{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"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":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2012.12395","title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","created":"2020-12-22","cited_by_count":228},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"1911.08460","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","created":"2019-11-19","cited_by_count":120},{"id":"1503.01313","title":"A Novel Performance Evaluation Methodology for Single-Target Trackers","created":"2015-03-04","cited_by_count":113},{"id":"2006.07327","title":"GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning","created":"2020-06-12","cited_by_count":113},{"id":"1704.06036","title":"End-to-end representation learning for Correlation Filter based tracking","created":"2017-04-20","cited_by_count":90},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","cited_by_count":89},{"id":"2005.13888","title":"P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds","created":"2020-05-28","cited_by_count":84},{"id":"2104.14682","title":"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion","created":"2021-04-29","cited_by_count":83},{"id":"1903.01784","title":"Leveraging Shape Completion for 3D Siamese Tracking","created":"2019-03-05","cited_by_count":74},{"id":"1608.05571","title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","created":"2016-08-19","cited_by_count":66},{"id":"2108.04728","title":"Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds","created":"2021-08-10","cited_by_count":66},{"id":"2001.05673","title":"Probabilistic 3D Multi-Object Tracking for Autonomous Driving","created":"2020-01-16","cited_by_count":64},{"id":"1905.03072","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","created":"2019-05-08","cited_by_count":63},{"id":"1605.05863","title":"Siamese Instance Search for Tracking","created":"2016-05-19","cited_by_count":60},{"id":"2108.06455","title":"PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds","created":"2021-08-14","cited_by_count":59},{"id":"1909.03850","title":"Robust Multi-Modality Multi-Object Tracking","created":"2019-09-09","cited_by_count":56},{"id":"2111.04426","title":"3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds","created":"2021-11-08","cited_by_count":54},{"id":"2110.14921","title":"3D Object Tracking with Transformer","created":"2021-10-28","cited_by_count":49},{"id":"2002.08397","title":"JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset","created":"2020-02-19","cited_by_count":39},{"id":"1811.10863","title":"Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters","created":"2018-11-27","cited_by_count":33},{"id":"1802.09975","title":"Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering","created":"2018-02-27","cited_by_count":32},{"id":"2103.06028","title":"Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences","created":"2021-03-10","cited_by_count":25},{"id":"2003.07847","title":"PTP: Parallelized Tracking and Prediction with Graph Neural Networks and Diversity Sampling","created":"2020-03-17","cited_by_count":14},{"id":"2006.13164","title":"Joint Object Detection and Multi-Object Tracking with Graph Neural Networks","created":"2020-06-23","cited_by_count":14},{"id":"1704.04057","title":"DCFNet: Discriminant Correlation Filters Network for Visual Tracking","created":"2017-04-13","cited_by_count":11}],"next_cursor":null}