AI Paper Atlas

Research map / Video / Video segmentation and tracking

Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers

Bohai Gu, Heng Fan, Libo Zhang

ICCV 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 18 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 video-image cross-attention interaction module (joint learning) (ablation)UniST · Image style transfercontent difference D_C: 15.44 -> 12.36Improved
add video-image cross-attention interaction module (joint learning) (ablation)UniST · Image style transferstyle difference D_S: 0.69 -> 0.46Improved
train jointly on image and video rather than image only (ablation)UniST · Image style transfercontent difference D_C: 19.29 -> 15.44Improved
use joint training instead of sequential training (ablation)UniST without interaction · Image style transfercontent difference D_C: 16.36 -> 15.44Improved
add more image-only training data (60K to 80K images) (ablation)image-only UniST · Image style transfercontent difference D_C: 19.80 -> 19.98No clear effect
replace standard MSA with axial MSA (AMSA) (ablation)UniST · efficiencyFLOPS (G): 4.29 -> 0.27Improved
replace standard MSA with axial MSA (AMSA) (ablation)UniST · 512x512 inferenceseconds per image: 0.182 -> 0.111Improved
use unimodal (image only) input at inference instead of bimodal (ablation)UniST · Image style transferD_C and D_S: 12.36 -> 12.36 (D_C), 0.46 -> 0.46 (D_S)No clear effect
feed output of first MSA as Q, K, V (or Q only) to the second MSA in AMSA (ablation)AMSA · qualitativevisual qualityHurt
retrain image baselines with the same training data as UniST (ablation)CCPL, StyleFormer, IEST, Stytr2, AdaAttN · Image style transferD_C: UniST 12.36 vs best baseline Stytr2 12.87No 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