{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"1903.08536","title":"Segmentation-Based Deep-Learning Approach for Surface-Defect Detection","created":"2019-03-20","cited_by_count":145},{"id":"2011.11156","title":"Better Aggregation in Test-Time Augmentation","created":"2020-11-23","cited_by_count":122},{"id":"2011.05005","title":"Deep Multimodal Fusion by Channel Exchanging","created":"2020-11-10","cited_by_count":118},{"id":"2110.02855","title":"Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection","created":"2021-10-06","cited_by_count":117},{"id":"2303.17569","title":"Iterative Prompt Learning for Unsupervised Backlit Image Enhancement","created":"2023-03-30","cited_by_count":107},{"id":"2104.06064","title":"Mixed supervision for surface-defect detection: from weakly to fully supervised learning","created":"2021-04-13","cited_by_count":101},{"id":"1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","created":"2019-02-19","cited_by_count":95},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"1609.03605","title":"Detecting Text in Natural Image with Connectionist Text Proposal Network","created":"2016-09-12","cited_by_count":85},{"id":"2202.08341","title":"Anomalib: A Deep Learning Library for Anomaly Detection","created":"2022-02-16","cited_by_count":75},{"id":"2204.00102","title":"Dynamic Multimodal Fusion","created":"2022-03-31","cited_by_count":55},{"id":"2305.11307","title":"Semantic Anomaly Detection with Large Language Models","created":"2023-05-18","cited_by_count":53},{"id":"2103.13582","title":"Learning Dynamic Alignment via Meta-filter for Few-shot Learning","created":"2021-03-25","cited_by_count":41},{"id":"2305.15302","title":"Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation","created":"2023-05-24","cited_by_count":36},{"id":"2112.01030","title":"TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning","created":"2021-12-02","cited_by_count":32},{"id":"2302.03751","title":"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective","created":"2023-02-07","cited_by_count":28},{"id":"2206.06367","title":"Does a Technique for Building Multimodal Representation Matter? -- Comparative Analysis","created":"2022-06-09","cited_by_count":22},{"id":"1904.08486","title":"Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset","created":"2019-04-02","cited_by_count":21},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21},{"id":"2311.01034","title":"Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation","created":"2023-11-02","cited_by_count":20},{"id":"2103.10895","title":"Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark","created":"2021-03-19","cited_by_count":17},{"id":"2306.09996","title":"Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering","created":"2023-06-16","cited_by_count":14},{"id":"2112.02252","title":"Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction","created":"2021-12-04","cited_by_count":11},{"id":"2203.02489","title":"Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion","created":"2022-03-04","cited_by_count":5},{"id":"2307.04838","title":"CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction","created":"2023-07-10","cited_by_count":4},{"id":"2208.03288","title":"Convolutional Ensembling based Few-Shot Defect Detection Technique","created":"2022-08-05","cited_by_count":1}],"next_cursor":null}