{"total":398,"rows":[{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"area":null},{"id":"2102.00463","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","created":"2021-01-31","cited_by_count":232,"area":null},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187,"area":null},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2101.07907","title":"IntentNet: Learning to Predict Intention from Raw Sensor Data","created":"2021-01-20","cited_by_count":158,"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":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"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":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127,"area":null},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116,"area":null},{"id":"2106.13365","title":"RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection","created":"2021-06-25","cited_by_count":115,"area":null},{"id":"2103.11402","title":"Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework","created":"2021-03-21","cited_by_count":113,"area":null},{"id":"2108.09017","title":"DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection","created":"2021-08-20","cited_by_count":106,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98,"area":null},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88,"area":null},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86,"area":null},{"id":"2103.01903","title":"Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection","created":"2021-03-02","cited_by_count":79,"area":null},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78,"area":null},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2105.06804","title":"Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition","created":"2021-05-14","cited_by_count":61,"area":null},{"id":"2103.00236","title":"Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection","created":"2021-02-27","cited_by_count":60,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56,"area":null},{"id":"2104.00885","title":"Adaptive Class Suppression Loss for Long-Tail Object Detection","created":"2021-04-02","cited_by_count":55,"area":null},{"id":"2103.16368","title":"Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection","created":"2021-03-29","cited_by_count":49,"area":null},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44,"area":null},{"id":"2206.06608","title":"Label Matching Semi-Supervised Object Detection","created":"2022-06-14","cited_by_count":44,"area":null},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43,"area":null},{"id":"2303.06949","title":"Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling","created":"2023-03-13","cited_by_count":41,"area":null},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2103.10374","title":"Consistency-based Active Learning for Object Detection","created":"2021-03-18","cited_by_count":32,"area":null},{"id":"2207.05739","title":"A Data-Based Perspective on Transfer Learning","created":"2022-07-12","cited_by_count":32,"area":null},{"id":"2111.14562","title":"Instance-wise Occlusion and Depth Orders in Natural Scenes","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2308.05737","title":"Follow Anything: Open-set detection, tracking, and following in real-time","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2101.06553","title":"Self-Supervised Representation Learning from Flow Equivariance","created":"2021-01-16","cited_by_count":28,"area":null},{"id":"2210.11539","title":"ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2109.10678","title":"Natural Language Video Localization with Learnable Moment Proposals","created":"2021-09-22","cited_by_count":27,"area":null},{"id":"2202.12031","title":"Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge","created":"2022-02-24","cited_by_count":27,"area":null},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26,"area":null},{"id":"2109.06062","title":"Semantics-Guided Contrastive Network for Zero-Shot Object detection","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26,"area":null},{"id":"2103.13933","title":"Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark","created":"2021-03-25","cited_by_count":25,"area":null},{"id":"2208.04171","title":"Object Detection Using Sim2Real Domain Randomization for Robotic Applications","created":"2022-08-08","cited_by_count":25,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2107.14391","title":"From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection","created":"2021-07-30","cited_by_count":24,"area":null},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2203.13903","title":"Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection","created":"2022-03-25","cited_by_count":23,"area":null},{"id":"2207.02842","title":"When does Bias Transfer in Transfer Learning?","created":"2022-07-06","cited_by_count":23,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2104.08797","title":"MonoGRNet: A General Framework for Monocular 3D Object Detection","created":"2021-04-18","cited_by_count":20,"area":null},{"id":"2102.10795","title":"Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search","created":"2021-02-22","cited_by_count":19,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2208.09686","title":"YOLOV: Making Still Image Object Detectors Great at Video Object Detection","created":"2022-08-20","cited_by_count":18,"area":null},{"id":"2101.10011","title":"They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors","created":"2021-01-25","cited_by_count":17,"area":null},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","created":"2022-09-06","cited_by_count":17,"area":null},{"id":"2303.08747","title":"Cascaded Zoom-in Detector for High Resolution Aerial Images","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2312.01220","title":"Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation","created":"2023-12-02","cited_by_count":17,"area":null},{"id":"2103.17123","title":"Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite","created":"2021-03-31","cited_by_count":16,"area":null},{"id":"2109.11906","title":"RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection","created":"2021-09-24","cited_by_count":16,"area":null},{"id":"2107.03609","title":"Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation","created":"2021-07-08","cited_by_count":15,"area":null},{"id":"2110.12093","title":"Circle Representation for Medical Object Detection","created":"2021-10-22","cited_by_count":15,"area":null},{"id":"2205.00968","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","created":"2022-05-02","cited_by_count":15,"area":null},{"id":"2206.08016","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2307.02402","title":"Unbalanced Optimal Transport: A Unified Framework for Object Detection","created":"2023-07-05","cited_by_count":15,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2201.04620","title":"SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining","created":"2022-01-12","cited_by_count":14,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2302.06650","title":"Surround-View Vision-based 3D Detection for Autonomous Driving: A Survey","created":"2023-02-13","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2107.08645","title":"Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2110.15017","title":"Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2105.03148","title":"A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approaches","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2105.13854","title":"Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2112.01740","title":"AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration","created":"2021-12-03","cited_by_count":12,"area":null},{"id":"2208.10895","title":"A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2208.11658","title":"AGO-Net: Association-Guided 3D Point Cloud Object Detection Network","created":"2022-08-24","cited_by_count":12,"area":null},{"id":"2103.12171","title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2106.10409","title":"AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes","created":"2021-06-19","cited_by_count":11,"area":null},{"id":"2108.10809","title":"Reconcile Prediction Consistency for Balanced Object Detection","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2111.03281","title":"Recognizing Vector Graphics without Rasterization","created":"2021-11-05","cited_by_count":11,"area":null},{"id":"2112.08782","title":"Improved YOLOv5 network for real-time multi-scale traffic sign detection","created":"2021-12-16","cited_by_count":11,"area":null},{"id":"2205.02101","title":"Dynamic Sparse R-CNN","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2307.00823","title":"Understanding the Transferability of Representations via Task-Relatedness","created":"2023-07-03","cited_by_count":11,"area":null},{"id":"2404.06180","title":"YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2407.04963","title":"Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training","created":"2024-07-06","cited_by_count":11,"area":null}],"next_cursor":"100"}