AI Paper Atlas

Research map / Video / Action recognition

Volterra Neural Networks (VNNs)

Siddharth Roheda, Hamid Krim, Bo Jiang

JMLR 2024 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fuse RGB and optical flow with Volterra filter instead of feature concatenation (ablation)O-VNN-H from scratch · UCF-101accuracy: 82.31 -> 90.28Improved
fuse with Volterra filter instead of weighted averaging (ablation)O-VNN-H from scratch · UCF-101accuracy: 85.79 -> 90.28Improved
fuse with Volterra filter instead of event driven fusion (ablation)O-VNN-H from scratch · HMDB-51accuracy: 60.36 -> 65.61Improved
add cascaded structure and higher complexity to plain Volterra filter (ablation)O-VNN-H RGB only from scratch · UCF-101accuracy: 38.19 -> 58.73Improved
use O-VNN-H instead of lighter O-VNN-L (ablation)two-stream from scratch · UCF-101accuracy: 86.16 -> 90.28Improved
add second stream (optical flow) to RGB-only O-VNN-HO-VNN-H from scratch · UCF-101accuracy: 58.73 -> 90.28Improved
pretrain O-VNN-H on Kineticstwo-stream O-VNN-H · UCF-101accuracy: 90.28 -> 98.49Improved
replace conv layers with Volterra layers in two-stream networkKinetics-400 · Kinetics-400accuracy: 74.2 -> 78.8Improved
use Volterra generator in WGANWGAN · CIFAR10inception score: 5.95 -> 6.20Improved
use Volterra layers with fixed dictionary in STGANSTGAN · CIFAR10inception score: 6.80 -> 7.05Improved
increase number of multipliers Q in cascaded Volterra filter (ablation)cascaded Volterra filter · training losstraining lossImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy