Large Scale Real-Life Action Recognition Using Conditional Random Fields with Stochastic Training

Action recognition is usually studied with limited lab settings and a small data set. Traditional lab settings assume that the start and the end of each action are known. However, this is not true for the real-life activity recognition, where different actions are present in a continuous temporal sequence, with their boundaries unknown to the recognizer. Also, unlike previous attempts, our study is based on a large-scale data set collected from real world activities. The novelty of this paper is twofold: (1) Large-scale non-boundary action recognition; (2) The first application of the averaged stochastic gradient training with feedback (ASF) to conditional random fields. We find the ASF training method outperforms a variety of traditional training methods in this task.

[1]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[2]  Daniel Marcu,et al.  Practical structured learning techniques for natural language processing , 2006 .

[3]  Hee Yong Youn,et al.  Proceedings of the 10th international conference on Ubiquitous computing , 2008, UbiComp 2008.

[4]  James C. Spall,et al.  Introduction to stochastic search and optimization - estimation, simulation, and control , 2003, Wiley-Interscience series in discrete mathematics and optimization.

[5]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[6]  Jianfeng Gao,et al.  Scalable training of L1-regularized log-linear models , 2007, ICML '07.

[7]  Michael Collins,et al.  Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Uwe Hansmann,et al.  Pervasive Computing , 2003 .

[10]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[11]  Pierre Priouret,et al.  Adaptive Algorithms and Stochastic Approximations , 1990, Applications of Mathematics.

[12]  Xu Sun,et al.  Averaged Stochastic Gradient Descent with Feedback: An Accurate, Robust, and Fast Training Method , 2010, 2010 IEEE International Conference on Data Mining.

[13]  Go Hirakawa,et al.  Gathering Large Scale Human Activity Information Using Mobile Sensor Devices , 2010, 2010 International Conference on Broadband, Wireless Computing, Communication and Applications.

[14]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[15]  Johannes Peltola,et al.  Activity classification using realistic data from wearable sensors , 2006, IEEE Transactions on Information Technology in Biomedicine.

[16]  Peter L. Bartlett,et al.  Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks , 2008, J. Mach. Learn. Res..