atlas

Research map / Video / Video segmentation and tracking

Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models

CVPR 2023 · Video › Video segmentation and tracking · approach: Deepfake video detection · 16 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
use LDEQ instead of HIHWFLW landmark detection · WFLW test, FullNME: 4.08 -> 3.92Helped
use LDEQ instead of HIHWFLW landmark detection · WFLW test, FullAUC_10: 0.605 -> 0.624Helped
use LDEQ instead of HIHWFLW landmark detection · WFLW test, FullFR_10: 2.60 -> 2.48Helped
add RwR at inference (ablation)LDEQ · WFLW-V hardNMF: 197.16 -> 172.95Helped
add RwR at inference (ablation)LDEQ · WFLW-V hardNME: 2.31 -> 2.30Helped
add RwR at inference (ablation)LDEQ · WFLW-V easyNMF: 84.03 -> 82.74Helped
add RwR at inference (ablation)LDEQ · WFLW-V easyNME: 1.24 -> 1.24No clear effect
add RwR at inference (ablation)LDEQ · WFLW-V FULLNMF: 140.59 -> 127.85Helped
add RwR at inference (ablation)LDEQ · WFLW-V FULLNME: 1.77 -> 1.77No clear effect

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