{"list":"other","total":85,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"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":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"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":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1712.09707","title":"Deep learning for universal linear embeddings of nonlinear dynamics","created":"2017-12-27","cited_by_count":494},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2102.12086","title":"Modern Koopman Theory for Dynamical Systems","created":"2021-02-24","cited_by_count":276},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"1710.04340","title":"Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition","created":"2017-10-12","cited_by_count":158},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"2003.02236","title":"Forecasting Sequential Data using Consistent Koopman Autoencoders","created":"2020-03-04","cited_by_count":115},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"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":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"2011.07949","title":"RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning","created":"2020-10-27","cited_by_count":83},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2004.07804","title":"A Game Theoretic Framework for Model Based Reinforcement Learning","created":"2020-04-16","cited_by_count":73},{"id":"2009.05769","title":"Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning","created":"2020-09-12","cited_by_count":66},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"2008.00975","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","created":"2020-08-03","cited_by_count":65},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64},{"id":"2006.15489","title":"Video Representation Learning with Visual Tempo Consistency","created":"2020-06-28","cited_by_count":57},{"id":"1409.5496","title":"Extracting spatial-temporal coherent patterns in large-scale neural recordings using dynamic mode decomposition","created":"2014-09-19","cited_by_count":49},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41},{"id":"1808.07507","title":"Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition","created":"2018-08-22","cited_by_count":40},{"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":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39},{"id":"2308.12962","title":"Motion-Guided Masking for Spatiotemporal Representation Learning","created":"2023-08-24","cited_by_count":30},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28},{"id":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27},{"id":"2303.17264","title":"Multifactor Sequential Disentanglement via Structured Koopman Autoencoders","created":"2023-03-30","cited_by_count":24},{"id":"2203.14221","title":"How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?","created":"2022-03-27","cited_by_count":23},{"id":"2207.12795","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","created":"2022-07-26","cited_by_count":23},{"id":"2210.04154","title":"Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders","created":"2022-10-09","cited_by_count":20},{"id":"1512.04205","title":"Compressed Dynamic Mode Decomposition for Background Modeling","created":"2015-12-14","cited_by_count":17},{"id":"2206.12534","title":"SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos","created":"2022-06-25","cited_by_count":17},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16},{"id":"2303.11003","title":"Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization","created":"2023-03-20","cited_by_count":12},{"id":"2206.14702","title":"Interventional Contrastive Learning with Meta Semantic Regularizer","created":"2022-06-29","cited_by_count":11},{"id":"2106.09703","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","created":"2021-06-17","cited_by_count":10},{"id":"2306.02014","title":"Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts","created":"2023-06-03","cited_by_count":4}],"next_cursor":null}