{"list":"other","total":63,"rows":[{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"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":"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2303.14070","title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","created":"2023-03-24","cited_by_count":325},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2305.04790","title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","created":"2023-05-08","cited_by_count":255},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2007.09654","title":"Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets","created":"2020-07-19","cited_by_count":122},{"id":"2308.09442","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","created":"2023-08-18","cited_by_count":100},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68},{"id":"2103.03375","title":"Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food","created":"2021-03-04","cited_by_count":58},{"id":"1901.09891","title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","created":"2019-01-26","cited_by_count":56},{"id":"1812.06164","title":"Inverse Cooking: Recipe Generation from Food Images","created":"2018-12-14","cited_by_count":47},{"id":"2008.05655","title":"ISIA Food-500: A Dataset for Large-Scale Food Recognition via Stacked Global-Local Attention Network","created":"2020-08-13","cited_by_count":47},{"id":"2105.05409","title":"A Large-Scale Benchmark for Food Image Segmentation","created":"2021-05-12","cited_by_count":45},{"id":"2003.02498","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","created":"2020-03-05","cited_by_count":34},{"id":"1705.02743","title":"ChineseFoodNet: A large-scale Image Dataset for Chinese Food Recognition","created":"2017-05-08","cited_by_count":21},{"id":"1905.06269","title":"Food Recommendation: Framework, Existing Solutions and Challenges","created":"2019-05-15","cited_by_count":21},{"id":"2003.03955","title":"Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism","created":"2020-03-09","cited_by_count":20},{"id":"2012.12509","title":"Deep Semantic Dictionary Learning for Multi-label Image Classification","created":"2020-12-23","cited_by_count":20},{"id":"1606.05675","title":"DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment","created":"2016-06-17","cited_by_count":19},{"id":"2009.00944","title":"Structure-Aware Generation Network for Recipe Generation from Images","created":"2020-09-02","cited_by_count":19},{"id":"2308.05938","title":"FoodSAM: Any Food Segmentation","created":"2023-08-11","cited_by_count":19},{"id":"1612.06543","title":"Wide-Slice Residual Networks for Food Recognition","created":"2016-12-20","cited_by_count":18},{"id":"1909.11946","title":"FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging","created":"2019-09-26","cited_by_count":18},{"id":"2308.14391","title":"FIRE: Food Image to REcipe generation","created":"2023-08-28","cited_by_count":18},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17},{"id":"2207.03692","title":"Mining Discriminative Food Regions for Accurate Food Recognition","created":"2022-07-08","cited_by_count":14},{"id":"1907.13075","title":"Pay attention to the activations: a modular attention mechanism for fine-grained image recognition","created":"2019-07-30","cited_by_count":12},{"id":"2301.07236","title":"Effective End-to-End Vision Language Pretraining with Semantic Visual Loss","created":"2023-01-18","cited_by_count":10},{"id":"2312.04763","title":"Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective","created":"2023-12-08","cited_by_count":10},{"id":"1702.06318","title":"Is Saki #delicious? The Food Perception Gap on Instagram and Its Relation to Health","created":"2017-02-21","cited_by_count":8},{"id":"1707.08816","title":"Food Ingredients Recognition through Multi-label Learning","created":"2017-07-27","cited_by_count":6},{"id":"2012.03087","title":"MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring","created":"2020-12-05","cited_by_count":6},{"id":"2306.09203","title":"Transferring Knowledge for Food Image Segmentation using Transformers and Convolutions","created":"2023-06-15","cited_by_count":5},{"id":"2004.03357","title":"Deep learning approaches in food recognition","created":"2020-04-04","cited_by_count":3}],"next_cursor":null}