{"total":62,"rows":[{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104,"area":null},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96,"area":null},{"id":"2508.05630","title":"MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes","created":"2025-08-07","cited_by_count":62,"area":null},{"id":"2108.05888","title":"Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)","created":"2021-08-12","cited_by_count":45,"area":null},{"id":"2103.11597","title":"Human De-occlusion: Invisible Perception and Recovery for Humans","created":"2021-03-22","cited_by_count":31,"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":"2108.06765","title":"Occlusion-Aware Video Object Inpainting","created":"2021-08-15","cited_by_count":30,"area":null},{"id":"2204.09848","title":"Weakly Aligned Feature Fusion for Multimodal Object Detection","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2111.02045","title":"Deep Point Set Resampling via Gradient Fields","created":"2021-11-03","cited_by_count":24,"area":null},{"id":"2304.03135","title":"VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision","created":"2023-04-06","cited_by_count":19,"area":null},{"id":"2108.11771","title":"ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2303.14395","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","created":"2023-03-25","cited_by_count":13,"area":null},{"id":"2407.11464","title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2106.15315","title":"Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics","created":"2021-06-21","cited_by_count":10,"area":null},{"id":"2302.12589","title":"Revisiting Modality Imbalance In Multimodal Pedestrian Detection","created":"2023-02-24","cited_by_count":10,"area":null},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8,"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":"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":"2101.04307","title":"LLA: Loss-aware Label Assignment for Dense Pedestrian Detection","created":"2021-01-12","cited_by_count":7,"area":null},{"id":"2211.05120","title":"Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review","created":"2022-11-09","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":"2203.02331","title":"F2DNet: Fast Focal Detection Network for Pedestrian Detection","created":"2022-03-04","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":"2206.10090","title":"KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences","created":"2022-06-21","cited_by_count":5,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"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":"2405.19305","title":"Real-Time Environment Condition Classification for Autonomous Vehicles","created":"2024-05-29","cited_by_count":5,"area":null},{"id":"2210.03686","title":"Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2212.05717","title":"Feature Calibration Network for Occluded Pedestrian Detection","created":"2022-12-12","cited_by_count":4,"area":null},{"id":"2305.13051","title":"Learning Pedestrian Actions to Ensure Safe Autonomous Driving","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2308.07590","title":"ADD: An Automatic Desensitization Fisheye Dataset for Autonomous Driving","created":"2023-08-15","cited_by_count":4,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"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":"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":"2209.11770","title":"Toward Smart Doors: A Position Paper","created":"2022-09-23","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":"2107.10050","title":"You Better Look Twice: a new perspective for designing accurate detectors with reduced computations","created":"2021-07-21","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":"2511.10308","title":"Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2603.05926","title":"Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.11439","title":"Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2103.09553","title":"Multi-channel Deep Supervision for Crowd Counting","created":"2021-03-17","cited_by_count":0,"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":"2201.02366","title":"Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency Deraining","created":"2022-01-07","cited_by_count":0,"area":null},{"id":"2206.03061","title":"Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection","created":"2022-06-07","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":"2212.05691","title":"CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection","created":"2022-12-12","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":"2309.11002","title":"PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving","created":"2023-09-20","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":"2408.13646","title":"Mean Height Aided Post-Processing for Pedestrian Detection","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2510.04339","title":"Pitch-Conditioned Instrument Sound Synthesis From an Interactive Timbre Latent Space","created":"2025-10-05","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":"2609.27238","title":"Strip Convolution and Direction-Aware Exclusion Loss for Oriented Ship Detection","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}