{"list":"other","total":65,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"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":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2303.13899","title":"Robust Test-Time Adaptation in Dynamic Scenarios","created":"2023-03-24","cited_by_count":189},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","cited_by_count":164},{"id":"2308.06038","title":"Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning","created":"2023-08-11","cited_by_count":154},{"id":"2110.03374","title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","created":"2021-10-07","cited_by_count":152},{"id":"2403.18293","title":"Efficient Test-Time Adaptation of Vision-Language Models","created":"2024-03-27","cited_by_count":141},{"id":"1912.06798","title":"Cross-Batch Memory for Embedding Learning","created":"2019-12-14","cited_by_count":132},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"2104.13415","title":"Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank","created":"2021-04-27","cited_by_count":125},{"id":"2303.01904","title":"EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization","created":"2023-03-03","cited_by_count":123},{"id":"2103.04224","title":"MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection","created":"2021-03-07","cited_by_count":106},{"id":"2311.01459","title":"Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization","created":"2023-11-02","cited_by_count":101},{"id":"2403.14119","title":"C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion","created":"2024-03-21","cited_by_count":83},{"id":"2106.14999","title":"Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation","created":"2021-06-28","cited_by_count":68},{"id":"1704.05737","title":"Learning Video Object Segmentation with Visual Memory","created":"2017-04-19","cited_by_count":66},{"id":"2301.05792","title":"RMM: Reinforced Memory Management for Class-Incremental Learning","created":"2023-01-14","cited_by_count":66},{"id":"2106.02885","title":"Category Contrast for Unsupervised Domain Adaptation in Visual Tasks","created":"2021-06-05","cited_by_count":65},{"id":"2207.10792","title":"Test-Time Adaptation via Self-Training with Nearest Neighbor Information","created":"2022-07-08","cited_by_count":64},{"id":"2210.01253","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","created":"2022-10-03","cited_by_count":64},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2106.02874","title":"RDA: Robust Domain Adaptation via Fourier Adversarial Attacking","created":"2021-06-05","cited_by_count":48},{"id":"2303.10902","title":"Feature Alignment and Uniformity for Test Time Adaptation","created":"2023-03-20","cited_by_count":42},{"id":"2106.06112","title":"Spectral Unsupervised Domain Adaptation for Visual Recognition","created":"2021-06-11","cited_by_count":40},{"id":"2312.09627","title":"TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification","created":"2023-12-15","cited_by_count":40},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35},{"id":"2103.17084","title":"DA-DETR: Domain Adaptive Detection Transformer with Information Fusion","created":"2021-03-31","cited_by_count":24},{"id":"2210.10362","title":"CPL: Counterfactual Prompt Learning for Vision and Language Models","created":"2022-10-19","cited_by_count":18},{"id":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13},{"id":"2401.09923","title":"MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection","created":"2024-01-18","cited_by_count":13},{"id":"2308.13236","title":"Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory","created":"2023-08-25","cited_by_count":11},{"id":"2401.14856","title":"Memory-Inspired Temporal Prompt Interaction for Text-Image Classification","created":"2024-01-26","cited_by_count":1}],"next_cursor":null}