BPJDet: Extended Object Representation for Generic Body-Part Joint Detection
Not on the map. Why?
Abstract (arXiv)
Detection of human body and its parts has been intensively studied. However, most of CNNs-based detectors are trained independently, making it difficult to associate detected parts with body. In this paper, we focus on the joint detection of human body and its parts. Specifically, we propose a novel extended object representation integrating center-offsets of body parts, and construct an end-to-end generic Body-Part Joint Detector (BPJDet). In this way, body-part associations are neatly embedded in a unified representation containing both semantic and geometric contents. Therefore, we can optimize multi-loss to tackle multi-tasks synergistically. Moreover, this representation is suitable for anchor-based and anchor-free detectors. BPJDet does not suffer from error-prone post matching, and keeps a better trade-off between speed and accuracy. Furthermore, BPJDet can be generalized to detect body-part or body-parts of either human or quadruped animals. To verify the superiority of BPJDet, we conduct experiments on datasets of body-part (CityPersons, CrowdHuman and BodyHands) and body-parts (COCOHumanParts and Animals5C). While keeping high detection accuracy, BPJDet achieves state-of-the-art association performance on all datasets. Besides, we show benefits of advanced body-part association capability by improving performance of two representative downstream applications: accurate crowd head detection and hand contact estimation. Project is available in https://hnuzhy.github.io/projects/BPJDet.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 72 of its 93 references that are in the map. First posted on arXiv 21 Apr 2023.
Builds on
72 of 93 references.
References · 72
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2017Mask R-CNNcited by 7,259
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
- 2017Deformable Convolutional Networkscited by 1,481
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2019Objects as Pointscited by 1,172
- 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
38 more
- 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
- 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
- 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
- 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
- 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
- 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
- 2020Tracking Objects as Pointscited by 483
- 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
- 2020Understanding Human Hands in Contact at Internet Scalecited by 281
- 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
- 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
- 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
- 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 180
- 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
- 2014Multiple Object Tracking: A Literature Reviewcited by 165
- 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
- 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
- 2019Single-Stage Multi-Person Pose Machinescited by 95
- 2021On Self-Contact and Human Posecited by 88
- 2020PaStaNet: Toward Human Activity Knowledge Enginecited by 79
- 2022PP-YOLOE: An evolved version of YOLOcited by 75
- 2019Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detectioncited by 73
- 2016Finding Tiny Facescited by 72
- 2019Adaptive NMS: Refining Pedestrian Detection in a Crowdcited by 66
- 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 66
- 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 63
- 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
- 2020Detection in Crowded Scenes: One Proposal, Multiple Predictionscited by 59
- 2022COAP: Compositional Articulated Occupancy of Peoplecited by 59
- 2018Occlusion-aware R-CNN: Detecting Pedestrians in a Crowdcited by 58
- 2021OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Associationcited by 55
- 2017Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identificationcited by 52
- 2019Learning 3D Human Shape and Pose from Dense Body Partscited by 48
- 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
- 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
- 2023Detecting Human-Object Contact in Imagescited by 41
- 2020Detecting Hands and Recognizing Physical Contact in the Wildcited by 38
- 2022DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networkscited by 38
50 most cited of 72 All 72 (JSON)
Built on by
Citing papers per year: 2024: 2.
2 papers.