{"list":"other","total":64,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2004.06320","title":"A2D2: Audi Autonomous Driving Dataset","created":"2020-04-14","cited_by_count":190},{"id":"2004.12636","title":"3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection","created":"2020-04-27","cited_by_count":176},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"id":"2109.03805","title":"Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking","created":"2021-09-08","cited_by_count":166},{"id":"1811.10200","title":"IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments","created":"2018-11-26","cited_by_count":163},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"2104.05833","title":"Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization","created":"2021-04-12","cited_by_count":141},{"id":"2004.01179","title":"Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline","created":"2020-04-02","cited_by_count":132},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"1902.09720","title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels","created":"2019-02-26","cited_by_count":124},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"1811.02146","title":"TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents","created":"2018-11-06","cited_by_count":111},{"id":"1810.08705","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","created":"2018-10-19","cited_by_count":106},{"id":"2004.08467","title":"Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems","created":"2020-04-17","cited_by_count":100},{"id":"2001.02394","title":"Convolutional Networks with Dense Connectivity","created":"2020-01-08","cited_by_count":98},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"1903.01568","title":"The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes","created":"2019-03-04","cited_by_count":80},{"id":"2012.03544","title":"End-to-End Object Detection with Fully Convolutional Network","created":"2020-12-07","cited_by_count":70},{"id":"2104.10546","title":"Invertible Denoising Network: A Light Solution for Real Noise Removal","created":"2021-04-21","cited_by_count":68},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2105.13084","title":"HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization","created":"2021-05-27","cited_by_count":58},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"1912.09021","title":"AANet: Attribute Attention Network for Person Re-Identifications","created":"2019-12-19","cited_by_count":56},{"id":"1901.07474","title":"Pedestrian Attribute Recognition: A Survey","created":"2019-01-22","cited_by_count":50},{"id":"1910.04562","title":"Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization","created":"2019-10-10","cited_by_count":46},{"id":"2103.02584","title":"Cross-View Regularization for Domain Adaptive Panoptic Segmentation","created":"2021-03-03","cited_by_count":41},{"id":"2006.07864","title":"Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection","created":"2020-06-14","cited_by_count":39},{"id":"2104.03778","title":"Progressive Semantic Segmentation","created":"2021-04-08","cited_by_count":35},{"id":"2005.03457","title":"NTIRE 2020 Challenge on NonHomogeneous Dehazing","created":"2020-05-07","cited_by_count":31},{"id":"1904.01975","title":"D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios","created":"2019-04-03","cited_by_count":28},{"id":"2002.05274","title":"Solving Missing-Annotation Object Detection with Background Recalibration Loss","created":"2020-02-12","cited_by_count":27},{"id":"1608.06037","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","created":"2016-08-22","cited_by_count":25},{"id":"1601.00400","title":"Multi-task CNN Model for Attribute Prediction","created":"2016-01-04","cited_by_count":21},{"id":"2005.11909","title":"Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method","created":"2020-05-25","cited_by_count":17},{"id":"2005.11576","title":"Hierarchical Feature Embedding for Attribute Recognition","created":"2020-05-23","cited_by_count":16},{"id":"2107.01189","title":"NTIRE 2021 Multi-modal Aerial View Object Classification Challenge","created":"2021-07-02","cited_by_count":7},{"id":"1911.11612","title":"On Symbiosis of Attribute Prediction and Semantic Segmentation","created":"2019-11-23","cited_by_count":6},{"id":"2004.01817","title":"Group Based Deep Shared Feature Learning for Fine-grained Image Classification","created":"2020-04-04","cited_by_count":4},{"id":"2006.16400","title":"Vehicle Attribute Recognition by Appearance: Computer Vision Methods for Vehicle Type, Make and Model Classification","created":"2020-06-29","cited_by_count":3},{"id":"1812.07857","title":"Physical Attribute Prediction Using Deep Residual Neural Networks","created":"2018-12-19","cited_by_count":2}],"next_cursor":null}