{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1801.00553","title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","created":"2018-01-02","cited_by_count":460},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"1712.03141","title":"Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning","created":"2017-12-08","cited_by_count":414},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1712.07107","title":"Adversarial Examples: Attacks and Defenses for Deep Learning","created":"2017-12-19","cited_by_count":351},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"id":"2010.03593","title":"Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples","created":"2020-10-07","cited_by_count":278},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"1909.08072","title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","created":"2019-09-17","cited_by_count":237},{"id":"2006.10963","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","created":"2020-06-19","cited_by_count":236},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207},{"id":"2010.00467","title":"Bag of Tricks for Adversarial Training","created":"2020-10-01","cited_by_count":200},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2103.15670","title":"On the Adversarial Robustness of Vision Transformers","created":"2021-03-29","cited_by_count":106},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"2002.06622","title":"Robustness Verification for Transformers","created":"2020-02-16","cited_by_count":76},{"id":"2008.09837","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","created":"2020-08-22","cited_by_count":75},{"id":"2007.00753","title":"Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey","created":"2020-07-01","cited_by_count":72},{"id":"1807.10706","title":"Diagnosing Error in Temporal Action Detectors","created":"2018-07-27","cited_by_count":71},{"id":"2106.04169","title":"On Improving Adversarial Transferability of Vision Transformers","created":"2021-06-08","cited_by_count":70},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57},{"id":"2010.03630","title":"Revisiting Batch Normalization for Improving Corruption Robustness","created":"2020-10-07","cited_by_count":55},{"id":"2012.03457","title":"VideoMix: Rethinking Data Augmentation for Video Classification","created":"2020-12-07","cited_by_count":55},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2110.07858","title":"Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation","created":"2021-10-15","cited_by_count":40},{"id":"2204.02932","title":"An Empirical Study of End-to-End Temporal Action Detection","created":"2022-04-06","cited_by_count":40},{"id":"2103.16241","title":"Improving robustness against common corruptions with frequency biased models","created":"2021-03-30","cited_by_count":34},{"id":"2110.06513","title":"Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions","created":"2021-10-13","cited_by_count":34},{"id":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29},{"id":"2207.01398","title":"Large-scale Robustness Analysis of Video Action Recognition Models","created":"2022-07-04","cited_by_count":29},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29},{"id":"2005.08087","title":"Universal Adversarial Perturbations: A Survey","created":"2020-05-16","cited_by_count":28},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28},{"id":"2203.13639","title":"Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness","created":"2022-03-25","cited_by_count":23},{"id":"2303.11126","title":"Robustifying Token Attention for Vision Transformers","created":"2023-03-20","cited_by_count":19},{"id":"2008.05721","title":"Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition","created":"2020-08-13","cited_by_count":13},{"id":"1904.07442","title":"Decoupling Localization and Classification in Single Shot Temporal Action Detection","created":"2019-04-16","cited_by_count":11},{"id":"1608.08128","title":"Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks","created":"2016-08-29","cited_by_count":10},{"id":"2206.15015","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","created":"2022-06-30","cited_by_count":9},{"id":"1905.01722","title":"Intra-clip Aggregation for Video Person Re-identification","created":"2019-05-05","cited_by_count":8}],"next_cursor":null}