Presenter: Yang Liu, Hong-Kong Baptist University, Hong-Kong
Paper: http://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_20.pdf
Authors: Yang Liu, Zhonglei Gu, Tobey H. Ko
Abstract: In this paper, we describe our model designed for automatic prediction of media interestingness. Specifically, a two-stage learning framework is proposed. In the first stage, supervised dimensionality reduction is employed to discover the key discriminant information embedded in the original feature space. We present a new algorithm dubbed biased discriminant embedding (BDE) to extract discriminant features with discrete labels and use supervised manifold regression (SMR) to extract discriminant features with continuous labels. In the second stage, SVM is utilized for prediction. Experimental results validate the effectiveness of our approaches.
Similar to MediaEval 2017 - Interestingness Task: Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
Significant Data Hiding through Discrete Wavelet Transformation ApproachEswar Publications
Similar to MediaEval 2017 - Interestingness Task: Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression (20)
HIV AND INFULENZA VIRUS PPT HIV PPT INFULENZA VIRUS PPT
MediaEval 2017 - Interestingness Task: Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
1. Predicting Media Interestingness via
Biased Discriminant Embedding and
Supervised Manifold Regression
Yang Liu1,2, Zhonglei Gu1, Tobey H. Ko3
1Department of Computer Science, Hong Kong Baptist University
2Institute of Research and Continuing Education, Hong Kong Baptist
University
3Department of Industrial and Manufacturing Systems Engineering,
University of Hong Kong
2. Our System
Feature Extraction + Prediction
Step1: Supervised Feature Extraction
Biased Discriminant Embedding (BDE) for discrete labels
Supervised Manifold Regression (SMR) for continuous labels
Step2: Classification/Regression
v-Support Vector Classification (v-SVC)
ε-Support Vector Regression (ε-SVR)
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
2
3. Feature Extraction for Discrete Labels:
Biased Discriminant Embedding
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
: Transformation matrix to be learned
: Biased between-class scatter matrix
Idea: The biased discriminant information in the reduced subspace
should be maximized. (Motivation: we are probably more interested
in the interesting class than the non-interesting one)
Formulation:
: Biased within-class scatter matrix
Solution: The problem can be solved by eigen-decomposition
3
4. Feature Extraction for Continuous Labels:
Supervised Manifold Regression
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
: Transformation matrix to be learned
: The i-th data sample
Idea: The more similar the interestingness levels of two data
samples, the closer the two feature vectors should be in the
learned subspace
Formulation:
: Interestingness similarity, i.e., label similarity
Solution: The problem can be solved by eigen-decomposition
: Data similarity in the original space
4
5. Media Interestingness Prediction
Predicting Interesting/Non-interesting
Formulated as a binary classification problem
v-Support Vector Classification (v-SVC)
Predicting Interestingness levels
Formulated as a real-value regression problem
ε-Support Vector Regression (ε-SVR)
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
5
6. Experimental Setting 1
Image feature vectors: 1299-D
128-D color histogram features, 300-D denseSIFT
features, 512-D gist features, 300-D hog2*2, 59-D LBP
features
Video feature vectors: 2598-D
Calculate the average and standard deviation over all
frames of the corresponding shot, and concatenate
these two 1299-D feature vectors
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
6
7. Experimental Setting 2
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
Run 1 of image data
Use the normalized 1299-D feature vector as the input of SVM
Runs 2-5 of image data
Reduce the original data to the 23-D, 25-D, 26-D, 27-D
subspaces via BDE (for discrete labels) and SMR (for continuous
labels), respectively
Run 1 of video data
Use the normalized 2598-D feature vector as the input of SVM
Runs 2-5 of video data
Reduce the original data to the 23-D, 25-D, 26-D, 27-D
subspaces via BDE (for discrete labels) and SMR (for continuous
labels), respectively
7
8. Experimental Setting 3
𝜈-SVC
Use an RBF kernel with 𝜈 = 0.1 and 𝑔𝑎𝑚𝑚𝑎 = 100
(for image data) / 64 (for video data).
ε-SVR
Use an RBF kernel with 𝑐𝑜𝑠𝑡 = 1, 𝜖 = 0.01, and 𝛾 =
1/𝐷
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
8
9. Results and Observations
Observation: For image data, the reduced features perform better than the
original ones
Subspaces learned by BDE and SMR capture important discriminant
information
Observation: For video data, the performance of reduced features is slightly
worse than that of the original ones
Video data are more complex than image data so that such a low-dimensional
representation cannot fully capture the key discriminant information embedded in
the original space.
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
9
11. Results and Observations
The contribution of the 𝑖-th dimension is defined as
where 𝜆𝑗 denotes the 𝑗-th eigenvalue, 𝑤𝑖𝑗 denotes the (𝑖, 𝑗)-th element of
W, and | · | denotes the absolute value operator.
Observation 1: Color histogram and LBP features contribute more than
the others while the GIST features contribute the least in the discrete
prediction task (Figures 1(a) and 1(c))
Observation 2: Color histogram and GIST features contribute the most
among the five feature sets in the continuous prediction task (Figures
1(b) and 1(d))
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
11
12. Outlook
Improve the performance of video interestingness
prediction by incorporating the video temporal
information
Refine the human labeled ground truth (especially
for continuous case) via machine learning
technologies
The ground truth (labels) of interestingness are
provided by human beings, they generally vary with
each individual and are somewhat subjective
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
12
13. Q & A
Thank You !
Predicting Media Interestingness via Biased Discriminant Embedding and Supervised Manifold Regression
13