{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1811.00751","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","created":"2018-11-02","cited_by_count":130},{"id":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106},{"id":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97},{"id":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88},{"id":"2007.07542","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","created":"2020-07-15","cited_by_count":85},{"id":"1806.00926","title":"NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition","created":"2018-06-04","cited_by_count":73},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"1912.12422","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","created":"2019-12-28","cited_by_count":68},{"id":"1910.02562","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","created":"2019-10-07","cited_by_count":65},{"id":"1910.04396","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","created":"2019-10-10","cited_by_count":59},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53},{"id":"2002.01276","title":"GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition","created":"2020-02-04","cited_by_count":52},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","cited_by_count":45},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41},{"id":"2211.10578","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","created":"2022-11-19","cited_by_count":40},{"id":"2111.11011","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","created":"2021-11-22","cited_by_count":36},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34},{"id":"1901.03003","title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","created":"2019-01-10","cited_by_count":30},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27},{"id":"2309.01083","title":"Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning","created":"2023-09-03","cited_by_count":26},{"id":"2112.12916","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","created":"2021-12-24","cited_by_count":25},{"id":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19},{"id":"2305.05140","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","created":"2023-05-09","cited_by_count":18},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13},{"id":"2207.10256","title":"SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition","created":"2022-07-21","cited_by_count":10},{"id":"2305.05322","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","created":"2023-05-09","cited_by_count":9},{"id":"2204.05535","title":"Open-set Text Recognition via Character-Context Decoupling","created":"2022-04-12","cited_by_count":8},{"id":"2308.08806","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","created":"2023-08-17","cited_by_count":8},{"id":"1912.03656","title":"Bidirectional Scene Text Recognition with a Single Decoder","created":"2019-12-08","cited_by_count":7},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7}],"next_cursor":null}