{"list":"other","total":60,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2212.01322","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","created":"2022-12-02","cited_by_count":178},{"id":"2204.13132","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","created":"2022-04-27","cited_by_count":164},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"1810.02575","title":"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime","created":"2018-10-05","cited_by_count":122},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"1808.01265","title":"Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding","created":"2018-08-03","cited_by_count":98},{"id":"2212.04145","title":"Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation","created":"2022-12-08","cited_by_count":98},{"id":"2210.04831","title":"Visual Prompt Tuning for Test-time Domain Adaptation","created":"2022-10-10","cited_by_count":97},{"id":"2204.08808","title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","created":"2022-04-19","cited_by_count":87},{"id":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87},{"id":"2005.14553","title":"Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation","created":"2020-05-28","cited_by_count":86},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83},{"id":"2104.10834","title":"DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation","created":"2021-04-22","cited_by_count":80},{"id":"2305.02317","title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","created":"2023-05-03","cited_by_count":69},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65},{"id":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60},{"id":"2304.00690","title":"3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds","created":"2023-04-03","cited_by_count":46},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45},{"id":"1901.01415","title":"Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding","created":"2019-01-05","cited_by_count":40},{"id":"2304.07919","title":"Chain of Thought Prompt Tuning in Vision Language Models","created":"2023-04-16","cited_by_count":34},{"id":"2204.01587","title":"FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation","created":"2022-04-04","cited_by_count":31},{"id":"2207.06825","title":"Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions","created":"2022-07-14","cited_by_count":31},{"id":"2311.03648","title":"Instruct Me More! Random Prompting for Visual In-Context Learning","created":"2023-11-07","cited_by_count":30},{"id":"2402.03631","title":"CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model","created":"2024-02-06","cited_by_count":27},{"id":"2112.00484","title":"Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding","created":"2021-12-01","cited_by_count":26},{"id":"2307.09362","title":"Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement","created":"2023-07-18","cited_by_count":12},{"id":"2309.15251","title":"VPA: Fully Test-Time Visual Prompt Adaptation","created":"2023-09-26","cited_by_count":11},{"id":"2201.02588","title":"FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images","created":"2022-01-07","cited_by_count":7},{"id":"2401.10005","title":"Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation","created":"2024-01-18","cited_by_count":2}],"next_cursor":null}