{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"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":"2401.16420","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","created":"2024-01-29","cited_by_count":326},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","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":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"1908.05900","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","created":"2019-08-16","cited_by_count":114},{"id":"2007.09482","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","created":"2020-07-18","cited_by_count":114},{"id":"1801.01671","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","created":"2018-01-05","cited_by_count":109},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84},{"id":"2211.10772","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","created":"2022-11-19","cited_by_count":74},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70},{"id":"2204.01918","title":"Text Spotting Transformers","created":"2022-04-05","cited_by_count":70},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"2105.00405","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","created":"2021-05-02","cited_by_count":65},{"id":"1908.09231","title":"Towards Unconstrained End-to-End Text Spotting","created":"2019-08-24","cited_by_count":57},{"id":"1707.03985","title":"Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks","created":"2017-07-13","cited_by_count":56},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53},{"id":"1803.03474","title":"An end-to-end TextSpotter with Explicit Alignment and Attention","created":"2018-03-09","cited_by_count":50},{"id":"2207.04491","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","created":"2022-07-10","cited_by_count":50},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46},{"id":"1905.05980","title":"Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation","created":"2019-05-15","cited_by_count":45},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","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":"1703.08289","title":"Deep Direct Regression for Multi-Oriented Scene Text Detection","created":"2017-03-24","cited_by_count":37},{"id":"1907.09653","title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition","created":"2019-07-23","cited_by_count":37},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35},{"id":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29},{"id":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26},{"id":"2203.10539","title":"End-to-End Video Text Spotting with Transformer","created":"2022-03-20","cited_by_count":22},{"id":"1903.03299","title":"You Only Recognize Once: Towards Fast Video Text Spotting","created":"2019-03-08","cited_by_count":21},{"id":"2007.07355","title":"TinyVIRAT: Low-resolution Video Action Recognition","created":"2020-07-14","cited_by_count":16},{"id":"2009.01766","title":"Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild","created":"2020-09-03","cited_by_count":15},{"id":"2005.11487","title":"Self-Training for Domain Adaptive Scene Text Detection","created":"2020-05-23","cited_by_count":11},{"id":"2305.03327","title":"FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation","created":"2023-05-05","cited_by_count":10},{"id":"2308.05911","title":"Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking","created":"2023-08-11","cited_by_count":10},{"id":"2308.10408","title":"Turning a CLIP Model into a Scene Text Spotter","created":"2023-08-21","cited_by_count":9},{"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},{"id":"2106.10026","title":"EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021: Team M3EM Technical Report","created":"2021-06-18","cited_by_count":4}],"next_cursor":null}