{"list":"other","total":56,"rows":[{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"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":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"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":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300},{"id":"1810.05642","title":"The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems","created":"2018-10-11","cited_by_count":277},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"id":"1711.11157","title":"A Semantic Loss Function for Deep Learning with Symbolic Knowledge","created":"2017-11-29","cited_by_count":270},{"id":"1612.02649","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","created":"2016-12-08","cited_by_count":243},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"2012.13635","title":"Logic Tensor Networks","created":"2020-12-25","cited_by_count":199},{"id":"2111.13216","title":"Cross-Domain Adaptive Teacher for Object Detection","created":"2021-11-25","cited_by_count":126},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2104.10834","title":"DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation","created":"2021-04-22","cited_by_count":80},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2203.06398","title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection","created":"2022-03-12","cited_by_count":74},{"id":"2408.14197","title":"Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving","created":"2024-08-26","cited_by_count":69},{"id":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63},{"id":"1911.06644","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","created":"2019-11-15","cited_by_count":59},{"id":"2003.13886","title":"TITAN: Future Forecast using Action Priors","created":"2020-03-31","cited_by_count":58},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54},{"id":"1609.04741","title":"Joint Attention in Autonomous Driving (JAAD)","created":"2016-09-15","cited_by_count":36},{"id":"2103.13427","title":"Multi-Label Classification Neural Networks with Hard Logical Constraints","created":"2021-03-24","cited_by_count":36},{"id":"1608.01529","title":"Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos","created":"2016-08-04","cited_by_count":35},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28},{"id":"2304.13615","title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","created":"2023-04-26","cited_by_count":26},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20},{"id":"2304.14291","title":"EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation","created":"2023-04-27","cited_by_count":17},{"id":"2110.07922","title":"Anomaly Detection in Multi-Agent Trajectories for Automated Driving","created":"2021-10-15","cited_by_count":15},{"id":"2101.05043","title":"Video action recognition for lane-change classification and prediction of surrounding vehicles","created":"2021-01-13","cited_by_count":14},{"id":"2304.03674","title":"Machine Learning with Requirements: a Manifesto","created":"2023-04-07","cited_by_count":8},{"id":"2201.05290","title":"Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals","created":"2022-01-14","cited_by_count":6},{"id":"2104.08194","title":"Spatiotemporal Deformable Scene Graphs for Complex Activity Detection","created":"2021-04-16","cited_by_count":5},{"id":"2310.17493","title":"A Hybrid Graph Network for Complex Activity Detection in Video","created":"2023-10-26","cited_by_count":2}],"next_cursor":null}