear-SVM feature-fusion extension matches or exceeds several prior video-classification baselines on Weizmann, KTH, YUPENN, and Maryland datasets.