{"list":"other","total":71,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2305.17100","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","created":"2023-05-26","cited_by_count":201},{"id":"2004.07703","title":"Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision","created":"2020-04-16","cited_by_count":198},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"1909.13589","title":"Domain Adaptation for Semantic Segmentation with Maximum Squares Loss","created":"2019-09-30","cited_by_count":138},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"1407.5736","title":"Learning Rich Features from RGB-D Images for Object Detection and Segmentation","created":"2014-07-22","cited_by_count":127},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2304.04709","title":"Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection","created":"2023-04-10","cited_by_count":100},{"id":"2304.06022","title":"SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything","created":"2023-04-12","cited_by_count":75},{"id":"2003.12789","title":"Polarized Reflection Removal with Perfect Alignment in the Wild","created":"2020-03-28","cited_by_count":69},{"id":"2112.11377","title":"Shape from Polarization for Complex Scenes in the Wild","created":"2021-12-21","cited_by_count":53},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41},{"id":"2203.07436","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","created":"2022-03-14","cited_by_count":39},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34},{"id":"2204.05453","title":"Glass Segmentation with RGB-Thermal Image Pairs","created":"2022-04-12","cited_by_count":26},{"id":"2011.13313","title":"Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion","created":"2020-11-26","cited_by_count":24},{"id":"2207.09988","title":"DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation","created":"2022-07-20","cited_by_count":23},{"id":"1701.02511","title":"Heterogeneous domain adaptation: An unsupervised approach","created":"2017-01-10","cited_by_count":17},{"id":"2108.09682","title":"Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification","created":"2021-08-22","cited_by_count":15},{"id":"2301.02120","title":"Reprogramming Pretrained Language Models for Protein Sequence Representation Learning","created":"2023-01-05","cited_by_count":12},{"id":"2310.00730","title":"EventLFM: Event Camera integrated Fourier Light Field Microscopy for Ultrafast 3D imaging","created":"2023-10-01","cited_by_count":12},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6},{"id":"1904.04061","title":"Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain","created":"2019-04-08","cited_by_count":5},{"id":"2211.00227","title":"Transfer Learning with Kernel Methods","created":"2022-11-01","cited_by_count":5},{"id":"2207.12570","title":"Seeing Far in the Dark with Patterned Flash","created":"2022-07-25","cited_by_count":1}],"next_cursor":null}