{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","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":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82},{"id":"1610.02055","title":"Places: An Image Database for Deep Scene Understanding","created":"2016-10-06","cited_by_count":76},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2211.12739","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","created":"2022-11-23","cited_by_count":51},{"id":"2301.09506","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","created":"2023-01-23","cited_by_count":43},{"id":"1903.09950","title":"Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention","created":"2019-03-24","cited_by_count":19},{"id":"2312.01564","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","created":"2023-12-04","cited_by_count":19},{"id":"2401.06397","title":"UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding","created":"2024-01-12","cited_by_count":13},{"id":"2010.09103","title":"Unsupervised Foveal Vision Neural Networks with Top-Down Attention","created":"2020-10-18","cited_by_count":2}],"next_cursor":null}