{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"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":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2102.09508","title":"Domain Adaptation for Medical Image Analysis: A Survey","created":"2021-02-18","cited_by_count":352},{"id":"1712.06087","title":"\"Zero-Shot\" Super-Resolution using Deep Internal Learning","created":"2017-12-17","cited_by_count":286},{"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":"2201.05718","title":"Parameter-free Online Test-time Adaptation","created":"2022-01-15","cited_by_count":189},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"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":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77},{"id":"2204.12667","title":"MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation","created":"2022-04-27","cited_by_count":76},{"id":"1911.12036","title":"Discriminative Adversarial Domain Adaptation","created":"2019-11-27","cited_by_count":74},{"id":"2207.01077","title":"Can Language Understand Depth?","created":"2022-07-03","cited_by_count":69},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69},{"id":"2404.03635","title":"WorDepth: Variational Language Prior for Monocular Depth Estimation","created":"2024-04-04","cited_by_count":34},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33},{"id":"2110.12369","title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","created":"2021-10-24","cited_by_count":31},{"id":"2303.00914","title":"Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation","created":"2023-03-02","cited_by_count":23},{"id":"2310.19011","title":"Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction","created":"2023-10-29","cited_by_count":18},{"id":"2403.12033","title":"HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation","created":"2024-03-18","cited_by_count":14},{"id":"2303.11180","title":"Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation","created":"2023-03-20","cited_by_count":7},{"id":"2408.13983","title":"Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation","created":"2024-08-26","cited_by_count":4}],"next_cursor":null}