Research map / Video / Video-language understanding
GLOMA: Global Video Text Spotting with Morphological Association
Han Wang, Yanjie Wang, Yang Li, Can Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes GLOMA, a global video text spotting method that associates text instances across frames using morphological characteristics instead of local IoU-based association and complex post-processing.
Problem
Video Text Spotting (VTS), predicting the trajectories and content of texts in videos; prior methods rely on local association with IoU-based distance and complex post-processing, ignoring temporal information and morphological characteristics.
Approach
Models the tracking problem globally over the video, exploiting abundant temporal information and the morphological characteristics of text, rather than local IoU-based frame-to-frame association with heavy post-processing.
Closest papers by meaning
- End-to-End Video Text Spotting with Transformer (IJCV 2024 · similarity 0.90)
- GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching (NeurIPS 2024 · similarity 0.88)
- VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization (TPAMI 2025 · similarity 0.87)
- Beyond Detection: A Structure-Aware Framework for Scene Text Tracking (ICML 2026 · similarity 0.86)
- A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer (NeurIPS 2021 · similarity 0.85)
- SwinTextSpotter: Scene Text Spotting via Better Synergy Between Text Detection and Text Recognition (CVPR 2022 · similarity 0.85)
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.
