Structural and Temporal Inference Search (STIS): Pattern Identification in Multimodal Data (bibtex)
by Miller, Christopher, Morency, Louis-Philippe and Quek, Francis
Abstract:
There are a multitude of annotated behavior corpora (manual and automatic annotations) available as research expands in multimodal analysis of human behavior. Despite the rich representations within these datasets, search strate- gies are limited with respect to the advanced representations and complex structures describing human interaction sequences. The relationships amongst human interactions are structural in nature. Hence, we present Structural and Temporal Inference Search (STIS) to support search for rel- evant patterns within a multimodal corpus based on the structural and temporal nature of human interactions. The user defines the structure of a behavior of interest driving a search focused on the characteristics of the structure. Occurrences of the structure are returned. We compare against two pattern mining algorithms purposed for pattern identification amongst sequences of symbolic data (e.g., sequence of events such as behavior interactions). The results are promising as STIS performs well with several datasets.
Reference:
Structural and Temporal Inference Search (STIS): Pattern Identification in Multimodal Data (Miller, Christopher, Morency, Louis-Philippe and Quek, Francis), In ACM International Conference on Multimodal Interaction (ICMI), 2012.
Bibtex Entry:
@inproceedings{miller_structural_2012,
	address = {Santa Monica, CA},
	title = {Structural and {Temporal} {Inference} {Search} ({STIS}): {Pattern} {Identification} in {Multimodal} {Data}},
	isbn = {978-1-4503-1467-1},
	url = {http://ict.usc.edu/pubs/Structural%20and%20Temporal%20Inference%20Search%20(STIS)-%20Pattern%20Identi%EF%AC%81cation%20in%20Multimodal%20Data.pdf},
	doi = {10.1145/2388676.2388702},
	abstract = {There are a multitude of annotated behavior corpora (manual and automatic annotations) available as research expands in multimodal analysis of human behavior. Despite the rich representations within these datasets, search strate- gies are limited with respect to the advanced representations and complex structures describing human interaction sequences. The relationships amongst human interactions are structural in nature. Hence, we present Structural and Temporal Inference Search (STIS) to support search for rel- evant patterns within a multimodal corpus based on the structural and temporal nature of human interactions. The user defines the structure of a behavior of interest driving a search focused on the characteristics of the structure. Occurrences of the structure are returned. We compare against two pattern mining algorithms purposed for pattern identification amongst sequences of symbolic data (e.g., sequence of events such as behavior interactions). The results are promising as STIS performs well with several datasets.},
	booktitle = {{ACM} {International} {Conference} on {Multimodal} {Interaction} ({ICMI})},
	author = {Miller, Christopher and Morency, Louis-Philippe and Quek, Francis},
	month = oct,
	year = {2012},
	keywords = {Virtual Humans},
	pages = {101--108}
}
Powered by bibtexbrowser