{"list":"other","total":127,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1904.02639","title":"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection","created":"2019-04-04","cited_by_count":564},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"1906.06972","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","created":"2019-06-17","cited_by_count":466},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2002.11927","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","created":"2020-02-27","cited_by_count":325},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"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":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"2303.11950","title":"Learning A Sparse Transformer Network for Effective Image Deraining","created":"2023-03-21","cited_by_count":205},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"1905.05265","title":"Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds","created":"2019-05-13","cited_by_count":165},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2008.10937","title":"A Survey on Evolutionary Neural Architecture Search","created":"2020-08-25","cited_by_count":142},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2007.03639","title":"Human Trajectory Forecasting in Crowds: A Deep Learning Perspective","created":"2020-07-07","cited_by_count":129},{"id":"2108.06852","title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","created":"2021-08-16","cited_by_count":129},{"id":"2003.06297","title":"Harmonizing Transferability and Discriminability for Adapting Object Detectors","created":"2020-03-13","cited_by_count":126},{"id":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"2305.05938","title":"V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting","created":"2023-05-10","cited_by_count":114},{"id":"1912.12147","title":"Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensors","created":"2019-12-18","cited_by_count":110},{"id":"2301.04634","title":"Street-View Image Generation from a Bird's-Eye View Layout","created":"2023-01-11","cited_by_count":102},{"id":"1511.04136","title":"UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking","created":"2015-11-13","cited_by_count":98},{"id":"2004.06711","title":"Deformable Siamese Attention Networks for Visual Object Tracking","created":"2020-04-14","cited_by_count":97},{"id":"2104.01528","title":"SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction","created":"2021-04-04","cited_by_count":97},{"id":"2203.11474","title":"Remember Intentions: Retrospective-Memory-based Trajectory Prediction","created":"2022-03-22","cited_by_count":86},{"id":"1804.07437","title":"Vision Meets Drones: A Challenge","created":"2018-04-20","cited_by_count":81},{"id":"2203.13608","title":"Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task","created":"2022-03-25","cited_by_count":81},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74},{"id":"1512.01355","title":"Staple: Complementary Learners for Real-Time Tracking","created":"2015-12-04","cited_by_count":60},{"id":"2302.05087","title":"Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models","created":"2023-02-10","cited_by_count":59},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53},{"id":"1907.10211","title":"Motion-Aware Feature for Improved Video Anomaly Detection","created":"2019-07-24","cited_by_count":48},{"id":"2208.00219","title":"Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation","created":"2022-07-30","cited_by_count":48},{"id":"2209.08162","title":"Uncertainty Quantification of Collaborative Detection for Self-Driving","created":"2022-09-16","cited_by_count":46},{"id":"1910.04104","title":"Vehicle Re-identification with Viewpoint-aware Metric Learning","created":"2019-10-09","cited_by_count":45},{"id":"2207.08003","title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","created":"2022-07-16","cited_by_count":45},{"id":"2011.02763","title":"Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction","created":"2020-11-05","cited_by_count":42},{"id":"2204.06527","title":"A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research","created":"2022-04-13","cited_by_count":40},{"id":"1809.05782","title":"CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis","created":"2018-09-16","cited_by_count":39},{"id":"2404.04804","title":"Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving","created":"2024-04-07","cited_by_count":35},{"id":"1905.03397","title":"A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification","created":"2019-05-09","cited_by_count":34},{"id":"1806.09283","title":"RAM: A Region-Aware Deep Model for Vehicle Re-Identification","created":"2018-06-25","cited_by_count":30},{"id":"1901.08292","title":"Anomaly Detection in Road Traffic Using Visual Surveillance: A Survey","created":"2019-01-24","cited_by_count":30},{"id":"2211.08824","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","created":"2022-11-16","cited_by_count":29},{"id":"2208.09191","title":"Synthetic Data in Human Analysis: A Survey","created":"2022-08-19","cited_by_count":28},{"id":"1707.09476","title":"FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras","created":"2017-07-29","cited_by_count":27},{"id":"2103.06879","title":"CoMoGAN: continuous model-guided image-to-image translation","created":"2021-03-11","cited_by_count":27},{"id":"1703.00686","title":"BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance","created":"2017-03-02","cited_by_count":23},{"id":"2008.11887","title":"A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels","created":"2020-08-27","cited_by_count":23},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23}],"next_cursor":"100"}