TY - JOUR
T1 - Evaluating visual query methods for articulated motion video search
AU - Mauceri, Cecilia
AU - Suma, Evan A.
AU - Finkelstein, Samantha
AU - Souvenir, Richard
N1 - Publisher Copyright:
© 2015 Elsevier Ltd. All rights reserved.
PY - 2015/5
Y1 - 2015/5
N2 - We develop and evaluate three interfaces for video search of articulated objects, specifically humans performing common actions. The three interfaces, (1) a freehand interface with motion cues (e.g., arrows), (2) an articulated human stick figure with motion cues, and (3) a keyframe interface, were designed to allow users to quickly generate motion-based queries. We performed both quantitative and qualitative analyses of the interfaces through a formal user study by measuring accuracy and speed of user input and asking the users to complete a free-response questionnaire. Our results indicate that the constrained interfaces outperform the freehand sketch-based interface, in terms of both search accuracy and query completion time. Additionally, the users described strong preferences for the search interfaces containing pre-defined models, and the generated queries were rated higher, in terms of semantic matches to the query concept.
AB - We develop and evaluate three interfaces for video search of articulated objects, specifically humans performing common actions. The three interfaces, (1) a freehand interface with motion cues (e.g., arrows), (2) an articulated human stick figure with motion cues, and (3) a keyframe interface, were designed to allow users to quickly generate motion-based queries. We performed both quantitative and qualitative analyses of the interfaces through a formal user study by measuring accuracy and speed of user input and asking the users to complete a free-response questionnaire. Our results indicate that the constrained interfaces outperform the freehand sketch-based interface, in terms of both search accuracy and query completion time. Additionally, the users described strong preferences for the search interfaces containing pre-defined models, and the generated queries were rated higher, in terms of semantic matches to the query concept.
KW - Action recognition
KW - Sketch-based interface
KW - Video search
UR - http://www.scopus.com/inward/record.url?scp=84961332827&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961332827&partnerID=8YFLogxK
U2 - 10.1016/j.ijhcs.2014.12.009
DO - 10.1016/j.ijhcs.2014.12.009
M3 - Article
AN - SCOPUS:84961332827
SN - 1071-5819
VL - 77
SP - 10
EP - 22
JO - International Journal of Human Computer Studies
JF - International Journal of Human Computer Studies
ER -