Aggregated pyramid gating network for human pose estimation without pre-training

Jiang, Chenru; Huang, Kaizhu; Zhang, Shufei; Wang, Xinheng; Xiao, Jimin; Goulermas, John Y.

doi:10.1016/j.patcog.2023.109429

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As multi-stage feature integration enables the network to retain diverse semantic information from fine to coarse scale [24,37,64], we propose to simultaneously aggregate shallow feature differences (early stages) compressing detailed motion cues and deep feature differences (late stages) encoding global semantic movements to derive informative and fine-grained motion representations. A naive approach to fuse features in multiple stages is to feed them into a convolutional network [9,26].…”

Section: Multi-stage Temporal Difference Encodermentioning

confidence: 99%

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Feng¹,

Gao²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict fullspectrum motion fields, which might incur numerous irrelevant cues, such as a nearby person or background. Without further efforts to excavate meaningful motion priors, their results are suboptimal, especially in complicated spatiotemporal interactions. On the other hand, the temporal difference has the ability to encode representative motion information which can potentially be valuable for pose estimation but has not been fully exploited. In this paper, we present a novel multi-frame human pose estimation framework, which employs temporal differences across frames to model dynamic contexts and engages mutual information objectively to facilitate useful motion information disentanglement. To be specific, we design a multi-stage Temporal Difference Encoder that performs incremental cascaded learning conditioned on multi-stage feature difference sequences to derive informative motion representation. We further propose a Representation Disentanglement module from the mutual information perspective, which can grasp discriminative task-relevant motion signals by explicitly defining useful and noisy constituents of the raw motion features and minimizing their mutual information. These place us to rank No.1 in the Crowd Pose Estimation in Complex Events Challenge on benchmark dataset HiEve, and achieve state-of-the-art performance on three benchmarks PoseTrack2017, PoseTrack2018, and PoseTrack21.

show abstract

Section: Multi-stage Temporal Difference Encodermentioning

confidence: 99%

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Feng¹,

Gao²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The machine learning methods currently mainly include time series [8], image convolutional neural [9], and deep neural networks [10]. Time series methods, which include recurrent neural networks [11], long short-term memory networks [12], bidirectional long short-term memory networks [13], and gated network methods [14], are mainly applicable to prediction problems with strong time series characteristics. Deep neural networks are mainly applicable to classification and prediction problems with few data dimensions that are not prone to overfitting.…”

Section: Introductionmentioning

confidence: 99%

Pearson-ShuffleDarkNet37-SE-Fully Connected-Net for Fault Classification of the Electric System of Electric Vehicles

Lu,

Chen,

Yin

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

As the core components of electric vehicles, the safety of the electric system, including motors, batteries, and electronic control systems, has always been of great concern. To provide early warning of electric-system failure and troubleshoot the problem in time, this study proposes a novel energy-vehicle electric-system failure-classification method, which is named Pearson-ShuffleDarkNet37-SE-Fully Connected-Net (PSDSEF). Firstly, the raw data were preprocessed and dimensionality reduction was performed after the Pearson correlation coefficient; then, data features were extracted utilizing ShuffleNet and an improved DarkNet37-SE network based on DarkNet53; secondly, the inserted squeeze-and-excitation networks (SE-Net) channel attention were able to obtain more fault-related target information; finally, the prediction results of the ShuffleNet and DarkNet37-SE networks were aggregated with a fully connected neural network to output the classification results. The experimental results showed that the proposed PSDSEF-based electric vehicles electric-system fault-classification method achieved an accuracy of 97.22%, which is better than other classical convolutional neural networks with the highest accuracy of 92.19% (ResNet101); the training time is faster than the average training time of the comparative networks. The proposed PSDSEF has the advantage of high classification accuracy and small number of parameters.

show abstract

SP-YOLO: an end-to-end lightweight network for real-time human pose estimation

Zhang,

Wang,

et al. 2023

SIViP

View full text Add to dashboard Cite

Aggregated pyramid gating network for human pose estimation without pre-training

Cited by 9 publications

References 7 publications

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Pearson-ShuffleDarkNet37-SE-Fully Connected-Net for Fault Classification of the Electric System of Electric Vehicles

SP-YOLO: an end-to-end lightweight network for real-time human pose estimation

Contact Info

Product

Resources

About