Learning to Share Latent Tasks for Action Recognition

By Qiang-feng Zhou, G. Wang, K. Jia, Qi Zhao. 2013

60 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, 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. G. Wang
2. Abhinav Kumar Gupta
3. Ishan Misra
4. Dacheng Tao
5. Amir Shahroudy
6. Jun Liu
7. Martial Hebert
8. Abhinav Shrivastava

In Biomedical Engineering

1. G. Wang
2. Amir Shahroudy
3. J. Lai
4. Abhinav Kumar Gupta
5. Weishi Zheng
6. Jianfang Hu
7. Jianguo Zhang
8. Tian-Tsong Ng

In Computer Vision and Pattern Recognition

1. G. Wang
2. Dacheng Tao
3. Luc Van Gool
4. Xiaogang Wang
5. Jun Liu
6. Ming-Hsuan Yang
7. Yi Yang
8. Abhinav Kumar Gupta

Citations in the corpus

• Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, background): “If multiple learning tasks at hand share some inherent constituents or structures, “Multitask Learning” [33], [34], [35], [36] techniques could be globally beneficial.”
• Multi-Task CNN Model for Attribute Prediction (2015, methodology): “Multi-task learning is an effective method for feature sharing, as well as competition among classifiers (the so-called ’tasks’ in the term multi-task) [21], [62].”
• Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, background): “poses in the literature [8], [32], [37], [40], [45], [57].”
• Cross-Stitch Networks for Multi-task Learning (2016, methodology): “So as our final baseline, we compare to a variant of [1, 62] by adapting their method to our setting and report this as ‘MTL-shared’.”
• Simple to Complex Transfer Learning for Action Recognition (2016, methodology): “Following [42], (·, ·) is the popular squared hinge loss”