AI Paper Atlas

Research map / Video / Video segmentation and tracking

Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction

Andrey Savchenko

ICML 2023 · Video › Video segmentation and tracking · approach: Deepfake video detection

Read the paper

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
Benjamini-Hochberg multiple-testing thresholds instead of the same FAR at every step (ablation)adaptive frame-rate pipeline with EmotiEffNet-B0 · ABAW-3 validation (200->100->50->10->1)F1-score and time per frame: F1 0.4190 -> 0.4217; time 20.15 -> 3.70 msImproved
Adaptive frame-rate selection with BH-corrected thresholds vs. processing all framesEmotiEffNet-B0 · ABAW-3 validationF1-score: 0.4262 -> 0.4217 (drop under 0.5%)Mixed
Adaptive frame-rate selection with BH thresholds vs. all framesEmotiEffNet-B0 · AFEW validation (18->9->1)accuracy: 0.5927 -> 0.5850Hurt
Adaptive frame-rate selection with BH thresholds vs. all framesMT-EmotiEffNet-B0 and EmotiEffNet-B2 · ABAW-3 validationspeed-up over all frames: up to 40x (MT-EmotiEffNet) and 25x (EmotiEffNet-B2)Improved
Proposed adaptive method vs. FrameExit early exitEmotiEffNet-B0 · ABAW-3 validationF1-score and time: F1 0.4217 vs 0.4177; time 3.70 vs 5.97 msImproved
Proposed adaptive method vs. OCSampler and AR-NetEmotiEffNet-B0 · AFEW validationaccuracy: 0.5910 vs 0.5530 (OCSampler), 0.5526 (AR-Net)Improved
Proposed adaptive method vs. AdaFrame, LiteEval on ABAWEmotiEffNet-B0 · ABAW-3 validationF1-score: proposed 0.4217 vs AdaFrame 0.4205 and LiteEval 0.4220 (LiteEval slightly higher)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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