{"list":"other","total":89,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"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":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2002.10187","title":"3DSSD: Point-based 3D Single Stage Object Detector","created":"2020-02-24","cited_by_count":440},{"id":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1907.03670","title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","created":"2019-07-08","cited_by_count":368},{"id":"1907.03739","title":"Point-Voxel CNN for Efficient 3D Deep Learning","created":"2019-07-08","cited_by_count":343},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"1706.01307","title":"Submanifold Sparse Convolutional Networks","created":"2017-06-05","cited_by_count":223},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2012.12397","title":"Multi-Task Multi-Sensor Fusion for 3D Object Detection","created":"2020-12-22","cited_by_count":203},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2004.01803","title":"SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation","created":"2020-04-03","cited_by_count":170},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151},{"id":"2204.12463","title":"Focal Sparse Convolutional Networks for 3D Object Detection","created":"2022-04-26","cited_by_count":142},{"id":"1903.08701","title":"LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving","created":"2019-03-20","cited_by_count":133},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125},{"id":"1611.07709","title":"Fully Convolutional Instance-aware Semantic Segmentation","created":"2016-11-23","cited_by_count":123},{"id":"2206.02099","title":"Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation","created":"2022-06-05","cited_by_count":119},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115},{"id":"2008.01550","title":"Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation","created":"2020-08-04","cited_by_count":112},{"id":"2108.10723","title":"Improving 3D Object Detection with Channel-wise Transformer","created":"2021-08-23","cited_by_count":108},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"2207.00026","title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","created":"2022-06-30","cited_by_count":93},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92},{"id":"2303.03595","title":"LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion","created":"2023-03-07","cited_by_count":80},{"id":"1608.07711","title":"3D Object Proposals using Stereo Imagery for Accurate Object Class Detection","created":"2016-08-27","cited_by_count":58},{"id":"2211.11962","title":"Transformation-Equivariant 3D Object Detection for Autonomous Driving","created":"2022-11-22","cited_by_count":52},{"id":"1812.05276","title":"IPOD: Intensive Point-based Object Detector for Point Cloud","created":"2018-12-13","cited_by_count":46},{"id":"2210.08064","title":"LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds","created":"2022-10-14","cited_by_count":41},{"id":"2007.11622","title":"TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning","created":"2020-07-22","cited_by_count":32},{"id":"2303.08333","title":"DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception","created":"2023-03-15","cited_by_count":30},{"id":"1901.03353","title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","created":"2019-01-10","cited_by_count":24},{"id":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24},{"id":"2304.01464","title":"Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection","created":"2023-04-04","cited_by_count":24},{"id":"2212.07289","title":"ConQueR: Query Contrast Voxel-DETR for 3D Object Detection","created":"2022-12-14","cited_by_count":21},{"id":"2108.05818","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","created":"2021-08-12","cited_by_count":15},{"id":"2306.12398","title":"Multi-Task Consistency for Active Learning","created":"2023-06-21","cited_by_count":9},{"id":"2311.03620","title":"FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusion","created":"2023-11-07","cited_by_count":5},{"id":"1905.02285","title":"Simultaneous Object Detection and Semantic Segmentation","created":"2019-05-06","cited_by_count":4},{"id":"2308.12817","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","created":"2023-08-23","cited_by_count":4},{"id":"2311.03742","title":"3DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusion","created":"2023-11-07","cited_by_count":4}],"next_cursor":null}