Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methods

By Massimiliano Patacchiola, Angelo Cangelosi. 2017

201 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jianfei Cai
2. Jiuxiang Gu
3. Amir Shahroudy
4. James M. Rehg
5. Tobias Fischer
6. Yiannis Demiris
7. Zhenhua Wang
8. Ting Liu

In Computer Vision and Pattern Recognition

1. Jianfei Cai
2. G. Wang
3. Jiuxiang Gu
4. Amir Shahroudy
5. Tsuhan Chen
6. Bing Shuai
7. Ming-Hsuan Yang
8. Jun Liu

Citations in the corpus

• Recent advances in convolutional neural networks (2015, background): “Since the breakthrough in deep structure learning, many recent works pay more attention to learn multiple levels of representations and abstractions for human-body pose estimation task with CNNs [220, 221].”
• Fine-Grained Head Pose Estimation Without Keypoints (2017, methodology): “[19] presents an in-depth study of relatively shallow networks trained using a regression loss on the AFLW dataset.”
• Facial Landmark Detection: A Literature Survey (2018, unknown): “The model complexity is on par with the deep models used for other related face analysis tasks, such as head pose estimation (Patacchiola and Cangelosi 2017), age and gender estimation (Levi and Hassncer 2015), and facial expression recognition (Lopes et al.”
• RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (2018, background): “The weights for the network estimating the head pose are fixed and taken from a pre-trained model [43].”