{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"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":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2305.15075","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","created":"2023-05-24","cited_by_count":214},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194},{"id":"2104.12836","title":"Multimodal Contrastive Training for Visual Representation Learning","created":"2021-04-26","cited_by_count":124},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"1810.07212","title":"Cross-Modal and Hierarchical Modeling of Video and Text","created":"2018-10-16","cited_by_count":103},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"2306.09968","title":"ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation","created":"2023-06-16","cited_by_count":88},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"1803.01207","title":"Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning","created":"2018-03-03","cited_by_count":81},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2107.12435","title":"A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation","created":"2021-07-26","cited_by_count":41},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39},{"id":"2207.13162","title":"Retrieval-Augmented Transformer for Image Captioning","created":"2022-07-26","cited_by_count":38},{"id":"2306.00576","title":"MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding","created":"2023-06-01","cited_by_count":36},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36},{"id":"2311.15879","title":"EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension","created":"2023-11-27","cited_by_count":32},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32},{"id":"2403.05949","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","created":"2024-03-09","cited_by_count":25},{"id":"1703.10701","title":"Concurrent Segmentation and Localization for Tracking of Surgical Instruments","created":"2017-03-30","cited_by_count":24},{"id":"1703.08580","title":"Deep Residual Learning for Instrument Segmentation in Robotic Surgery","created":"2017-03-24","cited_by_count":22},{"id":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20},{"id":"2111.04911","title":"Real-time Instance Segmentation of Surgical Instruments using Attention and Multi-scale Feature Fusion","created":"2021-11-09","cited_by_count":17},{"id":"2107.00875","title":"LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos","created":"2021-07-02","cited_by_count":15},{"id":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","cited_by_count":12},{"id":"2007.04505","title":"Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks","created":"2020-07-09","cited_by_count":7},{"id":"2306.06010","title":"A Large-Scale Analysis on Self-Supervised Video Representation Learning","created":"2023-06-09","cited_by_count":5}],"next_cursor":null}