{"list":"other","total":131,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"1808.01974","title":"A Survey on Deep Transfer Learning","created":"2018-08-06","cited_by_count":419},{"id":"1511.05547","title":"Return of Frustratingly Easy Domain Adaptation","created":"2015-11-17","cited_by_count":391},{"id":"2003.09005","title":"Semi-Supervised Semantic Segmentation with Cross-Consistency Training","created":"2020-03-19","cited_by_count":376},{"id":"1802.03916","title":"Detecting and Correcting for Label Shift with Black Box Predictors","created":"2018-02-12","cited_by_count":366},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1905.03670","title":"S4L: Self-Supervised Semi-Supervised Learning","created":"2019-05-09","cited_by_count":335},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1406.6909","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","created":"2014-06-26","cited_by_count":300},{"id":"1706.07567","title":"Sampling Matters in Deep Embedding Learning","created":"2017-06-23","cited_by_count":285},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1912.01805","title":"Adversarial Domain Adaptation with Domain Mixup","created":"2019-12-04","cited_by_count":250},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1906.03950","title":"Domain-Specific Batch Normalization for Unsupervised Domain Adaptation","created":"2019-05-27","cited_by_count":197},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"1712.00479","title":"Image to Image Translation for Domain Adaptation","created":"2017-12-01","cited_by_count":171},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"id":"1607.03516","title":"Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation","created":"2016-07-12","cited_by_count":163},{"id":"1901.05335","title":"A review of domain adaptation without target labels","created":"2019-01-16","cited_by_count":156},{"id":"2006.00632","title":"Neural Unsupervised Domain Adaptation in NLP---A Survey","created":"2020-05-31","cited_by_count":144},{"id":"1911.02054","title":"Federated Adversarial Domain Adaptation","created":"2019-11-05","cited_by_count":140},{"id":"1904.11245","title":"Exploring Object Relation in Mean Teacher for Cross-Domain Detection","created":"2019-04-25","cited_by_count":137},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137},{"id":"2112.00463","title":"The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization","created":"2021-12-01","cited_by_count":131},{"id":"1702.05374","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","created":"2017-02-17","cited_by_count":128},{"id":"1808.04205","title":"Partial Adversarial Domain Adaptation","created":"2018-08-10","cited_by_count":127},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"1703.03492","title":"A New Representation of Skeleton Sequences for 3D Action Recognition","created":"2017-03-09","cited_by_count":126},{"id":"2003.04475","title":"Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift","created":"2020-03-10","cited_by_count":125},{"id":"2003.07554","title":"A Unified View of Label Shift Estimation","created":"2020-03-17","cited_by_count":119},{"id":"2004.05214","title":"A Review on Deep Learning Techniques for Video Prediction","created":"2020-04-10","cited_by_count":114},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"id":"1610.04420","title":"Theoretical Analysis of Domain Adaptation with Optimal Transport","created":"2016-10-14","cited_by_count":105},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2007.03141","title":"Dual Mixup Regularized Learning for Adversarial Domain Adaptation","created":"2020-07-07","cited_by_count":99},{"id":"2010.10864","title":"A Short Note on the Kinetics-700-2020 Human Action Dataset","created":"2020-10-21","cited_by_count":92},{"id":"1803.09210","title":"Importance Weighted Adversarial Nets for Partial Domain Adaptation","created":"2018-03-25","cited_by_count":90},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82},{"id":"2105.08128","title":"PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training","created":"2021-05-17","cited_by_count":80},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"1904.07848","title":"Active Adversarial Domain Adaptation","created":"2019-04-16","cited_by_count":73},{"id":"2010.08666","title":"Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings","created":"2020-10-16","cited_by_count":72},{"id":"2005.00065","title":"Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directions","created":"2020-04-30","cited_by_count":65},{"id":"2003.04614","title":"Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation","created":"2020-03-10","cited_by_count":62},{"id":"2003.03703","title":"Transferring Cross-domain Knowledge for Video Sign Language Recognition","created":"2020-03-08","cited_by_count":60},{"id":"1605.04988","title":"Going Deeper into Action Recognition: A Survey","created":"2016-05-16","cited_by_count":55},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"1904.09172","title":"Video Object Segmentation and Tracking: A Survey","created":"2019-04-19","cited_by_count":50},{"id":"2110.15128","title":"Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing","created":"2021-10-28","cited_by_count":49},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"1812.00452","title":"Disentangling Propagation and Generation for Video Prediction","created":"2018-12-02","cited_by_count":44},{"id":"2107.04520","title":"Online Adaptation to Label Distribution Shift","created":"2021-07-09","cited_by_count":44},{"id":"2002.08681","title":"Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice","created":"2020-02-20","cited_by_count":43}],"next_cursor":"100"}