TY - JOUR
T1 - Probabilistic models for concurrent chatting activity recognition
AU - Hsu, Jane Yung Jen
AU - Lian, Chia Chun
AU - Jih, Wan Rong
PY - 2011/1
Y1 - 2011/1
N2 - Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogues presents special challenges. To model the conversational dynamics of concurrent chatting behaviors, this article advocates Factorial Conditional Random Fields (FCRFs) as a model to accommodate co-temporal relationships among multiple activity states. In addition, to avoid the use of inefficient Loopy Belief Propagation (LBP) algorithm, we propose using Iterative Classification Algorithm (ICA) as the inference method for FCRFs. We designed experiments to compare our FCRFs model with two dynamic probabilistic models, Parallel Condition Random Fields (PCRFs) and Hidden Markov Models (HMMs), in learning and decoding based on auditory data. The experimental results show that FCRFs outperform PCRFs and HMMs-like models. We also discover that FCRFs using the ICA inference approach not only improves the recognition accuracy but also takes significantly less time than the LBP inference method.
AB - Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogues presents special challenges. To model the conversational dynamics of concurrent chatting behaviors, this article advocates Factorial Conditional Random Fields (FCRFs) as a model to accommodate co-temporal relationships among multiple activity states. In addition, to avoid the use of inefficient Loopy Belief Propagation (LBP) algorithm, we propose using Iterative Classification Algorithm (ICA) as the inference method for FCRFs. We designed experiments to compare our FCRFs model with two dynamic probabilistic models, Parallel Condition Random Fields (PCRFs) and Hidden Markov Models (HMMs), in learning and decoding based on auditory data. The experimental results show that FCRFs outperform PCRFs and HMMs-like models. We also discover that FCRFs using the ICA inference approach not only improves the recognition accuracy but also takes significantly less time than the LBP inference method.
KW - Chatting activity recognition
KW - Factorial conditional random fields
KW - Iterative classification
KW - Loopy belief propagation
UR - http://www.scopus.com/inward/record.url?scp=79955151444&partnerID=8YFLogxK
U2 - 10.1145/1889681.1889685
DO - 10.1145/1889681.1889685
M3 - 文章
AN - SCOPUS:78751685123
SN - 2157-6904
VL - 2
JO - ACM Transactions on Intelligent Systems and Technology
JF - ACM Transactions on Intelligent Systems and Technology
IS - 1
M1 - 4
ER -