{"list":"other","total":79,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"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":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"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":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"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":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"1811.04256","title":"Scene Text Detection and Recognition: The Deep Learning Era","created":"2018-11-10","cited_by_count":114},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86},{"id":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81},{"id":"1603.03101","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","created":"2016-03-09","cited_by_count":74},{"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":"1910.05085","title":"Rosetta: Large scale system for text detection and recognition in images","created":"2019-10-11","cited_by_count":69},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69},{"id":"1912.12422","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","created":"2019-12-28","cited_by_count":68},{"id":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63},{"id":"1809.06508","title":"Scene Text Recognition from Two-Dimensional Perspective","created":"2018-09-18","cited_by_count":57},{"id":"2106.12326","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","created":"2021-06-23","cited_by_count":46},{"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":"1506.04395","title":"Reading Scene Text in Deep Convolutional Sequences","created":"2015-06-14","cited_by_count":44},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41},{"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":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27},{"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":"2301.07464","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","created":"2023-01-18","cited_by_count":16},{"id":"2106.06960","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2021-06-13","cited_by_count":6}],"next_cursor":null}