{"list":"other","total":60,"rows":[{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1704.04232","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","created":"2017-04-13","cited_by_count":207},{"id":"2204.13132","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","created":"2022-04-27","cited_by_count":164},{"id":"2007.08103","title":"Probabilistic Anchor Assignment with IoU Prediction for Object Detection","created":"2020-07-16","cited_by_count":150},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"1703.03329","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","created":"2017-03-09","cited_by_count":130},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"1711.08189","title":"An Analysis of Scale Invariance in Object Detection - SNIP","created":"2017-11-22","cited_by_count":120},{"id":"1712.05080","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","created":"2017-12-14","cited_by_count":100},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90},{"id":"1805.09300","title":"SNIPER: Efficient Multi-Scale Training","created":"2018-05-23","cited_by_count":88},{"id":"1802.10151","title":"Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data","created":"2018-02-27","cited_by_count":76},{"id":"1807.08333","title":"AutoLoc: Weakly-supervised Temporal Action Localization","created":"2018-07-22","cited_by_count":75},{"id":"1911.09963","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","created":"2019-11-22","cited_by_count":73},{"id":"1807.10706","title":"Diagnosing Error in Temporal Action Detectors","created":"2018-07-27","cited_by_count":71},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69},{"id":"2003.12424","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","created":"2020-03-27","cited_by_count":59},{"id":"2010.11594","title":"Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization","created":"2020-10-22","cited_by_count":53},{"id":"1812.01600","title":"AutoFocus: Efficient Multi-Scale Inference","created":"2018-12-04","cited_by_count":46},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43},{"id":"2007.14449","title":"Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation","created":"2020-07-28","cited_by_count":41},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40},{"id":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34},{"id":"2203.02925","title":"Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation","created":"2022-03-06","cited_by_count":32},{"id":"2203.16897","title":"Multi-Granularity Alignment Domain Adaptation for Object Detection","created":"2022-03-31","cited_by_count":29},{"id":"2010.15764","title":"Domain adaptation under structural causal models","created":"2020-10-29","cited_by_count":28},{"id":"1603.08358","title":"Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs","created":"2016-03-28","cited_by_count":27},{"id":"1807.02929","title":"Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector","created":"2018-07-09","cited_by_count":27},{"id":"2104.14135","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","created":"2021-04-29","cited_by_count":26},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26},{"id":"1904.00227","title":"RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization","created":"2019-03-30","cited_by_count":24},{"id":"2203.05114","title":"OpenTAL: Towards Open Set Temporal Action Localization","created":"2022-03-10","cited_by_count":23},{"id":"2303.12332","title":"Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature","created":"2023-03-22","cited_by_count":22},{"id":"2305.17861","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","created":"2023-05-29","cited_by_count":20},{"id":"2104.02967","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","created":"2021-04-07","cited_by_count":19},{"id":"1910.01286","title":"Learning Temporal Action Proposals With Fewer Labels","created":"2019-10-03","cited_by_count":17},{"id":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17},{"id":"2204.04615","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","created":"2022-04-10","cited_by_count":16},{"id":"1908.02422","title":"Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization","created":"2019-08-07","cited_by_count":14},{"id":"2309.05590","title":"Temporal Action Localization with Enhanced Instant Discriminability","created":"2023-09-11","cited_by_count":13},{"id":"2307.16415","title":"DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization","created":"2023-07-31","cited_by_count":7},{"id":"2205.00400","title":"Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization","created":"2022-05-01","cited_by_count":2},{"id":"2304.12616","title":"Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint","created":"2023-04-25","cited_by_count":2}],"next_cursor":null}