TY - JOUR
T1 - Dancelets Mining for Video Recommendation Based on Dance Styles
AU - Han, Tingting
AU - Yao, Hongxun
AU - Xu, Chenliang
AU - Sun, Xiaoshuai
AU - Zhang, Yanhao
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 1999-2012 IEEE.
PY - 2017/4
Y1 - 2017/4
N2 - Dance is a unique and meaningful type of human expression, composed of abundant and various action elements. However, existing methods based on associated texts and spatial visual features have difficulty capturing the highly articulated motion patterns. To overcome this limitation, we propose to take advantage of the intrinsic motion information in dance videos to solve the video recommendation problem. We present a novel system that recommends dance videos based on a mid-level action representation, termed Dancelets. The Dancelets are used to bridge the semantic gap between video content and high-level concept, dance style, which plays a significant role in characterizing different types of dances. The proposed method executes automatic mining of dancelets with a concatenation of normalized cut clustering and linear discriminant analysis. This ensures that the discovered dancelets are both representative and discriminative. Additionally, to exploit the motion cues in videos, we employ motion boundaries as saliency priors to generate volumes of interest and extract C3D features to capture spatiotemporal information from the mid-level patches. Extensive experiments validated on our proposed large dance dataset, HIT Dances dataset, demonstrate the effectiveness of the proposed methods for dance style-based video recommendation.
AB - Dance is a unique and meaningful type of human expression, composed of abundant and various action elements. However, existing methods based on associated texts and spatial visual features have difficulty capturing the highly articulated motion patterns. To overcome this limitation, we propose to take advantage of the intrinsic motion information in dance videos to solve the video recommendation problem. We present a novel system that recommends dance videos based on a mid-level action representation, termed Dancelets. The Dancelets are used to bridge the semantic gap between video content and high-level concept, dance style, which plays a significant role in characterizing different types of dances. The proposed method executes automatic mining of dancelets with a concatenation of normalized cut clustering and linear discriminant analysis. This ensures that the discovered dancelets are both representative and discriminative. Additionally, to exploit the motion cues in videos, we employ motion boundaries as saliency priors to generate volumes of interest and extract C3D features to capture spatiotemporal information from the mid-level patches. Extensive experiments validated on our proposed large dance dataset, HIT Dances dataset, demonstrate the effectiveness of the proposed methods for dance style-based video recommendation.
KW - Dancelets
KW - LDA detector
KW - dance style
KW - normalized cuts
KW - spatiotemporal features
KW - video recommendation
UR - http://www.scopus.com/inward/record.url?scp=85017642606&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85017642606&partnerID=8YFLogxK
U2 - 10.1109/TMM.2016.2631881
DO - 10.1109/TMM.2016.2631881
M3 - Article
AN - SCOPUS:85017642606
SN - 1520-9210
VL - 19
SP - 712
EP - 724
JO - IEEE Transactions on Multimedia
JF - IEEE Transactions on Multimedia
IS - 4
M1 - 7752919
ER -