{"list":"other","total":52,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"2103.01486","title":"Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition","created":"2021-03-02","cited_by_count":238},{"id":"1710.00935","title":"Interpretable Convolutional Neural Networks","created":"2017-10-02","cited_by_count":162},{"id":"1805.09662","title":"LF-Net: Learning Local Features from Images","created":"2018-05-24","cited_by_count":151},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128},{"id":"1903.06593","title":"PifPaf: Composite Fields for Human Pose Estimation","created":"2019-03-15","cited_by_count":120},{"id":"1904.00889","title":"Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters","created":"2019-04-01","cited_by_count":118},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1909.06933","title":"Self-Supervised Correspondence in Visuomotor Policy Learning","created":"2019-09-16","cited_by_count":107},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"1910.08350","title":"A Mutual Information Maximization Perspective of Language Representation Learning","created":"2019-10-18","cited_by_count":85},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"1810.07121","title":"Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation","created":"2018-10-16","cited_by_count":76},{"id":"1608.01807","title":"SIFT Meets CNN: A Decade Survey of Instance Retrieval","created":"2016-08-05","cited_by_count":67},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2011.00401","title":"The MAGICAL Benchmark for Robust Imitation","created":"2020-11-01","cited_by_count":32},{"id":"1901.00555","title":"An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation","created":"2019-01-02","cited_by_count":31},{"id":"2003.03463","title":"Training Deep Energy-Based Models with f-Divergence Minimization","created":"2020-03-06","cited_by_count":29},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23},{"id":"2005.03648","title":"Plan2Vec: Unsupervised Representation Learning by Latent Plans","created":"2020-05-07","cited_by_count":21},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20},{"id":"2011.12930","title":"Unsupervised Object Keypoint Learning using Local Spatial Predictability","created":"2020-11-25","cited_by_count":13},{"id":"1805.12295","title":"Image-Dependent Local Entropy Models for Learned Image Compression","created":"2018-05-31","cited_by_count":12},{"id":"2006.05077","title":"SEKD: Self-Evolving Keypoint Detection and Description","created":"2020-06-09","cited_by_count":11},{"id":"1905.06002","title":"Simitate: A Hybrid Imitation Learning Benchmark","created":"2019-05-15","cited_by_count":10},{"id":"2005.03995","title":"DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation","created":"2020-05-06","cited_by_count":9},{"id":"1411.1434","title":"On the Information Theoretic Limits of Learning Ising Models","created":"2014-11-05","cited_by_count":4},{"id":"2108.01034","title":"An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning","created":"2021-08-02","cited_by_count":2},{"id":"2011.03882","title":"Multi-Modal Learning of Keypoint Predictive Models for Visual Object Manipulation","created":"2020-11-08","cited_by_count":1}],"next_cursor":null}