TY - GEN
T1 - Multi-view Regularized Extreme Learning Machine for Human Action Recognition
AU - Iosifidis, Alexandros
AU - Tefas, Anastasios
AU - Pitas, Ioannis
PY - 2014
Y1 - 2014
N2 - In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.
AB - In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.
KW - Extreme Learning Machine
KW - Multi-view Learning
KW - Single-hidden Layer Feedforward networks
KW - Human Action Recognition
U2 - 10.1007/978-3-319-07064-3_7
DO - 10.1007/978-3-319-07064-3_7
M3 - Conference Contribution (Conference Proceeding)
SN - 9783319070636
T3 - Lecture Notes in Computer Science
SP - 84
EP - 94
BT - Artificial Intelligence: Methods and Applications
T2 - Conference on Artificial Intelligence (SETN): Methods and Applications
Y2 - 15 May 2014 through 17 May 2014
ER -