{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"1901.07042","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","created":"2019-01-21","cited_by_count":597},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"1809.09401","title":"Hypergraph Neural Networks","created":"2018-09-25","cited_by_count":488},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212},{"id":"2301.04558","title":"Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing","created":"2023-01-11","cited_by_count":211},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159},{"id":"2301.02228","title":"MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology","created":"2023-01-05","cited_by_count":149},{"id":"2303.13076","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","created":"2023-03-23","cited_by_count":133},{"id":"2105.00956","title":"UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks","created":"2021-05-03","cited_by_count":130},{"id":"2302.14042","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","created":"2023-02-27","cited_by_count":128},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113},{"id":"2405.18541","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":104},{"id":"1912.12142","title":"Lung and Colon Cancer Histopathological Image Dataset (LC25000)","created":"2019-12-16","cited_by_count":89},{"id":"2301.12959","title":"GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis","created":"2023-01-30","cited_by_count":85},{"id":"2301.13155","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","created":"2023-01-30","cited_by_count":75},{"id":"2101.12355","title":"A Petri Dish for Histopathology Image Analysis","created":"2021-01-29","cited_by_count":64},{"id":"2307.12577","title":"PRIOR: Prototype Representation Joint Learning from Medical Images and Reports","created":"2023-07-24","cited_by_count":55},{"id":"2402.17417","title":"CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification","created":"2024-02-27","cited_by_count":40},{"id":"2503.08497","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","created":"2025-03-11","cited_by_count":39},{"id":"2406.01837","title":"Boosting Vision-Language Models with Transduction","created":"2024-06-03","cited_by_count":36},{"id":"2406.00510","title":"Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection","created":"2024-06-01","cited_by_count":24},{"id":"2402.02045","title":"MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning","created":"2024-02-03","cited_by_count":23},{"id":"2410.00807","title":"WiGNet: Windowed Vision Graph Neural Network","created":"2024-10-01","cited_by_count":8},{"id":"2411.12044","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","created":"2024-11-18","cited_by_count":7},{"id":"2502.02069","title":"LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models","created":"2025-02-04","cited_by_count":7}],"next_cursor":null}