Qian Bao

Qian Bao

Auto-generated profile, based on publicly available information

Qian Bao

JD Explore Academy

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 November 2022 in ACM Computing Surveys
Verified
Journal Article
Open access
WLWu Liu
Wu Liu
QBQian Bao
Qian Bao
YSYu Sun
Yu Sun
TMTao Mei
Tao Mei
Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications. Recently, benefiting from the deep learning technologies, a significant amount of research efforts have advanced the monocular human pose estimation both in 2D and 3D areas. Although there have been some works to summarize different approaches, it still remains challenging for researchers to have an in-depth view of how these approaches work from 2D to 3D. In this article, we provide a comprehensive and holistic 2D-to-3D perspective to tackle this problem. First, we comprehensively summarize the 2D and 3D representations of human body. Then, we summarize the mainstream and milestone approaches for these human body presentations since the year 2014 under unified frameworks. Especially, we provide insightful analyses for the intrinsic connections and methods evolution from 2D to 3D pose estimation. Furthermore, we analyze the solutions for challenging cases, such as the lack of data, the inherent ambiguity between 2D and 3D, and the complex multi-person scenarios. Next, we summarize the benchmarks, evaluation metrics, and the quantitative performance of popular approaches. Finally, we discuss the challenges and give deep thinking of promising directions for future research. We believe this survey will provide the readers (researchers, engineers, developers, etc.) with a deep and insightful understanding of monocular human pose estimation.

12 March 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
QBQian Bao
Qian Bao
WLWu Liu
Wu Liu
YCYuhao Cheng
Yuhao Cheng
BZBoyan Zhou
Boyan Zhou
TMTao Mei
Tao Mei
This paper addresses the multi-person pose tracking task that aims to estimate and track person pose keypoints in video. Most of the previous methods follow the general track-by-detection strategy that ignores the consistent pose information during the whole framework, thus, they often suffer from missing detections and inaccurate human association in challenging scenes with motion blur and person occlusion. To handle those problems, we propose a pose-guided tracking-by-detection framework which fuses pose information into both video human detection and human association procedures. In the video human detection stage, we firstly adopt the pose-guided person location prediction to exploit the temporal information for making up missing detections. Technically, pose heatmaps are utilized to cope with the person-specific intra-class distractors. Furthermore, in the human association stage we propose a hierarchical pose-guided graph convolutional networks (PoseGCN) based appearance discriminative model. The PoseGCN-based model exploits the human structural relations to boost the person representation. Extensive experiments show the superiority of our method on the challenging pose tracking benchmark, which ranks first on the PoseTrack leaderboard. Our code has been publicly available at https://github.com/human-centric982/PGPT.

12 June 2017 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
QBQian Bao
Qian Bao
YLYun Lin
Yun Lin
WHWen Hong
Wen Hong
WSWenjie Shen
Wenjie Shen
YZYue Zhao
Yue Zhao
XPXueming Peng
Xueming Peng
In this letter, we propose an imaging algorithm for the holographic synthetic aperture radar tomography in the circumstance of sparse and nonuniform elevation circular passes. Considering the anisotropic behavior of scatterers and the off-grid effect of sparse signal recovery, the algorithm combines the 2-D adaptive imaging method for circular SAR and the sparse Bayesian inference-based method for elevation reconstruction. For each circular pass, the azimuth-range 2-D image can be formed by the adaptive imaging method, which depends on the preretrieved maximum azimuth response angle and the azimuth persistence width. To deal with the off-grid effect in elevation reconstruction, which is caused by the deviation between the true scatterers and the discretized imaging grids, the off-grid sparse Bayesian inference method jointly estimates the scatterers and elevation off-grid error by applying their hierarchical priors. Compared with the conventional compressive sensing method that does not concern the off-grid effect, the proposed algorithm can provide more accurate 3-D reconstruction for pointlike targets, which is verified by the real-data experiments.

1 January 2022
Verified
Book Chapter
Closed access
PDF file
SZShuaitao Zhao
Shuaitao Zhao
KLKun Liu
Kun Liu
YHYuhang Huang
Yuhang Huang
QBQian Bao
Qian Bao
DZDan Zeng
Dan Zeng
WLWu Liu
Wu Liu

24 May 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Shan AnShan An
Shan An
SLSi Liu
Si Liu
ZHZhibiao Huang
Zhibiao Huang
GCGuangfu Che
Guangfu Che
QBQian Bao
Qian Bao
DWDennis Z. Weng
Dennis Z. Weng
Product display in e-commerce commonly uses static images or videos. In this paper, we design a novel video composition system “RotateView” which displays real-world products videos on the mobile phone in an interactive and 3D-like way. The system (1) estimates the rotation direction of products using optical flow, (2) segments products using an improved version of Online Adaptive Video Object Segmentation (iOnAVOS), (3) adjusts motion and color for composition. The rotation direction estimation methods are evaluated on a video dataset of 1500 rotated videos that are uploaded by sellers, and on our collected real-world video object segmentation (RVOS) dataset. On our RVOS dataset, experimental results show an improvement in segmentation over the state of the art. Moreover, the proposed algorithms for motion and color adjustment are evaluated using extensive user studies. The RVOS dataset can be downloaded via https://realvos.github.io/ for further studies and code will be made available.

12 July 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YSYu Sun
Yu Sun
LXLubing Xu
Lubing Xu
QBQian Bao
Qian Bao
WLWu Liu
Wu Liu
WGWenpeng Gao
Wenpeng Gao
YFYILI FU
YILI FU
In this study, we address the challenge of estimating 3D body pose, shape, and depth relationships from single RGB images in crowded scenes. The difficulty lies in the limited availability of in-the-wild training samples, which feature densely populated scenes. To mitigate this issue, we introduce a synthesis-based approach that fuses multiple human samples into a single composite scene. Our innovative scene-aware blending technique maintains human-scene consistency by positioning individuals within plausible locations and adjusting their scales to conform to 3D settings. Furthermore, our method enables flexible per-subject occlusion management during the blending process, bolstering the robustness of 3D human body representations through a novel de-occlusion training scheme. We present a one-stage model, CBD, designed to learn monocular regression of 3D people in crowds by leveraging blending and de-occlusion techniques. Our quantitative and qualitative evaluations on four benchmark datasets reveal that CBD surpasses existing state-of-the-art approaches in terms of 3D human pose and mesh regression accuracy, thereby establishing it as a promising solution for monocular 3D human mesh recovery in densely populated scenes.