Mining actionlet ensemble for action recognition with depth cameras

J Wang, Z Liu, Y Wu, J Yuan - 2012 IEEE conference on …, 2012 - ieeexplore.ieee.org
Human action recognition is an important yet challenging task. The recently developed
commodity depth sensors open up new possibilities of dealing with this problem but also …

Deep learning technique for human parsing: A survey and outlook

L Yang, W Jia, S Li, Q Song - International Journal of Computer Vision, 2024 - Springer
Human parsing aims to partition humans in image or video into multiple pixel-level semantic
parts. In the last decade, it has gained significantly increased interest in the computer vision …

Articulated pose estimation by a graphical model with image dependent pairwise relations

X Chen, AL Yuille - Advances in neural information …, 2014 - proceedings.neurips.cc
We present a method for estimating articulated human pose from a single static image
based on a graphical model with novel pairwise relations that make adaptive use of local …

Learning actionlet ensemble for 3D human action recognition

J Wang, Z Liu, Y Wu, J Yuan - IEEE transactions on pattern …, 2013 - ieeexplore.ieee.org
Human action recognition is an important yet challenging task. Human actions usually
involve human-object interactions, highly articulated motions, high intra-class variations, and …

Interpreting CNN knowledge via an explanatory graph

Q Zhang, R Cao, F Shi, YN Wu, SC Zhu - Proceedings of the AAAI …, 2018 - ojs.aaai.org
This paper learns a graphical model, namely an explanatory graph, which reveals the
knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv …

From red wine to red tomato: Composition with context

I Misra, A Gupta, M Hebert - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Compositionality and contextuality are key building blocks of intelligence. They allow us to
compose known concepts to generate new and complex ones. However, traditional learning …

Hierarchical human semantic parsing with comprehensive part-relation modeling

W Wang, T Zhou, S Qi, J Shen… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Modeling the human structure is central for human parsing that extracts pixel-wise semantic
information from images. We start with analyzing three types of inference processes over the …

Hierarchical human parsing with typed part-relation reasoning

W Wang, H Zhu, J Dai, Y Pang… - Proceedings of the …, 2020 - openaccess.thecvf.com
Human parsing is for pixel-wise human semantic understanding. As human bodies are
underlying hierarchically structured, how to model human structures is the central theme in …

Compositional convolutional neural networks: A robust and interpretable model for object recognition under occlusion

A Kortylewski, Q Liu, A Wang, Y Sun… - International Journal of …, 2021 - Springer
Computer vision systems in real-world applications need to be robust to partial occlusion
while also being explainable. In this work, we show that black-box deep convolutional …

A survey on model based approaches for 2D and 3D visual human pose recovery

X Perez-Sala, S Escalera, C Angulo, J Gonzalez - Sensors, 2014 - mdpi.com
Human Pose Recovery has been studied in the field of Computer Vision for the last 40
years. Several approaches have been reported, and significant improvements have been …