{"list":"other","total":75,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2004.02025","title":"It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction","created":"2020-04-04","cited_by_count":236},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"2012.01526","title":"From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting","created":"2020-12-02","cited_by_count":167},{"id":"1612.01079","title":"End-to-end Learning of Driving Models from Large-scale Video Datasets","created":"2016-12-04","cited_by_count":148},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"1904.10117","title":"Learning Actor Relation Graphs for Group Activity Recognition","created":"2019-04-23","cited_by_count":83},{"id":"1812.04767","title":"TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions","created":"2018-12-12","cited_by_count":82},{"id":"1712.02616","title":"In-Place Activated BatchNorm for Memory-Optimized Training of DNNs","created":"2017-12-07","cited_by_count":81},{"id":"1811.07391","title":"Temporal Recurrent Networks for Online Action Detection","created":"2018-11-18","cited_by_count":80},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"1911.10496","title":"Two Causal Principles for Improving Visual Dialog","created":"2019-11-24","cited_by_count":75},{"id":"1812.00442","title":"Deep Cosine Metric Learning for Person Re-Identification","created":"2018-12-02","cited_by_count":73},{"id":"2002.08945","title":"Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction","created":"2020-02-20","cited_by_count":71},{"id":"1806.06498","title":"Conditional Affordance Learning for Driving in Urban Environments","created":"2018-06-18","cited_by_count":70},{"id":"1903.00618","title":"Unsupervised Traffic Accident Detection in First-Person Videos","created":"2019-03-02","cited_by_count":70},{"id":"1912.12148","title":"DADA: Driver Attention Prediction in Driving Accident Scenarios","created":"2019-12-18","cited_by_count":70},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"1905.12887","title":"Does computer vision matter for action?","created":"2019-05-30","cited_by_count":64},{"id":"1711.06406","title":"Predicting Driver Attention in Critical Situations","created":"2017-11-17","cited_by_count":61},{"id":"2003.13886","title":"TITAN: Future Forecast using Action Priors","created":"2020-03-31","cited_by_count":58},{"id":"1804.02675","title":"Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB","created":"2018-04-08","cited_by_count":51},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"1811.05432","title":"Deep Object-Centric Policies for Autonomous Driving","created":"2018-11-13","cited_by_count":41},{"id":"1911.12736","title":"DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling","created":"2019-11-28","cited_by_count":40},{"id":"1711.06330","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","created":"2017-11-16","cited_by_count":37},{"id":"1905.06937","title":"Monocular Plan View Networks for Autonomous Driving","created":"2019-05-16","cited_by_count":37},{"id":"2003.02425","title":"Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference","created":"2020-03-05","cited_by_count":34},{"id":"2009.06435","title":"Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions","created":"2020-08-31","cited_by_count":34},{"id":"1705.06560","title":"Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization","created":"2017-05-18","cited_by_count":33},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"1911.10455","title":"Looking at the right stuff: Guided semantic-gaze for autonomous driving","created":"2019-11-24","cited_by_count":32},{"id":"1910.01751","title":"Causal Induction from Visual Observations for Goal Directed Tasks","created":"2019-10-03","cited_by_count":31},{"id":"1811.11718","title":"Partial Convolution based Padding","created":"2018-11-28","cited_by_count":29},{"id":"1912.07773","title":"MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning","created":"2019-12-17","cited_by_count":29},{"id":"1909.09272","title":"Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks","created":"2019-09-20","cited_by_count":22},{"id":"1812.06152","title":"A Parametric Top-View Representation of Complex Road Scenes","created":"2018-12-14","cited_by_count":20},{"id":"1903.09950","title":"Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention","created":"2019-03-24","cited_by_count":19},{"id":"1905.02848","title":"Goal-oriented Object Importance Estimation in On-road Driving Videos","created":"2019-05-08","cited_by_count":19},{"id":"2003.06045","title":"Interaction Graphs for Object Importance Estimation in On-road Driving Videos","created":"2020-03-12","cited_by_count":15},{"id":"2011.13588","title":"Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehicles","created":"2020-11-27","cited_by_count":12},{"id":"2012.02148","title":"Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction","created":"2020-12-03","cited_by_count":12},{"id":"1905.13586","title":"Deep Dual Relation Modeling for Egocentric Interaction Recognition","created":"2019-05-31","cited_by_count":11},{"id":"1906.02859","title":"Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer","created":"2019-06-07","cited_by_count":6},{"id":"1910.14260","title":"A Self Validation Network for Object-Level Human Attention Estimation","created":"2019-10-31","cited_by_count":5},{"id":"1909.05152","title":"Context Aware Road-user Importance Estimation (iCARE)","created":"2019-08-30","cited_by_count":3}],"next_cursor":null}