WISS 2018 [2 4] [5,6] Query-by-Dancing Query-by- Dancing Cao [1] OpenPose 2 Ghias [7] Query by humming Chen [8] Query by rhythm Jang [9] Query-by-tapp

Similar documents
[2][3][4][5] 4 ( 1 ) ( 2 ) ( 3 ) ( 4 ) 2. Shiratori [2] Shiratori [3] [4] GP [5] [6] [7] [8][9] Kinect Choi [10] 3. 1 c 2016 Information Processing So

IPSJ-MUS

3 2 2 (1) (2) (3) (4) 4 4 AdaBoost 2. [11] Onishi&Yoda [8] Iwashita&Stoica [5] 4 [3] 3. 3 (1) (2) (3)

(MIRU2008) HOG Histograms of Oriented Gradients (HOG)

2 3, 4, [1] [2] [3]., [4], () [3], [5]. Mel Frequency Cepstral Coefficients (MFCC) [9] Logan [4] MFCC MFCC Flexer [10] Bogdanov2010 [3] [14],,,

第122号.indd

1 Kinect for Windows M = [X Y Z] T M = [X Y Z ] T f (u,v) w 3.2 [11] [7] u = f X +u Z 0 δ u (X,Y,Z ) (5) v = f Y Z +v 0 δ v (X,Y,Z ) (6) w = Z +

Gaze Head Eye (a) deg (b) 45 deg (c) 9 deg 1: - 1(b) - [5], [6] [7] Stahl [8], [9] Fang [1], [11] Itti [12] Itti [13] [7] Fang [1],

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s

28 Horizontal angle correction using straight line detection in an equirectangular image

IPSJ SIG Technical Report Vol.2009-DPS-141 No.20 Vol.2009-GN-73 No.20 Vol.2009-EIP-46 No /11/27 1. MIERUKEN 1 2 MIERUKEN MIERUKEN MIERUKEN: Spe

1(a) (b),(c) - [5], [6] Itti [12] [13] gaze eyeball head 2: [time] [7] Stahl [8], [9] Fang [1], [11] 3 -

2). 3) 4) 1.2 NICTNICT DCRA Dihedral Corner Reflector micro-arraysdcra DCRA DCRA DCRA 3D DCRA PC USB PC PC ON / OFF Velleman K8055 K8055 K8055

3.1 Thalmic Lab Myo * Bluetooth PC Myo 8 RMS RMS t RMS(t) i (i = 1, 2,, 8) 8 SVM libsvm *2 ν-svm 1 Myo 2 8 RMS 3.2 Myo (Root

The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). The material has been made available on the website

Microsoft Word - deim2011_new-ichinose doc

258 5) GPS 1 GPS 6) GPS DP 7) 8) 10) GPS GPS ) GPS Global Positioning System

xx/xx Vol. Jxx A No. xx 1 Fig. 1 PAL(Panoramic Annular Lens) PAL(Panoramic Annular Lens) PAL (2) PAL PAL 2 PAL 3 2 PAL 1 PAL 3 PAL PAL 2. 1 PAL

([ ]!) name1 name2 : [Name]! name SuperSQL,,,,,,, (@) < >@{ < > } =,,., 200,., TFE,, 1 2.,, 4, 3.,,,, Web EGG [5] SSVisual [6], Java SSedit( ss

GUI(Graphical User Interface) GUI CLI(Command Line Interface) GUI

1. HNS [1] HNS HNS HNS [2] HNS [3] [4] [5] HNS 16ch SNR [6] 1 16ch 1 3 SNR [4] [5] 2. 2 HNS API HNS CS27-HNS [1] (SOA) [7] API Web 2

pp d 2 * Hz Hz 3 10 db Wind-induced noise, Noise reduction, Microphone array, Beamforming 1

(3.6 ) (4.6 ) 2. [3], [6], [12] [7] [2], [5], [11] [14] [9] [8] [10] (1) Voodoo 3 : 3 Voodoo[1] 3 ( 3D ) (2) : Voodoo 3D (3) : 3D (Welc


(fnirs: Functional Near-Infrared Spectroscopy) [3] fnirs (oxyhb) Bulling [4] Kunze [5] [6] 2. 2 [7] [8] fnirs 3. 1 fnirs fnirs fnirs 1

[2] 2. [3 5] 3D [6 8] Morishima [9] N n 24 24FPS k k = 1, 2,..., N i i = 1, 2,..., n Algorithm 1 N io user-specified number of inbetween omis

(a) (b) 1 JavaScript Web Web Web CGI Web Web JavaScript Web mixi facebook SNS Web URL ID Web 1 JavaScript Web 1(a) 1(b) JavaScript & Web Web Web Webji

理工ジャーナル 23‐1☆/1.外村

DEIM Forum 2012 E Web Extracting Modification of Objec

Convolutional Neural Network A Graduation Thesis of College of Engineering, Chubu University Investigation of feature extraction by Convolution

[12] [5, 6, 7] [5, 6] [7] 1 [8] 1 1 [9] 1 [10, 11] [10] [11] 1 [13, 14] [13] [14] [13, 14] [10, 11, 13, 14] 1 [12]

DPA,, ShareLog 3) 4) 2.2 Strino Strino STRain-based user Interface with tacticle of elastic Natural ObjectsStrino 1 Strino ) PC Log-Log (2007 6)

2007/8 Vol. J90 D No. 8 Stauffer [7] 2 2 I 1 I 2 2 (I 1(x),I 2(x)) 2 [13] I 2 = CI 1 (C >0) (I 1,I 2) (I 1,I 2) Field Monitoring Server

main.dvi

3_23.dvi

IPSJ SIG Technical Report Vol.2012-CG-149 No.13 Vol.2012-CVIM-184 No /12/4 3 1,a) ( ) DB 3D DB 2D,,,, PnP(Perspective n-point), Ransa

2. 30 Visual Words TF-IDF Lowe [4] Scale-Invarient Feature Transform (SIFT) Bay [1] Speeded Up Robust Features (SURF) SIFT 128 SURF 64 Visual Words Ni

IPSJ SIG Technical Report Vol.2012-MUS-96 No /8/10 MIDI Modeling Performance Indeterminacies for Polyphonic Midi Score Following and

5 I The Current Situation and Future Prospects of the North Korean Economy presented at the 2014 Korea Dialogue Conference on Strengthenin

& Vol.5 No (Oct. 2015) TV 1,2,a) , Augmented TV TV AR Augmented Reality 3DCG TV Estimation of TV Screen Position and Ro

2016 : M SF

IPSJ SIG Technical Report Vol.2014-DBS-159 No.6 Vol.2014-IFAT-115 No /8/1 1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Info

,,.,.,,.,.,.,.,,.,..,,,, i

Lyra X Y X Y ivis Designer Lyra ivisdesigner Lyra ivisdesigner 2 ( 1 ) ( 2 ) ( 3 ) ( 4 ) ( 5 ) (1) (2) (3) (4) (5) Iv Studio [8] 3 (5) (4) (1) (

2011 : M Schell Interest curve Schell Chan FPS Schell Interest curve Chan FPS Chan Chan Chan Chan

,, WIX. 3. Web Index 3. 1 WIX WIX XML URL, 1., keyword, URL target., WIX, header,, WIX. 1 entry keyword 1 target 1 keyword target., entry, 1 1. WIX [2

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

2

,398 4% 017,

HASC2012corpus HASC Challenge 2010,2011 HASC2011corpus( 116, 4898), HASC2012corpus( 136, 7668) HASC2012corpus HASC2012corpus

IPSJ SIG Technical Report Vol.2011-EC-19 No /3/ ,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-

sigmusdemo.dvi

Transcription:

Query-by-Dancing: WISS 2018. Query-by-Dancing Query-by-Dancing 1 OpenPose [1] Copyright is held by the author(s). DJ DJ DJ

WISS 2018 [2 4] [5,6] Query-by-Dancing Query-by- Dancing Cao [1] OpenPose 2 Ghias [7] Query by humming Chen [8] Query by rhythm Jang [9] Query-by-tapping Maezawa [10] Query-by-conducting 3 1 10 10 10 2. Query-bydancing 2 2 3.1 3.1.1 1 OpenPose [1] OpenPose x x max x min y y max y max A o P d P c (X mean, Y mean ) D c R = Ao D c

Query-by-Dancing: 身体動作の類似性に基づくダンス楽曲検索システム 図 1. UI 画面 図 4. 関節角度の算出 図 2. システム概要 図 3. ダンサーの検出 準の 0 度として 時計回りに角度を算出する さら に これら関節角度を図 4 に示すように θx と θy の 2 つの次元に分解し i 番目の動画の n 番目のフ レームにおける関節角度を 34 次元の特徴ベクトル vθ (n)(1 n N )(1 i I) で表す データ ベースのビデオ総数を I i 番目のビデオのフレーム 数を N とした 骨格情報が検出されなかった関節 角度は 0 を代入した 次に モーションを考慮する ために フレーム間の関節角度の変化に焦点を当て る v θ (n) と v 2 θ (n) を次式に基づいて算出する: v θ (n) = abs(vθ (n) vθ (n 1)) (1) v 2 θ (n) = abs(v θ (n) v θ (n 1)) (2) 踊っているダンサーとして選択した (図 3). 3.1.2 特徴量 動画間のダンス動作類似度を計算するために フ レームごとに 3 つ特徴量を抽出する ここで ダン スを特徴付ける要素としてポーズ 姿勢 とモーショ ン 動作 が重要であると考える まずポーズを考 慮するために OpenPose によって推定された骨格 情報から得られる 17 個の関節角度すべてを 1 フレー ムごとに計算する 角度は 画面垂直方向上側を基 x の各要素の絶対値を含むベクトルを abs(x) とし た 以上 3 つの特徴量を 102 次元の 1 つのベクトル vα (n) にまとめた 検索対象のすべての動画で計 算したベクトルの各要素の平均と分散を求め それ らを用いて vα (n) の各要素が平均 0 分散 1 になる ように正規化を行なった

WISS 2018 4 2 100 82 Hip-hop Break Pop Waack 4 1 25 5. 3.2 2 v α (n) in (1 n N in ) (1 i I) i (1 m N ) d(vα in (n), v α (m)) ( 5) x y d(x, y) N IN N : R α = 1 N in N N in N d(v in α (n), v α (m)). (3) R α tf-idf : 1 N N d(v in W α (n) = α (n), v α (m)) max { 1 N d(v i I N in α (n), v α (m)}. (4) W α (n) 30 W α(n) 30 : N in [W U α = α (n) N d(vα in (n), v α (m))]. N in N (5) U α 10. 4.1 : 12 ( 4 8 ) 1 15 8.5 ADD ADD DTW DTW 4. vα(n) i ADD. (3, 4, 5) α (m)) Dynamic Time Warping d(v in α (n), v 6 DTW 15 Waack 11 5. Waack 5 5 6 (F (3,236) = 4.21, p <.05) LSD ADD (p <.05) ADD 4.2 : 12 ( 6 6 ) 1 15 5.9 Waack Hip-hop Pop Break 4 I Waack Break 13 Break Pop Hip-hop 16

Query-by-Dancing: 5.0 4.0 : : : p<.05 5.0 4.0 : p<.05 3.0 3.0 2.0 2.0 1.0 ADD( ) ADD( ) DTW( ) DTW( ) 1.0 Waack Break Hip-hop Pop 1 2 3 4 5 1 2 3 4 5 6. : I: II( ) 4 ADD 5 I 5 6 (F (3,236) = 3.92, p <.05) LSD Waack Hip-hop Break Hip-hop Break Pop (p <.05) Hip-hop Break 2 1 Hip-hop Hip-hop Middle Hip-hop Style Hip-hop Jazz Hip-hop Girls Hiphop 2 Middle Hip-hop Break Break Middle Hip-hop 2 Break Pop Break Waack. 5 Query-by-Dancing 5.1

WISS 2018 5.2 5.3 6 Query-by-Dancing JST ACCEL (JPMJAC1602) [1] Z. Cao, T. Simon, S.E. Wei, and Y. Sheikh. Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017. [2] W. Chai and B. Vercoe. Using user models in music information retrieval systems. In Proceedings of the 1st International Society of Music Information Retrieval, pp. 23 25, 2000. [3] K. Hoashi, K. Matsumoto, and N. Inoue. Personalization of user profiles for content-based music retrieval based on relevance feedback. In Proceedings of the 11th ACM international conference on Multimedia, pp. 110 119, 2003. [4] K. Hoashi, H. Ishizaki, K. Matsumoto, and F. Sugaya. Content-based music retrieval using query integration for users with diverse preferences. In Proceedings of the 8th International Society of Music Information Retrieval, pp. 463 466, 2007. [5] SoundHound Inc. Soundhound. https://www. soundhound.com/soundhound (accessed June 1, 2018). [6] Shazam Entertainment Ltd. Shazam. https:// www.shazam.com/ (accessed June 1, 2018). [7] A. Ghias, J. Logan, D. Chamberlin, and B. C. Smith. Query by humming - musical information retrieval in an audio database. In Proceedings of the 3rd ACM international conference on Multimedia, pp. 231 236, 1995. [8] J.C.C. Chen and A.L.P. Chen. Query by rhythm: an approach for song retrieval in music databases. In Proceedings of the 8th International Workshop on Research Issues in Data Engineering: Continuous-Media Databases and Applications, pp. 139 146, 1998. [9] J.S.R. Jang, H. R. Lee, and C. H. Yeh. Query by tapping: A new paradigm for content-based music retrieval from acoustic input. In Proceedings of the 2nd Pacific-Rim Conference on Multimedia, pp. 590 597, 2001. [10] A. Maezawa, M. Goto, and H. G. Okuno. Query-by-conducting: An interface to retrieve classical-music interpretations by realtime tempo input. In Proceedings of the 11th International Society of Music Information Retrieval, pp 477 482, 2010.