{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1604.04573","title":"CNN-RNN: A Unified Framework for Multi-label Image Classification","created":"2016-04-15","cited_by_count":190},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"1410.0210","title":"A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input","created":"2014-10-01","cited_by_count":112},{"id":"1911.06258","title":"Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA","created":"2019-11-14","cited_by_count":107},{"id":"1505.05612","title":"Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering","created":"2015-05-21","cited_by_count":80},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"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":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"1801.01331","title":"VnCoreNLP: A Vietnamese Natural Language Processing Toolkit","created":"2018-01-04","cited_by_count":51},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41},{"id":"2205.06457","title":"ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation","created":"2022-05-13","cited_by_count":37},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27},{"id":"1709.06307","title":"A Fast and Accurate Vietnamese Word Segmenter","created":"2017-09-19","cited_by_count":21},{"id":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20},{"id":"1612.06530","title":"Automatic Generation of Grounded Visual Questions","created":"2016-12-20","cited_by_count":19},{"id":"2301.10186","title":"ViHOS: Hate Speech Spans Detection for Vietnamese","created":"2023-01-24","cited_by_count":13},{"id":"2308.16383","title":"Separate and Locate: Rethink the Text in Text-based Visual Question Answering","created":"2023-08-31","cited_by_count":7},{"id":"2302.11752","title":"EVJVQA Challenge: Multilingual Visual Question Answering","created":"2023-02-23","cited_by_count":6},{"id":"2310.18046","title":"ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese","created":"2023-10-27","cited_by_count":5},{"id":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3},{"id":"2303.10606","title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","created":"2023-03-19","cited_by_count":2}],"next_cursor":null}