{"list":"other","total":71,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"1511.02680","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","created":"2015-11-09","cited_by_count":218},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"id":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"1904.07846","title":"Temporal Cycle-Consistency Learning","created":"2019-04-16","cited_by_count":154},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2006.06606","title":"What makes instance discrimination good for transfer learning?","created":"2020-06-11","cited_by_count":111},{"id":"1904.04620","title":"Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving","created":"2019-04-09","cited_by_count":105},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"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":"1412.6623","title":"Word Representations via Gaussian Embedding","created":"2014-12-20","cited_by_count":96},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"2001.00294","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","created":"2020-01-02","cited_by_count":81},{"id":"1901.07590","title":"Striking the Right Balance with Uncertainty","created":"2019-01-22","cited_by_count":79},{"id":"2008.00975","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","created":"2020-08-03","cited_by_count":65},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"1912.01001","title":"View-Invariant Probabilistic Embedding for Human Pose","created":"2019-12-02","cited_by_count":47},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"2009.05757","title":"Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion","created":"2020-09-12","cited_by_count":39},{"id":"1905.10296","title":"Uncertainty Estimation in One-Stage Object Detection","created":"2019-05-24","cited_by_count":36},{"id":"1504.06654","title":"Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space","created":"2015-04-24","cited_by_count":35},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31},{"id":"2008.13426","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","created":"2020-08-31","cited_by_count":29},{"id":"2108.08426","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","created":"2021-08-19","cited_by_count":28},{"id":"2011.13046","title":"Can Temporal Information Help with Contrastive Self-Supervised Learning?","created":"2020-11-25","cited_by_count":27},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23},{"id":"2012.07504","title":"Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates","created":"2020-12-14","cited_by_count":14},{"id":"2104.00616","title":"Composable Augmentation Encoding for Video Representation Learning","created":"2021-04-01","cited_by_count":13},{"id":"2004.04096","title":"Probabilistic embeddings for speaker diarization","created":"2020-04-06","cited_by_count":11},{"id":"1909.11702","title":"Stochastic Prototype Embeddings","created":"2019-09-25","cited_by_count":10},{"id":"2110.03446","title":"A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction","created":"2021-10-06","cited_by_count":10}],"next_cursor":null}