{"list":"other","total":71,"rows":[{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2004.05498","title":"FDA: Fourier Domain Adaptation for Semantic Segmentation","created":"2020-04-11","cited_by_count":541},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1703.01780","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","created":"2017-03-06","cited_by_count":472},{"id":"2106.01226","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","created":"2021-06-02","cited_by_count":463},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"1908.09822","title":"Confidence Regularized Self-Training","created":"2019-08-26","cited_by_count":419},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"1812.04798","title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","created":"2018-12-12","cited_by_count":270},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268},{"id":"1612.02649","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","created":"2016-12-08","cited_by_count":243},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2007.08702","title":"DACS: Domain Adaptation via Cross-domain Mixed Sampling","created":"2020-07-17","cited_by_count":226},{"id":"2105.00097","title":"Self-supervised Augmentation Consistency for Adapting Semantic Segmentation","created":"2021-04-30","cited_by_count":149},{"id":"1909.00589","title":"Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation","created":"2019-09-02","cited_by_count":126},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"1808.01265","title":"Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding","created":"2018-08-03","cited_by_count":98},{"id":"1711.11556","title":"ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes","created":"2017-11-30","cited_by_count":95},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2104.13613","title":"Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-04-28","cited_by_count":80},{"id":"2105.08128","title":"PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training","created":"2021-05-17","cited_by_count":80},{"id":"2108.03557","title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","created":"2021-08-08","cited_by_count":79},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"1703.10664","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","created":"2017-03-30","cited_by_count":50},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"1506.01929","title":"Learning to track for spatio-temporal action localization","created":"2015-06-05","cited_by_count":44},{"id":"1911.00232","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","created":"2019-11-01","cited_by_count":37},{"id":"1608.01529","title":"Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos","created":"2016-08-04","cited_by_count":35},{"id":"1708.00938","title":"Associative Domain Adaptation","created":"2017-08-02","cited_by_count":32},{"id":"1805.08162","title":"VideoCapsuleNet: A Simplified Network for Action Detection","created":"2018-05-21","cited_by_count":30},{"id":"1911.10751","title":"Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition","created":"2019-11-25","cited_by_count":21},{"id":"2104.07461","title":"Action Segmentation with Mixed Temporal Domain Adaptation","created":"2021-04-15","cited_by_count":21},{"id":"2203.04251","title":"End-to-End Semi-Supervised Learning for Video Action Detection","created":"2022-03-08","cited_by_count":17},{"id":"2001.11657","title":"Modality Compensation Network: Cross-Modal Adaptation for Action Recognition","created":"2020-01-31","cited_by_count":16},{"id":"1805.11333","title":"Pointly-Supervised Action Localization","created":"2018-05-29","cited_by_count":12},{"id":"1704.04952","title":"AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture","created":"2017-04-17","cited_by_count":9},{"id":"1808.00297","title":"TraMNet - Transition Matrix Network for Efficient Action Tube Proposals","created":"2018-08-01","cited_by_count":6},{"id":"2010.09211","title":"Unsupervised Domain Adaptation for Spatio-Temporal Action Localization","created":"2020-10-19","cited_by_count":6},{"id":"1704.01358","title":"Incremental Tube Construction for Human Action Detection","created":"2017-04-05","cited_by_count":5},{"id":"2011.10927","title":"We don't Need Thousand Proposals$\\colon$ Single Shot Actor-Action Detection in Videos","created":"2020-11-22","cited_by_count":5},{"id":"1802.08362","title":"Real-Time End-to-End Action Detection with Two-Stream Networks","created":"2018-02-23","cited_by_count":4}],"next_cursor":null}