DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild

Weinzaepfel, Philippe; Brégier, Romain; Combaluzier, Hadrien; Leroy, Vincent; Rogez, Grégory

doi:10.1007/978-3-030-58574-7_23

Cited by 43 publications

(21 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these works [39], [47]- [52] focus on how to design the pose estimation network to improve the model accuracy, while ignoring the overall process in the practice of multi-person pose estimation task. The generation stage of human candidate frame has not been widely concerned.…”

Section: Deep Learning Modelmentioning

confidence: 99%

A Lightweight Top-Down Multi-Person Pose Estimation Method Based on Symmetric Transformation and Global Matching

Yang

Chen

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The top-down human pose estimation method usually faces the following problems: (i) The target detection result is not well applied in the pose estimation network. (ii) Difficulty of human detection in the crowded state. (iii) The complicated model leads to a long training time. Aiming at the issues above, a lightweight multi-person pose estimation method based on symmetric transformation and global matching is proposed. Symmetric transformation module adds spatial transformation network(STN) and spatial de-transformer network(SDTN) before and after the single-person pose estimation(SPPE) to extract high-quality single-person pose regions from inaccurate human candidate frames. Global matching method is used to transform the key point prediction problem into the optimal matching problem of the human body-key point graph, and solve the questions of misjudgment and error detection of pose estimation in the crowded state. Finally, depth wise separable convolution and inverted residual model are used to reduce the complexity of model, so as to improve the running speed while balancing the accuracy of the algorithm. Experiments show that the algorithm proposed in this paper not only enhance the overall performance of the multi-person posture estimation network in the crowded state, but also improves the running speed significantly, which further confirms the effectiveness and competitiveness of this algorithm.INDEX TERMS Human pose estimation, symmetric transformation, depthwise separable convolution, global matching method.

show abstract

Section: Deep Learning Modelmentioning

confidence: 99%

A Lightweight Top-Down Multi-Person Pose Estimation Method Based on Symmetric Transformation and Global Matching

Yang

Chen

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Since the DJSLC dataset [5] used by [12] is not publicly available to facilitate a comparison, we turn to the publicly available BSLCORPUS with boundary annotations and compare to our re-implementation of their approach. In contrast to [12], which assumes 3D skeletal information given by motion capture, we estimate the 3D pose coordinates with the recently proposed monocular DOPE model [35]. While the performance is bounded by the quality of the pose estimation, this ensures that the method is applicable to unconstrained sign language videos.…”

Section: Comparison To Prior Workmentioning

confidence: 99%

Sign Language Segmentation with Temporal Convolutional Networks

Renz

Stache

Albanie

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The objective of this work is to determine the location of temporal boundaries between signs in continuous sign language videos. Our approach employs 3D convolutional neural network representations with iterative temporal segment refinement to resolve ambiguities between sign boundary cues. We demonstrate the effectiveness of our approach on the BSLCORPUS, PHOENIX14 and BSL-1K datasets, showing considerable improvement over the state of the art and the ability to generalise to new signers, languages and domains.

show abstract

“…Knowledge distillation methods have been widely used in many vision tasks, including object detection [30,6,13], line detection [20], semantic segmentation [62,18,34] and human pose estimation [66,40,56,58]. DOPE [58] proposes to distill the 2D and 3D poses from three independent body part expert models to the single whole-body pose detection model. Nie et al [40] distill the pose kernels via leveraging temporal cues from the previous frame in a one-shot feed-forward manner.…”

Section: Related Workmentioning

confidence: 99%

Online Knowledge Distillation for Efficient Pose Estimation

Song

et al. 2021

Preprint

View full text Add to dashboard Cite

Existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. One promising technique to obtain an accurate yet lightweight pose estimator is knowledge distillation, which distills the pose knowledge from a powerful teacher model to a less-parameterized student model. However, existing pose distillation works rely on a heavy pre-trained estimator to perform knowledge transfer and require a complex two-stage learning procedure. In this work, we investigate a novel Online Knowledge Distillation framework by distilling Human Pose structure knowledge in a one-stage manner to guarantee the distillation efficiency, termed OKDHP. Specifically, OKDHP trains a single multi-branch network and acquires the predicted heatmaps from each, which are then assembled by a Feature Aggregation Unit (FAU) as the target heatmaps to teach each branch in reverse. Instead of simply averaging the heatmaps, FAU which consists of multiple parallel transformations with different receptive fields, leverages the multi-scale information, thus obtains target heatmaps with higher-quality. Specifically, the pixelwise Kullback-Leibler (KL) divergence is utilized to minimize the discrepancy between the target heatmaps and the predicted ones, which enables the student network to learn the implicit keypoint relationship. Besides, an unbalanced OKDHP scheme is introduced to customize the student networks with different compression rates. The effectiveness of our approach is demonstrated by extensive experiments on two common benchmark datasets, MPII and COCO.

show abstract

DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild

Cited by 43 publications

References 59 publications

A Lightweight Top-Down Multi-Person Pose Estimation Method Based on Symmetric Transformation and Global Matching

A Lightweight Top-Down Multi-Person Pose Estimation Method Based on Symmetric Transformation and Global Matching

Sign Language Segmentation with Temporal Convolutional Networks

Online Knowledge Distillation for Efficient Pose Estimation

Contact Info

Product

Resources

About