{"list":"other","total":67,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"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":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2012.03816","title":"Invisible Backdoor Attack with Sample-Specific Triggers","created":"2020-12-07","cited_by_count":353},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2010.08138","title":"Input-Aware Dynamic Backdoor Attack","created":"2020-10-16","cited_by_count":313},{"id":"1912.02771","title":"Label-Consistent Backdoor Attacks","created":"2019-12-05","cited_by_count":296},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"1902.11237","title":"A new Backdoor Attack in CNNs by training set corruption without label poisoning","created":"2019-02-12","cited_by_count":242},{"id":"1301.3666","title":"Zero-Shot Learning Through Cross-Modal Transfer","created":"2013-01-16","cited_by_count":237},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2003.03030","title":"Clean-Label Backdoor Attacks on Video Recognition Models","created":"2020-03-06","cited_by_count":169},{"id":"1511.02251","title":"Learning Visual Features from Large Weakly Supervised Data","created":"2015-11-06","cited_by_count":165},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115},{"id":"1811.12641","title":"Transferable Adversarial Attacks for Image and Video Object Detection","created":"2018-11-30","cited_by_count":109},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69},{"id":"2304.07221","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","created":"2023-04-14","cited_by_count":68},{"id":"2008.00217","title":"Efficient Adversarial Attacks for Visual Object Tracking","created":"2020-08-01","cited_by_count":66},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63},{"id":"2210.01115","title":"LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models","created":"2022-10-03","cited_by_count":59},{"id":"2308.14960","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","created":"2023-08-29","cited_by_count":58},{"id":"2102.10496","title":"Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits","created":"2021-02-21","cited_by_count":49},{"id":"2112.06569","title":"Triangle Attack: A Query-efficient Decision-based Adversarial Attack","created":"2021-12-13","cited_by_count":48},{"id":"2303.18191","title":"Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency","created":"2023-03-27","cited_by_count":46},{"id":"2303.12993","title":"Backdoor Defense via Adaptively Splitting Poisoned Dataset","created":"2023-03-23","cited_by_count":43},{"id":"2306.16697","title":"Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features","created":"2023-06-29","cited_by_count":37},{"id":"2210.04287","title":"Learning to Decompose Visual Features with Latent Textual Prompts","created":"2022-10-09","cited_by_count":28},{"id":"2208.08052","title":"Imperceptible and Robust Backdoor Attack in 3D Point Cloud","created":"2022-08-17","cited_by_count":25},{"id":"2207.13417","title":"Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips","created":"2022-07-27","cited_by_count":22},{"id":"2207.12405","title":"Versatile Weight Attack via Flipping Limited Bits","created":"2022-07-25","cited_by_count":13},{"id":"2109.08868","title":"Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning","created":"2021-09-18","cited_by_count":12}],"next_cursor":null}