{"list":"other","total":78,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"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":"2007.00224","title":"Debiased Contrastive Learning","created":"2020-07-01","cited_by_count":356},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1801.02610","title":"Generating Adversarial Examples with Adversarial Networks","created":"2018-01-08","cited_by_count":258},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"1807.00734","title":"The relativistic discriminator: a key element missing from standard GAN","created":"2018-07-02","cited_by_count":238},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"1801.02612","title":"Spatially Transformed Adversarial Examples","created":"2018-01-08","cited_by_count":195},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"2006.04924","title":"A Self-supervised Approach for Adversarial Robustness","created":"2020-06-08","cited_by_count":180},{"id":"1804.05810","title":"ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector","created":"2018-04-16","cited_by_count":159},{"id":"1712.02328","title":"Generative Adversarial Perturbations","created":"2017-12-06","cited_by_count":153},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"1803.02077","title":"The Contextual Loss for Image Transformation with Non-Aligned Data","created":"2018-03-06","cited_by_count":135},{"id":"1906.07927","title":"SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing","created":"2019-06-19","cited_by_count":93},{"id":"1905.11736","title":"Cross-Domain Transferability of Adversarial Perturbations","created":"2019-05-28","cited_by_count":92},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86},{"id":"1904.06347","title":"Unrestricted Adversarial Examples via Semantic Manipulation","created":"2019-04-12","cited_by_count":84},{"id":"1502.02590","title":"Analysis of classifiers' robustness to adversarial perturbations","created":"2015-02-09","cited_by_count":76},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65},{"id":"1904.05181","title":"Black-box Adversarial Attacks on Video Recognition Models","created":"2019-04-10","cited_by_count":58},{"id":"1802.06430","title":"DARTS: Deceiving Autonomous Cars with Toxic Signs","created":"2018-02-18","cited_by_count":54},{"id":"2201.11528","title":"Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains","created":"2022-01-27","cited_by_count":42},{"id":"1911.09449","title":"Heuristic Black-box Adversarial Attacks on Video Recognition Models","created":"2019-11-21","cited_by_count":37},{"id":"2107.11878","title":"Spatio-Temporal Representation Factorization for Video-based Person Re-Identification","created":"2021-07-25","cited_by_count":29},{"id":"2110.01823","title":"Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations","created":"2021-10-05","cited_by_count":28},{"id":"1707.05495","title":"Order-Free RNN with Visual Attention for Multi-Label Classification","created":"2017-07-18","cited_by_count":26},{"id":"1905.03911","title":"Supporting Analysis of Dimensionality Reduction Results with Contrastive Learning","created":"2019-05-10","cited_by_count":26},{"id":"2108.00146","title":"T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning","created":"2021-07-31","cited_by_count":26},{"id":"2001.03754","title":"Sparse Black-box Video Attack with Reinforcement Learning","created":"2020-01-11","cited_by_count":24},{"id":"1911.13038","title":"Indirect Local Attacks for Context-aware Semantic Segmentation Networks","created":"2019-11-29","cited_by_count":23},{"id":"1901.00546","title":"Multi-Label Adversarial Perturbations","created":"2019-01-02","cited_by_count":18},{"id":"2112.03223","title":"Context-Aware Transfer Attacks for Object Detection","created":"2021-12-06","cited_by_count":18},{"id":"2003.07637","title":"Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior","created":"2020-03-17","cited_by_count":17},{"id":"2203.15230","title":"Zero-Query Transfer Attacks on Context-Aware Object Detectors","created":"2022-03-29","cited_by_count":17},{"id":"2007.09763","title":"Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency","created":"2020-07-19","cited_by_count":16},{"id":"2009.01005","title":"ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation","created":"2020-08-31","cited_by_count":15},{"id":"2003.09565","title":"Non-Adversarial Video Synthesis with Learned Priors","created":"2020-03-21","cited_by_count":13},{"id":"2108.08421","title":"Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes","created":"2021-08-19","cited_by_count":12},{"id":"1908.05185","title":"Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once","created":"2019-08-14","cited_by_count":10},{"id":"2107.09225","title":"Discriminator-Free Generative Adversarial Attack","created":"2021-07-20","cited_by_count":8},{"id":"2108.09929","title":"SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness","created":"2021-08-23","cited_by_count":7},{"id":"2008.05667","title":"Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness","created":"2020-08-13","cited_by_count":6}],"next_cursor":null}