{"total":59,"rows":[{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90,"area":null},{"id":"2210.06984","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2109.01066","title":"4D-Net for Learned Multi-Modal Alignment","created":"2021-09-02","cited_by_count":44,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2101.11223","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","created":"2021-01-27","cited_by_count":30,"area":null},{"id":"2109.03426","title":"Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection","created":"2021-09-08","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2507.08441","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2201.02784","title":"Relieving Long-tailed Instance Segmentation via Pairwise Class Balance","created":"2022-01-08","cited_by_count":18,"area":null},{"id":"2106.10506","title":"Exploring Visual Context for Weakly Supervised Person Search","created":"2021-06-19","cited_by_count":16,"area":null},{"id":"2201.01297","title":"Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation","created":"2022-01-04","cited_by_count":16,"area":null},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14,"area":"distill"},{"id":"2304.06354","title":"ODAM: Gradient-based instance-specific visual explanations for object detection","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2210.12758","title":"Beta R-CNN: Looking into Pedestrian Detection from Another Perspective","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2212.04067","title":"Consistency-Aware Anchor Pyramid Network for Crowd Localization","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2101.04307","title":"LLA: Loss-aware Label Assignment for Dense Pedestrian Detection","created":"2021-01-12","cited_by_count":7,"area":null},{"id":"2106.02426","title":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2306.16661","title":"NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency","created":"2023-06-29","cited_by_count":7,"area":null},{"id":"2111.07950","title":"Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge","created":"2021-11-15","cited_by_count":6,"area":null},{"id":"2211.12110","title":"Improving Crowded Object Detection via Copy-Paste","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2502.10683","title":"CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs","created":"2025-02-15","cited_by_count":6,"area":"distill"},{"id":"2212.07652","title":"Body-Part Joint Detection and Association via Extended Object Representation","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2309.08953","title":"Robust Backdoor Attacks on Object Detection in Real World","created":"2023-09-16","cited_by_count":5,"area":null},{"id":"2104.12574","title":"Detecting and Matching Related Objects with One Proposal Multiple Predictions","created":"2021-04-23","cited_by_count":4,"area":null},{"id":"2109.03451","title":"Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2309.08196","title":"ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2305.10801","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2503.13883","title":"YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multibranch Feature Interaction","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2104.03106","title":"V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2111.08974","title":"Pedestrian Detection by Exemplar-Guided Contrastive Learning","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2207.02013","title":"Multiview Detection with Cardboard Human Modeling","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2304.07705","title":"Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads","created":"2023-04-16","cited_by_count":2,"area":null},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2306.04482","title":"ICON$^2$: Reliably Benchmarking Predictive Inequity in Object Detection","created":"2023-06-07","cited_by_count":2,"area":null},{"id":"2408.03030","title":"Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2503.08201","title":"Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2505.16029","title":"Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2402.07814","title":"PBADet: A One-Stage Anchor-Free Approach for Part-Body Association","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2405.01311","title":"Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2504.09819","title":"Density-based Object Detection in Crowded Scenes","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2509.08738","title":"CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2605.18390","title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2103.10091","title":"Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2110.03302","title":"MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildings","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2211.00826","title":"TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2301.05565","title":"DINF: Dynamic Instance Noise Filter for Occluded Pedestrian Detection","created":"2023-01-13","cited_by_count":0,"area":null},{"id":"2310.15725","title":"Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2502.07194","title":"Dense Object Detection Based on De-homogenized Queries","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2508.07144","title":"Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models","created":"2025-08-10","cited_by_count":0,"area":"moe"},{"id":"2510.03314","title":"From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2601.06642","title":"Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2603.16241","title":"Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.21568","title":"A Smart Classroom Behavior Analysis Framework with a New Highly Congested Classroom Dataset","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.08265","title":"Tracking-by-detection in Multi-object Tracking: Survey and Experiments","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}