school of electronic information engineering , tianjin university

11
School of Electronic Information Engineering , Tianjin University Cross-view Action Recognition via a Transferable Dictionary Pair (TDP) Jia pingping

Upload: leo-delgado

Post on 30-Dec-2015

43 views

Category:

Documents


1 download

DESCRIPTION

Cross-view Action Recognition via a Transferable Dictionary Pair (TDP) Jia pingping. School of Electronic Information Engineering , Tianjin University. Outline :. Experimental Method. 1. Experimental Result. 2. School of Electronic Information Engineering , Tianjin University. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: School of Electronic Information Engineering , Tianjin University

School of Electronic Information Engineering , Tianjin University

Cross-view Action Recognition via a

Transferable Dictionary Pair (TDP)

Jia pingping

Page 2: School of Electronic Information Engineering , Tianjin University

School of Electronic Information Engineering , Tianjin University

Outline:

Experimental ResultExperimental Result2

Experimental MethodExperimental Method1

Page 3: School of Electronic Information Engineering , Tianjin University

Experimental MethodExperimental Method

– Method: a method for view invariant based on sparse

representations using a transferable dictionary pair.

1. Source-view BoVW/ Targe view BoVW

2. Learn a dictionary pair {Ds,Dt}

3. represent training videos in the source view and test videos in the target view using the corresponding source and target dictionaries respectively

4. classifier : k_NN

Page 4: School of Electronic Information Engineering , Tianjin University

2. Learn a dictionary pair {Ds,Dt}

Unsupervised:

: the feature representations of M videos of shared actions in the source and target views: the sparse representations

p source views , one target view

Page 5: School of Electronic Information Engineering , Tianjin University

2. Learn a dictionary pair {Ds,Dt}

Supervised:

: the feature representations of M videos of shared actions in the source and target views: the sparse representations

: consist of the ideal "discriminative" sparse codes of shared action videos in both views.

Page 6: School of Electronic Information Engineering , Tianjin University

2. Learn a dictionary pair {Ds,Dt}

Unsupervised:

Supervised:

Formulate the problem of learning a transferable dictionary pair as an optimization problem which can be efficiently solved using the K-SVD algorithm.Ds and Dt are learned by forcing two sets of videos of shared unlabeled/labeled actions in two views to have the same sparse representations.

Page 7: School of Electronic Information Engineering , Tianjin University

3. represent training videos in the source view and test videos in the target view using the corresponding source and target dictionaries respectively

version speed memory

Xs=OMP(Ds'*S, sum(S.*S) , (Ds')*Ds, sparsitythres) very fast very large

Xs=OMP(Ds, S, (Ds')*Ds, sparsitythres) fast moderate

Xt=OMP(Dt, T, [], sparsitythres) very slow small

OMP algorithm

S:all BoW of source view; T: orphan /test BoW of target view

Page 8: School of Electronic Information Engineering , Tianjin University

Experimental ResultExperimental Result

* Test dataset : IXMAS

1 、 10actors, 11actions, three time per action

2 、 experiments on all possible pairwise view combinations (20)

3 、 1500D local (cuboids) and global (shape flow) feature

4 、 Dictionary size : 50 、 100 、 200 、 300

Sparse : 10 、 20 、 30 、 50

(紫色: unsupervised ; 红色: supervised )

5 、 Leave one action class out

6 、 k-NN classifier

k = 1, 2, …, 10

Page 9: School of Electronic Information Engineering , Tianjin University

1 、 Each row corresponds to a source (training) view and each column a target (test) view.2 、 The recognition numbers in the bracket are the average recognition accuracies of k-NN without transfer, our unsupervised and supervised approaches respectively.

Page 10: School of Electronic Information Engineering , Tianjin University

1 、 Each column corresponds to one target view. 2 、 The first two rows show the recognition accuracies of our unsupervised and supervised approaches.

Page 11: School of Electronic Information Engineering , Tianjin University

School of Electronic Information Engineering , Tianjin University

参考文献Jingjing Zheng, Zhoulin Jiang, P.Jonathon Philips and Rama Chellappa. Cross-view Action Recognition via a Transferable Dictionary Pair.