{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"1511.06062","title":"Compact Bilinear Pooling","created":"2015-11-19","cited_by_count":97},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2303.17393","title":"Dynamic Conceptional Contrastive Learning for Generalized Category Discovery","created":"2023-03-30","cited_by_count":92},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86},{"id":"2005.10411","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","created":"2020-05-21","cited_by_count":75},{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73},{"id":"2303.16421","title":"ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models","created":"2023-03-29","cited_by_count":63},{"id":"1512.08086","title":"Part-Stacked CNN for Fine-Grained Visual Categorization","created":"2015-12-26","cited_by_count":62},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53},{"id":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","cited_by_count":51},{"id":"1807.09915","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","created":"2018-07-26","cited_by_count":47},{"id":"2212.01758","title":"Improving Zero-shot Generalization and Robustness of Multi-modal Models","created":"2022-12-04","cited_by_count":45},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43},{"id":"2207.08605","title":"Class-incremental Novel Class Discovery","created":"2022-07-18","cited_by_count":42},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35},{"id":"2305.14107","title":"Federated Generalized Category Discovery","created":"2023-05-23","cited_by_count":27},{"id":"2303.15322","title":"Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning","created":"2023-03-27","cited_by_count":24},{"id":"2304.06385","title":"TransHP: Image Classification with Hierarchical Prompting","created":"2023-04-13","cited_by_count":16},{"id":"2304.02364","title":"What's in a Name? Beyond Class Indices for Image Recognition","created":"2023-04-05","cited_by_count":9},{"id":"2111.03651","title":"The Curious Layperson: Fine-Grained Image Recognition without Expert Labels","created":"2021-11-05","cited_by_count":7},{"id":"2207.12994","title":"V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval","created":"2022-07-26","cited_by_count":3}],"next_cursor":null}