AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition

zhibin ma, Pengwen Dai, Yi Liu, Xugong Qin, Chenyun Yu, Xiaochun Cao

ECCV 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 0 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 rotation-equivariant encoder (F-Conv in RELG) (ablation)RISTER-S · IC13 avg over 4 rotationsaccuracy: 96.98 -> 98.40Improved
add rotation-invariant decoder (RITD) instead of CTC (ablation)RISTER-S · IC13 avg over 4 rotationsaccuracy: 93.82 -> 98.40Improved
add random-rotation augmentation to the non-equivariant-encoder variant (ablation)w/o Rot-E Encoder · IC13 avg over 4 rotationsaccuracy: 96.98 -> 97.25Improved
add random-rotation augmentation to the CTC-decoder variant (ablation)w/o Rot-I Decoder · IC13 avg over 4 rotationsaccuracy: 93.82 -> 95.48Improved
add random-rotation augmentation (ablation)w/o Rot-E Encoder · IC13 0 degreesaccuracy: 98.4 -> 97.5Hurt
add F-Conv equivariant convolutions to ResNet45 (ablation)ResNet45 encoder with RITD · Union14M-B Multi-Orientedaccuracy: 90.8 -> 94.9Improved
add G-CNN equivariant layers to ResNet45 (ablation)ResNet45 encoder with RITD · Union14M-B Multi-Orientedaccuracy: 90.8 -> 90.9No clear effect
add Stand-Alone equivariant self-attention to ViT (ablation)ViT encoder with RITD · IC13 0 degreesaccuracy: 98.5 -> 98.3Mixed
add self-attention global blocks to RELG (ablation)RELG · SVT 0 degreesaccuracy: 96.4 -> 98.3Improved
add self-attention global blocks to RELG (ablation)RELG · Union14M-B Multi-Orientedaccuracy: 95.0 -> 96.6Improved
increase input resolution from 32x128 to 128x128 (ablation)SVTRv2 · Mul-Oriaccuracy: 89.5 -> 90.2Improved
increase input resolution from 32x128 to 128x128 (ablation)IGTR · Mul-Oriaccuracy: 92.6 -> 92.9Improved

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