{"total":14,"rows":[{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200,"area":null},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44,"area":null},{"id":"2305.03347","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2203.10539","title":"End-to-End Video Text Spotting with Transformer","created":"2022-03-20","cited_by_count":22,"area":null},{"id":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2305.03327","title":"FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation","created":"2023-05-05","cited_by_count":10,"area":null},{"id":"2308.10408","title":"Turning a CLIP Model into a Scene Text Spotter","created":"2023-08-21","cited_by_count":9,"area":null},{"id":"2312.05286","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2207.08417","title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2312.01938","title":"DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text","created":"2023-11-29","cited_by_count":7,"area":null},{"id":"2205.04683","title":"UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2212.00377","title":"Domain Adaptive Scene Text Detection via Subcategorization","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2310.00917","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2404.19652","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization","created":"2024-04-30","cited_by_count":0,"area":null}],"next_cursor":null}