{"total":436,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"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,"area":null},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658,"area":null},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466,"area":"wm"},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302,"area":null},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"area":null},{"id":"2209.12836","title":"Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps","created":"2022-09-26","cited_by_count":255,"area":null},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249,"area":null},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214,"area":"diffusion"},{"id":"2104.02323","title":"Objects are Different: Flexible Monocular 3D Object Detection","created":"2021-04-06","cited_by_count":185,"area":null},{"id":"2111.06881","title":"Multimodal Virtual Point 3D Detection","created":"2021-11-12","cited_by_count":166,"area":null},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160,"area":null},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"area":null},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156,"area":null},{"id":"2107.13774","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":156,"area":null},{"id":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143,"area":null},{"id":"2103.16237","title":"Delving into Localization Errors for Monocular 3D Object Detection","created":"2021-03-30","cited_by_count":140,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130,"area":null},{"id":"2110.00966","title":"Translating Images into Maps","created":"2021-10-03","cited_by_count":115,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109,"area":null},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2402.19091","title":"Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection","created":"2024-02-29","cited_by_count":89,"area":null},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2108.11127","title":"AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection","created":"2021-08-25","cited_by_count":87,"area":null},{"id":"2104.03775","title":"Geometry-based Distance Decomposition for Monocular 3D Object Detection","created":"2021-04-08","cited_by_count":84,"area":null},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2304.14340","title":"SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection","created":"2023-04-27","cited_by_count":83,"area":null},{"id":"2203.10350","title":"CLRNet: Cross Layer Refinement Network for Lane Detection","created":"2022-03-19","cited_by_count":82,"area":null},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81,"area":null},{"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,"area":null},{"id":"2103.16107","title":"Large Scale Visual Food Recognition","created":"2021-03-30","cited_by_count":75,"area":null},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2101.07172","title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","created":"2021-01-18","cited_by_count":71,"area":null},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"area":null},{"id":"2201.10830","title":"MonoDistill: Learning Spatial Features for Monocular 3D Object Detection","created":"2022-01-26","cited_by_count":68,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null},{"id":"2112.04628","title":"Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection","created":"2021-12-09","cited_by_count":67,"area":null},{"id":"2209.06535","title":"CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer","created":"2022-09-14","cited_by_count":67,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2105.01922","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","created":"2021-05-05","cited_by_count":61,"area":null},{"id":"2104.05269","title":"Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection","created":"2021-04-12","cited_by_count":58,"area":null},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2106.01606","title":"Exploring Memorization in Adversarial Training","created":"2021-06-03","cited_by_count":55,"area":null},{"id":"2108.04204","title":"Meta Gradient Adversarial Attack","created":"2021-08-09","cited_by_count":55,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2108.05793","title":"Progressive Coordinate Transforms for Monocular 3D Object Detection","created":"2021-08-12","cited_by_count":52,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2205.14951","title":"Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection","created":"2022-05-30","cited_by_count":50,"area":null},{"id":"2202.10185","title":"OSegNet: Operational Segmentation Network for COVID-19 Detection using Chest X-ray Images","created":"2022-02-21","cited_by_count":48,"area":null},{"id":"2207.10758","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","created":"2022-07-21","cited_by_count":48,"area":null},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48,"area":null},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48,"area":null},{"id":"2101.03694","title":"Learning to Segment Rigid Motions from Two Frames","created":"2021-01-11","cited_by_count":46,"area":null},{"id":"2205.09373","title":"Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection","created":"2022-05-19","cited_by_count":46,"area":null},{"id":"2310.20234","title":"HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds","created":"2023-10-31","cited_by_count":45,"area":null},{"id":"2109.02199","title":"Parsing Table Structures in the Wild","created":"2021-09-06","cited_by_count":43,"area":null},{"id":"2109.06161","title":"Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image","created":"2021-09-13","cited_by_count":42,"area":null},{"id":"2208.03624","title":"Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph","created":"2022-08-07","cited_by_count":42,"area":null},{"id":"2103.12040","title":"LaneAF: Robust Multi-Lane Detection with Affinity Fields","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2207.09055","title":"Box-supervised Instance Segmentation with Level Set Evolution","created":"2022-07-19","cited_by_count":41,"area":null},{"id":"2103.13164","title":"M3DSSD: Monocular 3D Single Stage Object Detector","created":"2021-03-24","cited_by_count":39,"area":null},{"id":"2107.05946","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2108.02452","title":"VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild","created":"2021-08-05","cited_by_count":39,"area":null},{"id":"2207.08531","title":"DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection","created":"2022-07-18","cited_by_count":39,"area":null},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39,"area":"safety"},{"id":"2404.03181","title":"MonoCD: Monocular 3D Object Detection with Complementary Depths","created":"2024-04-04","cited_by_count":39,"area":null},{"id":"2106.15324","title":"Effective Evaluation of Deep Active Learning on Image Classification Tasks","created":"2021-06-16","cited_by_count":37,"area":null},{"id":"2206.07372","title":"MonoGround: Detecting Monocular 3D Objects from the Ground","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2209.10839","title":"Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization","created":"2022-09-22","cited_by_count":36,"area":null},{"id":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36,"area":null},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35,"area":null},{"id":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2203.14208","title":"Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking","created":"2022-03-27","cited_by_count":33,"area":null},{"id":"2204.07300","title":"Dense Learning based Semi-Supervised Object Detection","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"area":null},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31,"area":null},{"id":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2403.16051","title":"Segment Anything Model for Road Network Graph Extraction","created":"2024-03-24","cited_by_count":28,"area":null},{"id":"2203.08404","title":"RBC: Rectifying the Biased Context in Continual Semantic Segmentation","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2207.10047","title":"Densely Constrained Depth Estimator for Monocular 3D Object Detection","created":"2022-07-20","cited_by_count":27,"area":null},{"id":"2103.02263","title":"LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment","created":"2021-03-03","cited_by_count":26,"area":null},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2204.00754","title":"Homography Loss for Monocular 3D Object Detection","created":"2022-04-02","cited_by_count":24,"area":null},{"id":"2209.10150","title":"RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement","created":"2022-09-21","cited_by_count":24,"area":null},{"id":"2209.13036","title":"MonoGraspNet: 6-DoF Grasping with a Single RGB Image","created":"2022-09-26","cited_by_count":24,"area":null},{"id":"2211.01142","title":"OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection","created":"2022-11-02","cited_by_count":24,"area":null},{"id":"2208.03974","title":"Aerial Monocular 3D Object Detection","created":"2022-08-08","cited_by_count":23,"area":null},{"id":"2209.15458","title":"Towards General-Purpose Representation Learning of Polygonal Geometries","created":"2022-09-29","cited_by_count":22,"area":null},{"id":"2212.01579","title":"Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution","created":"2022-12-03","cited_by_count":22,"area":null}],"next_cursor":"100"}