{"list":"other","total":64,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"1904.02884","title":"Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks","created":"2019-04-05","cited_by_count":442},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"1703.08603","title":"Adversarial Examples for Semantic Segmentation and Object Detection","created":"2017-03-24","cited_by_count":275},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"2103.15571","title":"Enhancing the Transferability of Adversarial Attacks through Variance Tuning","created":"2021-03-29","cited_by_count":244},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"1711.09856","title":"On the Robustness of Semantic Segmentation Models to Adversarial Attacks","created":"2017-11-27","cited_by_count":126},{"id":"2007.08270","title":"Kernelized Memory Network for Video Object Segmentation","created":"2020-07-16","cited_by_count":111},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"2003.11540","title":"Learning What to Learn for Video Object Segmentation","created":"2020-03-25","cited_by_count":89},{"id":"2007.06765","title":"Patch-wise Attack for Fooling Deep Neural Network","created":"2020-07-14","cited_by_count":78},{"id":"2108.03151","title":"Full-Duplex Strategy for Video Object Segmentation","created":"2021-08-06","cited_by_count":78},{"id":"2003.00908","title":"Learning Fast and Robust Target Models for Video Object Segmentation","created":"2020-02-27","cited_by_count":76},{"id":"2207.12391","title":"SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness","created":"2022-07-25","cited_by_count":74},{"id":"2109.11404","title":"Hierarchical Memory Matching Network for Video Object Segmentation","created":"2021-09-23","cited_by_count":72},{"id":"2003.04253","title":"Motion-Attentive Transition for Zero-Shot Video Object Segmentation","created":"2020-03-09","cited_by_count":62},{"id":"1605.05863","title":"Siamese Instance Search for Tracking","created":"2016-05-19","cited_by_count":60},{"id":"1803.04242","title":"Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation","created":"2018-03-12","cited_by_count":56},{"id":"2002.05123","title":"Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks","created":"2020-02-12","cited_by_count":36},{"id":"1512.06735","title":"Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs","created":"2015-12-21","cited_by_count":32},{"id":"2003.09595","title":"Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises","created":"2020-03-21","cited_by_count":32},{"id":"2101.08466","title":"Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking","created":"2021-01-21","cited_by_count":31},{"id":"2012.11655","title":"Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation","created":"2020-12-21","cited_by_count":28},{"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":"2103.14938","title":"IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking","created":"2021-03-27","cited_by_count":25},{"id":"2105.11427","title":"Attention-guided Temporally Coherent Video Object Matting","created":"2021-05-24","cited_by_count":25},{"id":"2010.00263","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","created":"2020-10-01","cited_by_count":23},{"id":"2206.07179","title":"Proximal Splitting Adversarial Attacks for Semantic Segmentation","created":"2022-06-14","cited_by_count":23},{"id":"2103.02927","title":"QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval","created":"2021-03-04","cited_by_count":22},{"id":"1810.03783","title":"Unsupervised Online Video Object Segmentation with Motion Property Understanding","created":"2018-10-09","cited_by_count":21},{"id":"1901.05602","title":"Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing","created":"2019-01-17","cited_by_count":16},{"id":"2011.14585","title":"Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack","created":"2020-11-30","cited_by_count":12},{"id":"2204.02791","title":"Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation","created":"2022-04-06","cited_by_count":10},{"id":"2306.12048","title":"Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering","created":"2023-06-21","cited_by_count":6},{"id":"2309.11707","title":"Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation","created":"2023-09-21","cited_by_count":5},{"id":"2309.11933","title":"Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation","created":"2023-09-21","cited_by_count":4},{"id":"2309.12557","title":"Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation","created":"2023-09-22","cited_by_count":1}],"next_cursor":null}