{"total":176,"rows":[{"id":"2102.09480","title":"Unbiased Teacher for Semi-Supervised Object Detection","created":"2021-02-18","cited_by_count":306,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137,"area":null},{"id":"2108.02350","title":"Hierarchical Aggregation for 3D Instance Segmentation","created":"2021-08-05","cited_by_count":127,"area":null},{"id":"2108.06753","title":"Learning Open-World Object Proposals without Learning to Classify","created":"2021-08-15","cited_by_count":109,"area":null},{"id":"2108.10723","title":"Improving 3D Object Detection with Channel-wise Transformer","created":"2021-08-23","cited_by_count":108,"area":null},{"id":"2103.12902","title":"Region Similarity Representation Learning","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2103.03067","title":"TPCN: Temporal Point Cloud Networks for Motion Forecasting","created":"2021-03-04","cited_by_count":94,"area":null},{"id":"2104.00324","title":"STMTrack: Template-free Visual Tracking with Space-time Memory Networks","created":"2021-04-01","cited_by_count":91,"area":null},{"id":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91,"area":null},{"id":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","cited_by_count":90,"area":null},{"id":"2112.09205","title":"AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds","created":"2021-12-16","cited_by_count":88,"area":null},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84,"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":"2112.02205","title":"Behind the Curtain: Learning Occluded Shapes for 3D Object Detection","created":"2021-12-04","cited_by_count":58,"area":null},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55,"area":"distill"},{"id":"2203.16317","title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","created":"2022-03-30","cited_by_count":51,"area":null},{"id":"2301.10938","title":"Compact Transformer Tracker with Correlative Masked Modeling","created":"2023-01-26","cited_by_count":50,"area":null},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"area":null},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46,"area":null},{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46,"area":null},{"id":"2106.00168","title":"Rethinking Pseudo Labels for Semi-Supervised Object Detection","created":"2021-06-01","cited_by_count":45,"area":null},{"id":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40,"area":"diffusion"},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2207.07922","title":"Learning Quality-aware Dynamic Memory for Video Object Segmentation","created":"2022-07-16","cited_by_count":35,"area":null},{"id":"2108.03637","title":"Saliency-Associated Object Tracking","created":"2021-08-08","cited_by_count":30,"area":null},{"id":"2203.14662","title":"MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation","created":"2022-03-28","cited_by_count":30,"area":null},{"id":"2101.06849","title":"CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images","created":"2021-01-18","cited_by_count":29,"area":null},{"id":"2112.12402","title":"Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier","created":"2021-12-23","cited_by_count":27,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"area":null},{"id":"2207.11209","title":"Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization","created":"2022-07-22","cited_by_count":26,"area":null},{"id":"2108.03648","title":"From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder","created":"2021-08-08","cited_by_count":23,"area":null},{"id":"2107.11669","title":"Rank & Sort Loss for Object Detection and Instance Segmentation","created":"2021-07-24","cited_by_count":22,"area":null},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21,"area":null},{"id":"2304.14394","title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","created":"2023-04-27","cited_by_count":21,"area":null},{"id":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2102.04700","title":"Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search","created":"2021-02-09","cited_by_count":20,"area":null},{"id":"2203.09510","title":"DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection","created":"2022-03-17","cited_by_count":20,"area":null},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2307.00934","title":"Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2307.11035","title":"Cascade-DETR: Delving into High-Quality Universal Object Detection","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2110.02687","title":"Objects in Semantic Topology","created":"2021-10-06","cited_by_count":18,"area":null},{"id":"2111.00928","title":"Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2203.12335","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","created":"2022-03-23","cited_by_count":18,"area":null},{"id":"2208.10976","title":"Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking","created":"2022-08-23","cited_by_count":17,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2107.04362","title":"RGB Stream Is Enough for Temporal Action Detection","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2107.04517","title":"Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2204.01475","title":"Unsupervised Learning of Accurate Siamese Tracking","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2104.00829","title":"Learning to Filter: Siamese Relation Network for Robust Tracking","created":"2021-04-02","cited_by_count":15,"area":null},{"id":"2105.03817","title":"TrTr: Visual Tracking with Transformer","created":"2021-05-09","cited_by_count":14,"area":null},{"id":"2303.14960","title":"Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection","created":"2023-03-27","cited_by_count":14,"area":null},{"id":"2306.13337","title":"Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning","created":"2023-06-23","cited_by_count":14,"area":null},{"id":"2308.05988","title":"MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection","created":"2023-08-11","cited_by_count":14,"area":null},{"id":"2108.03634","title":"Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud","created":"2021-08-08","cited_by_count":13,"area":null},{"id":"2211.09224","title":"Are we certain it's anomalous?","created":"2022-11-16","cited_by_count":13,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2407.05352","title":"Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model","created":"2024-07-07","cited_by_count":13,"area":"diffusion"},{"id":"2207.05536","title":"DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2407.01016","title":"SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection","created":"2024-07-01","cited_by_count":12,"area":null},{"id":"2108.10809","title":"Reconcile Prediction Consistency for Balanced Object Detection","created":"2021-08-24","cited_by_count":11,"area":null},{"id":"2202.05659","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","created":"2022-02-11","cited_by_count":11,"area":"distill"},{"id":"2205.04281","title":"Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2109.05986","title":"Mutual Supervision for Dense Object Detection","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2303.04346","title":"Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module","created":"2023-03-08","cited_by_count":10,"area":null},{"id":"2105.11237","title":"SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking","created":"2021-05-24","cited_by_count":9,"area":null},{"id":"2108.04644","title":"FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network","created":"2021-08-10","cited_by_count":9,"area":null},{"id":"2109.07662","title":"Dynamic Fusion Network for RGBT Tracking","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2201.02302","title":"Extending One-Stage Detection with Open-World Proposals","created":"2022-01-07","cited_by_count":9,"area":null},{"id":"2511.19221","title":"Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving","created":"2025-11-24","cited_by_count":9,"area":"mllm"},{"id":"2110.10239","title":"1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2203.07688","title":"InsCon:Instance Consistency Feature Representation via Self-Supervised Learning","created":"2022-03-15","cited_by_count":8,"area":null},{"id":"2304.11805","title":"OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2310.10975","title":"NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning","created":"2023-10-17","cited_by_count":8,"area":null},{"id":"2310.15955","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2312.14446","title":"Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2210.04252","title":"Precise Single-stage Detector","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2404.19384","title":"Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection","created":"2024-04-30","cited_by_count":7,"area":null},{"id":"2103.07017","title":"CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement","created":"2021-03-12","cited_by_count":6,"area":null},{"id":"2201.01087","title":"Learning Quality-aware Representation for Multi-person Pose Regression","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2210.06008","title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2510.22675","title":"DAMap: Distance-aware MapNet for High Quality HD Map Construction","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2102.12808","title":"SCD: A Stacked Carton Dataset for Detection and Segmentation","created":"2021-02-25","cited_by_count":5,"area":null},{"id":"2104.13876","title":"PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2109.10092","title":"Bayesian Confidence Calibration for Epistemic Uncertainty Modelling","created":"2021-09-21","cited_by_count":5,"area":null},{"id":"2112.06467","title":"An Informative Tracking Benchmark","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2208.00817","title":"DSLA: Dynamic smooth label assignment for efficient anchor-free object detection","created":"2022-08-01","cited_by_count":5,"area":null},{"id":"2208.03006","title":"Task-Balanced Distillation for Object Detection","created":"2022-08-05","cited_by_count":5,"area":"distill"},{"id":"2212.02747","title":"Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty","created":"2022-12-06","cited_by_count":5,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2305.20055","title":"Cross-Domain Car Detection Model with Integrated Convolutional Block Attention Mechanism","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2309.09765","title":"Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2311.10437","title":"DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection","created":"2023-11-17","cited_by_count":5,"area":null},{"id":"2312.05923","title":"Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting","created":"2023-12-10","cited_by_count":5,"area":null},{"id":"2312.15219","title":"Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery","created":"2023-12-23","cited_by_count":5,"area":null},{"id":"2107.14342","title":"Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness","created":"2021-07-29","cited_by_count":4,"area":null},{"id":"2112.01793","title":"A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization","created":"2021-12-03","cited_by_count":4,"area":null}],"next_cursor":"100"}