{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"1507.07629","title":"Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades","created":"2015-07-28","cited_by_count":314},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"1803.07913","title":"HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification","created":"2018-03-21","cited_by_count":218},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2009.08283","title":"Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy","created":"2020-09-17","cited_by_count":125},{"id":"2203.17149","title":"AEGNN: Asynchronous Event-based Graph Neural Networks","created":"2022-03-31","cited_by_count":118},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2003.09148","title":"Event-based Asynchronous Sparse Convolutional Networks","created":"2020-03-20","cited_by_count":104},{"id":"1811.08230","title":"Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks","created":"2018-11-20","cited_by_count":97},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90},{"id":"1908.06648","title":"Graph-Based Object Classification for Neuromorphic Vision Sensing","created":"2019-08-19","cited_by_count":85},{"id":"2207.01077","title":"Can Language Understand Depth?","created":"2022-07-03","cited_by_count":69},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","cited_by_count":69},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41},{"id":"2106.00216","title":"A Voxel Graph CNN for Object Classification with Event Cameras","created":"2021-06-01","cited_by_count":38},{"id":"2106.05836","title":"EventDrop: data augmentation for event-based learning","created":"2021-06-07","cited_by_count":28},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28},{"id":"2212.09737","title":"Position-guided Text Prompt for Vision-Language Pre-training","created":"2022-12-19","cited_by_count":27},{"id":"2202.05054","title":"Exploiting Spatial Sparsity for Event Cameras with Visual Transformers","created":"2022-02-10","cited_by_count":23},{"id":"2002.11656","title":"Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras","created":"2020-02-26","cited_by_count":19},{"id":"2302.14736","title":"TextIR: A Simple Framework for Text-based Editable Image Restoration","created":"2023-02-28","cited_by_count":17},{"id":"2008.08046","title":"TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition","created":"2020-08-01","cited_by_count":16},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14}],"next_cursor":null}