{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"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":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"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":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2112.07916","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","created":"2021-12-15","cited_by_count":232},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"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":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90},{"id":"2106.06169","title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","created":"2021-06-11","cited_by_count":75},{"id":"1904.01475","title":"Good News, Everyone! Context driven entity-aware captioning for news images","created":"2019-04-02","cited_by_count":66},{"id":"2207.09666","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","created":"2022-07-20","cited_by_count":56},{"id":"2004.12316","title":"Towards Persona-Based Empathetic Conversational Models","created":"2020-04-26","cited_by_count":53},{"id":"2004.08070","title":"Transform and Tell: Entity-Aware News Image Captioning","created":"2020-04-17","cited_by_count":52},{"id":"2103.09120","title":"Structural Adapters in Pretrained Language Models for AMR-to-text Generation","created":"2021-03-16","cited_by_count":48},{"id":"2004.07672","title":"Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation","created":"2020-04-16","cited_by_count":41},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33},{"id":"2107.11970","title":"Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph","created":"2021-07-26","cited_by_count":31},{"id":"2109.12487","title":"Parallel Refinements for Lexically Constrained Text Generation with BART","created":"2021-09-26","cited_by_count":24},{"id":"1908.08529","title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning","created":"2019-08-22","cited_by_count":21},{"id":"1603.07141","title":"BreakingNews: Article Annotation by Image and Text Processing","created":"2016-03-23","cited_by_count":20},{"id":"2305.03668","title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding","created":"2023-05-05","cited_by_count":18},{"id":"2212.01803","title":"Controllable Image Captioning via Prompting","created":"2022-12-04","cited_by_count":15},{"id":"2109.02865","title":"Journalistic Guidelines Aware News Image Captioning","created":"2021-09-07","cited_by_count":14},{"id":"2308.08325","title":"Visually-Aware Context Modeling for News Image Captioning","created":"2023-08-16","cited_by_count":12},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10},{"id":"2212.00843","title":"Focus! Relevant and Sufficient Context Selection for News Image Captioning","created":"2022-12-01","cited_by_count":10},{"id":"2104.08857","title":"Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation","created":"2021-04-18","cited_by_count":9},{"id":"2306.00931","title":"\"Let's not Quote out of Context\": Unified Vision-Language Pretraining for Context Assisted Image Captioning","created":"2023-06-01","cited_by_count":7}],"next_cursor":null}