We present a novel two-phase Support Vector Machine (SVM) based specific recognition model that is learned using an optimized generic recognition model.

1. Generic to Specific Recognition Models for
Membership Analysis in Group
Videos
Wenxuan Mou1, Christos Tzelepis 1,3, Vasileios Mezaris 3, Hatice Gunes2,
Ioannis Patras1
Queen Mary University of London1, University of Cambridge2, Information Technologies
Institute/Centre for Research and Technology Hellas (CERTH) 3

2. 2
Outline
 Introduction
 The Proposed Framework
 Experiments and Results
 Conclusions and Future Work

3. 3
Introduction
 Definitions of group membership recognition
Recognize which group each individual is part of
Group 1 Group 2
Group 3
Subject 1 Subject 2 Subject 3 Subject 4 Subject 5 Subject 6 Subject 7 Subject 8
Subject 9 Subject 10 Subject 11 Subject 12

4. 4
Introduction
 Motivation
People in a group share similar behaviors and
emotions [1]
Body features work better than the face features
in predicting group membership [2]
[1] S. G. Barsade, “The ripple effect: Emotional contagion and its influence on group behavior,” Administrative Science Quarterly, 2002.
[2] W. Mou, H. Gunes, and I. Patras, “Automatic recognition of emotions and membership in group videos,” in CVPRW, 2016.

5. 5
The Proposed Framework
X Y
f
X：Body behaviors
Y：Group membership
(Group 1 ? 2 ? 3 ?)
f：Linear-SVM
12 subjects from 3 groups watching 4 videos
Leave one subject out (blue) cross-validation
 Group membership recognition is modelled as
a classification problem

6. 6
The Proposed Framework
Independent recognition modelGeneric recognition model Independent recognition modelGeneric recognition model
(W1)
(W2)
(W3)
(W4)
 Generic model and independent model

7. 7
The Proposed Framework
(W0)
(W1)
(W2)
(W3)
(W4)
(W0)
(W1)
(W2)
(W3)
(W4)
 The proposed two-phase learning model

8. 8
The Proposed Framework
λ : the regularization parameter
w0, b0 : the optimization parameters
𝐿 : the loss function and is given by the hinge-loss
𝑃𝑔𝑒𝑛𝑒𝑟𝑖𝑐: min
𝑤0, 𝑏0
λ
2
||𝑤0||2 +
1
𝑙
𝑖=1
𝑙
𝐿 𝑤0 , 𝑏0; 𝑥𝑖, 𝑧𝑖
 Generic model

9. 9
The Proposed Framework
𝑃𝑠𝑝𝑒𝑐𝑖𝑓𝑖𝑐: min
w,𝑏
μ
2
||w||2
+
ν
2
||𝑤 − 𝑤0||2
+
1
|𝑋𝑡|
𝐿(𝑤, 𝑏; (𝑥𝑖, 𝑧𝑖))
𝑋𝑡 ：a subset of the original training set
μ and ν ：regularization parameters
ν
2
||𝑤 − 𝑤0||2
： is used to bias 𝑤 to be close to 𝑤0
 Specific model

10. 10
The Proposed Framework
 Optimization: stochastic gradient descent (SGD)
𝐽 𝑤, 𝑏 =
μ
2
||w||2 +
ν
2
||𝑤 − 𝑤0||2 +
1
𝑘
𝑥 𝑖, 𝑧 𝑖 ∈𝑋𝑡
𝐿(𝑤, 𝑏; (𝑥𝑖, 𝑧𝑖))
Update 𝑤 and 𝑏 : 𝑤 𝑡+1
= 𝑤 𝑡
−
𝛿𝑡
𝑘
𝜕𝐽
𝜕𝑤
𝑏 𝑡+1 = 𝑏 𝑡 −
𝛿𝑡
𝑘
𝜕𝐽
𝜕𝑏
The first derivatives of 𝐽 with respect to 𝑤 and 𝑏:
𝜕𝐽
𝜕𝑤
= 𝜇𝑤 − 𝜈 𝑤 − 𝑤0 +
𝑥 𝑖, 𝑧 𝑖 ∈𝑋𝑡
𝜕𝐽
𝜕𝑤
𝜕𝐽
𝜕𝑏
=
1
𝑘
𝑥 𝑖, 𝑧 𝑖 ∈𝑋𝑡
𝜕𝐽
𝜕𝑏
Objective function of 𝑃𝑠𝑝𝑒𝑐𝑖𝑓𝑖𝑐 :

11. 11
The Proposed Framework
[1]
[1] H. Wang, A. Kl¨ aser, C. Schmid, and C.-L. Liu, “Dense trajectories and motion boundary descriptors for action recognition,” IJCV, 2013.
 Feature extraction

12. 12
Experiments and Results
• Data: 3 groups of data, 12 participants in total
• Feature: Body HOF feature
• Classifier: linear-SVM
Different Models Average Accuracy (p-value)
Specific recognition model 52% (p<0.01)
Generic recognition model 35% (p=0.41)
Independent recognition model 33% (p=0.42)
Chance level 33%
 Experiment setup
 Experimental results

13. 13
Conclusions and Future Work
The proposed two-phase learning model outperforms
the other models
Group membership recognition results also indicates
that individuals influence each others behaviours
within a group and their nonverbal behaviours share
commonalities
 Conclusions

14. 14
Conclusions and Future Work
 Future work
Testing with a larger database
Applying the two-phase learning model to other
applications, such as affect recognition

15. 15
Many thanks for your
attention !
Acknowledgement: The work of Wenxuan Mou is supported by CSC/Queen Mary joint PhD scholarship. The
work of Hatice Gunes and Wenxuan Mou is partially funded by the EPSRC under its IDEAS Factory Sandpits call
on Digital Personhood (grant ref: EP/L00416X/1). The work of Christos Tzelepis and Vasileios Mezaris is
supported by EU’s Horizon 2020 programme under grant agreement H2020-693092 MOVING.