AI Paper Atlas

Research map / Video / Action recognition

Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better

Kaihao Zhang, Dongxu Li, Wenhan Luo, Wenqi Ren, Wei Liu

TPAMI 2022 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 273 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
add STIM temporal modeling over 5 frames instead of single-frame 2D CNN (ablation)ESTINet · NTURainPSNR: 35.44 -> 37.28Improved
add STIM temporal modeling over 5 frames instead of single-frame 2D CNN (ablation)ESTINet · NTURainSSIM: 0.9562 -> 0.9693Improved
increase input frames from 2 to 5 (ablation)SICM + STIM · NTURainPSNR: 36.61 -> 37.28Improved
use STIM instead of ConvLSTM before ESTM (ablation)SICM + ESTM · NTURainPSNR: 36.43 -> 37.48Improved
use STIM instead of B-ConvLSTM before ESTM (ablation)SICM + ESTM · NTURainPSNR: 36.76 -> 37.48Improved
add 3D-convolution ESTM instead of 2D CNN refinement (ablation)SICM + STIM (#5) · NTURainPSNR: 37.35 -> 37.48Improved
add 3D-convolution ESTM instead of 2D CNN refinement (ablation)SICM + STIM (#5) · NTURainSSIM: 0.9695 -> 0.9700Improved
add ESTM refinement to STIM(#5) (ablation)SICM + STIM · NTURainPSNR: 37.28 -> 37.48Improved

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