![](bg8.png)
outperforms the direct approach model in within and
across category attribute prediction, multi-class clas-
sification and zero-shot learning. In addition, our
model is simple and computationally more efficient
than methods that use the base feature space.
ACKNOWLEDGEMENTS
This study is funded by OSEO, French State agency
for innovation, as part of the Quaero Programme.
REFERENCES
Chang, C.-C. and Lin, C.-J. (2011). LIBSVM: A library
for support vector machines. ACM Transactions on
Intelligent Systems and Technology, 2:27:1–27:27.
Comon, P. (1994). Independent component analysis, A new
concept? Signal Processing, 36(3):287–314.
de Jong, S. (1993). SIMPLS: An alternative approach to
partial least squares regression. Chemometrics and In-
telligent Laboratory Systems, 18(3):251–263.
Duan, K., Parikh, D., Carndall, D., and Grauman, K.
(2012). Discovering localized attributes for fine-
grained recognition. In CVPR.
Everingham, M., Van Gool, L., Williams, C. K. I., Winn,
J., and Zisserman, A. (2008). The PASCAL Visual
Object Classes Challenge 2008 (VOC2008) Results.
Farhadi, A., Endres, I., and Hoiem, D. (2010). Attribute-
Centric Recognition for Cross-category Generaliza-
tion. In CVPR.
Farhadi, A., Endres, I., Hoiem, D., and Forsyth, D. (2009).
Describing Objects by their Attributes. In CVPR.
Ferrari, V. and Zisserman, A. (2008). Learning Visual At-
tributes. In NIPS.
Fu, Y., Hospedales, T. M., Xiang, T., and Gong, S. (2012).
Attribute Learning for Understanding Unstructured
Social Activity. In ECCV.
Gehrig, T. and Ekenel, H. K. (2011). Facial Action Unit
Detection Using Kernel Partial Least Squares. In 1st
IEEE Int’l Workshop on Benchmarking Facial Image
Analysis Technologies (BeFIT 2011).
Guo, G. and Mu, G. (2011). Simultaneous Dimensional-
ity Reduction and Human Age Estimation via Kernel
Partial Least Squares Regression. In CVPR.
Haj, M. A., Gonz
`
ales, J., and Davis, L. S. (2012). On
Partial Least Squares in Head Pose Estimation: How
to simultaneously deal with misalignment. In CVPR,
Providence, RI, USA.
Hyv
¨
arinen, A. and Oja, E. (2000). Independent component
analysis: algorithms and applications. Neural net-
works : the official journal of the International Neural
Network Society, 13(4-5):411–30.
Kumar, N., Berg, A., Belhumeur, P. N., and Nayar, S.
(2011). Describable Visual Attributes for Face Verifi-
cation and Image Search. In PAMI, pages 1962–1977.
Lampert, C., Nickisch, H., and Harmeling, S. (2009).
Learning to detect unseen object classes by between-
class attribute transfer. In CVPR.
Liu, J., Kuipers, B., and Savarese, S. (2011). Recognizing
Human Actions by Attributes. In CVPR.
Parikh, D. and Grauman, K. (2011). Relative Attributes. In
ICCV.
Rosipal, R. and Kr
¨
amer, N. (2006). Overview and recent
advances in partial least squares. In Saunders, C.,
Grobelnik, M., Gunn, S., and Shawe-Taylor, J., ed-
itors, Subspace, Latent Structure and Feature Selec-
tion, pages 34–51. Springer.
Schwartz, W., Guo, H., and Davis, L. (2010). A robust
and scalable approach to face identification. In ECCV.
Springer.
Schwartz, W. R. and Davis, L. S. (2009). Learning discrim-
inative appearance-based models using partial least
squares. In XXII Brazilian Symposium on Computer
Graphics and Image Processing, pages 322–329.
Schwartz, W. R., Kembhavi, A., Harwood, D., and Davis,
L. S. (2009). Human detection using partial least
squares analysis. In ICCV.
Sharma, A. and Jacobs, D. (2011). Bypassing Synthesis:
PLS for Face Recognition with Pose, Low-Resolution
and Sketch. In CVPR.
Wang, G. and Forsyth, D. (2009). Joint learning of visual
attributes, object classes and visual saliency. In ICCV.
Wang, Y. and Mori, G. (2010). A Discriminative Latent
Model of Object Classes and Attributes. In ECCV.
Yao, B., Jiang, X., Khosla, A., Lin, A. L., Guibas, L.,
and Fei-Fei, L. (2011). Human action recognition by
learning bases of action attributes and parts. In ICCV.
LearningSemanticAttributesviaaCommonLatentSpace
55