AI Paper Atlas

Research map / Video / Action recognition

Privacy-Preserving Video Classification with Convolutional Neural Networks

ICML 2021 · Video › Action recognition · approach: Contrastive video representation learning · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace Softmax with the approximate Softmax functionConvNet video classifier · RAVDESS test setvideo classification accuracy: 56% -> 56.8%Helped
Use passive 3PC rather than passive 2PCPrivate video classification · RAVDESS videosAvg. Time (sec): 511.64 -> 13.12Helped
Use active 3PC rather than active 2PCPrivate video classification · RAVDESS videosAvg. Time (sec): 8423.81 -> 48.20Helped
Use active 4PC rather than active 3PCPrivate video classification · RAVDESS videosAvg. Time (sec): 48.20 -> 18.40Helped
Use active rather than passive security in 3PCPrivate video classification · RAVDESS videosAvg. Time (sec): 13.12 -> 48.20Hurt

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