Pose Flow: Efficient Online Pose Tracking
By Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, Cewu Lu. British Machine Vision Conference, 2018
334 citations recorded by the source corpus.
Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First, we design an online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder). Second, a novel pose flow non-maximum suppression (PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Extensive experiments show that our method significantly outperforms best-reported results on two standard Pose Tracking datasets by 13 mAP 25 MOTA and 6 mAP 3 MOTA respectively. Moreover, in the case of working on detected poses in individual frames, the extra computation of pose tracker is very minor, guaranteeing online 10FPS tracking. Our source codes are made publicly available(this https URL).
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/f9717a0056ad863c5f9dc00916ab87bdf1cdf5f7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Yi Yang
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Chen Change Loy
Citations in the corpus
- Behavior-Driven Synthesis of Human Dynamics (2021, background): “Since powerful pose estimators [59, 48] are readily available, pose sequences x = [x0, .”
- AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time (2022, methodology): “Some other top-down methods allow to input a single frame, and then use designed poseflow[47], GCN[48], [52], optical flow[31] or transformer [54] for identity matching.”
- Simple Baselines for Human Pose Estimation and Tracking (2018, background): “Compared with the recent work [35], our best model (ResNet152*) has 7.”
- Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “To detect landmarks from occluded images, we use Al-phaPose [8, 37] pre-trained on the COCO dataset [20].”
- Deep High-Resolution Representation Learning for Human Pose Estimation (2019, neutral): “[75] 66.”
- CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark (2018, background): “Some works [5, 8, 39, 25] in human tracking area use temporal information to fix wrong detection with CNN or RNN [3, 32] module.”