![](bg8.png)
Table 4: Attribute recognition results on VIPeR (in %).
Attributes
Accuracy Recall@FPR=0.2 AUC
svm(Layne
et al., 2012)
mlcnn-p(Zhu
et al., 2015)
ours svm(Layne
et al., 2012)
mlcnn-p(Zhu
et al., 2015)
ours ours
redshirt 85.5 91.9 94.4 88.4 88.9 95.9 95.2
blueshirt 73.0 69.1 91.5 60.8 70.8 75.5 83.1
lightshirt 83.7 83.0 84.4 87.8 85.3 88.2 91.7
darkshirt 84.2 82.3 83.3 87.5 85.8 86.1 90.9
greenshirt 71.4 75.9 96.2 54.3 69.4 84.6 88.7
nocoat 70.6 71.3 74.2 59.3 57.2 65.4 80.4
notlightdarkjean 70.3 90.7 96.7 57.2 78.6 80.0 86.0
darkbottoms 75.7 78.4 78.9 70.2 76.2 74.9 85.7
lightbottoms 74.7 76.4 76.5 69.5 73.3 72.3 83.6
hassatchel 47.8 57.8 70.9 22.0 31.7 39.1 64.8
barelegs 75.6 84.1 92.2 68.7 85.4 92.2 92.8
shorts 70.4 81.7 92.3 59.8 82.9 87.3 88.6
jeans 76.4 77.5 80.6 72.7 74.7 81.7 87.6
male 66.5 69.6 74.7 48.2 57.2 67.9 82.1
skirt 63.6 78.1 94.3 40.7 60.7 61.3 72.8
patterned 46.9 57.9 90 26.3 41.0 49.9 68.1
midhair 64.1 76.1 75.2 43.0 63.5 54.1 73.1
darkhair 63.9 73.1 67.5 39.6 58.4 49.7 71.9
hashandbagcarrierbag 45.3 42.0 90.9 17.4 18.5 27.5 55.1
hasbackpack 67.5 64.9 72.7 47.9 49.9 57.4 76.3
average 68.9 74.1 83.9 56.1 65.5 69.6 80.9
Ding, S., Lin, L., Wang, G., and Chao, H. (2015). Deep
feature learning with relative distance comparison
for person re-identification. Pattern Recognition,
48(10):2993–3003.
Duan, K., Parikh, D., Crandall, D., and Grauman, K.
(2012). Discovering localized attributes for fine-
grained recognition. In Proc. of the IEEE Interna-
tional Conference on Computer Vision and Pattern
Recognition (CVPR), pages 3474–3481.
Gray, D., Brennan, S., and Tao, H. (2007). Evaluating ap-
pearance models for recognition, reacquisition, and
tracking. In Proc. of International Workshop on Per-
formance Evaluation for Tracking and Surveillance
(PETS).
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Im-
agenet classification with deep convolutional neural
networks. In Proc. of Advances in neural information
processing systems (NIPS), pages 1097–1105.
Kumar, N., Berg, A. C., Belhumeur, P. N., and Nayar, S. K.
(2009). Attribute and simile classifiers for face veri-
fication. In Proc. of the International Conference on
Computer Vision (ICCV), pages 365–372.
Layne, R., Hospedales, T. M., and Gong, S. (2014).
Attributes-based re-identification. In Person Re-
Identification, pages 93–117. Springer.
Layne, R., Hospedales, T. M., Gong, S., and Mary, Q.
(2012). Person re-identification by attributes. In Proc.
of the British Machine Vision Conference (BMVC),
page 8.
Lefebvre, G. and Garcia, C. (2013). Learning a bag of
features based nonlinear metric for facial similarity.
In Advanced Video and Signal Based Surveillance
(AVSS), 2013 10th IEEE International Conference on,
pages 238–243. IEEE.
Li, D., Chen, X., and Huang, K. (2015). Multi-attribute
learning for pedestrian attribute recognition in surveil-
lance scenarios. Proc. of the Asian Conference on Pat-
tern Recognition (ACPR).
Li, H., Chen, J., Lu, H., and Chi, Z. (2017). Cnn for saliency
detection with low-level feature integration. Neuro-
computing, 226:212–220.
Li, W., Zhao, R., Xiao, T., and Wang, X. (2014). Deep-
reid: Deep filter pairing neural network for person re-
identification. In Proceedings of the IEEE Conference
on Computer Vision and Pattern Recognition, pages
152–159.
Liao, S., Hu, Y., Zhu, X., and Li, S. Z. (2015). Person re-
identification by local maximal occurrence represen-
tation and metric learning. In Proc. of the IEEE Inter-
national Conference on Computer Vision and Pattern
Recognition (CVPR), pages 2197–2206.
Liao, S., Zhao, G., Kellokumpu, V., Pietik
¨
ainen, M., and
Li, S. Z. (2010). Modeling pixel process with scale
invariant local patterns for background subtraction in
complex scenes. In Proc. of the IEEE International
Conference on Computer Vision and Pattern Recogni-
tion (CVPR), pages 1301–1306.
Liu, J., Kuipers, B., and Savarese, S. (2011). Recognizing
human actions by attributes. In Proc. of the IEEE In-
ternational Conference on Computer Vision and Pat-
tern Recognition (CVPR), pages 3337–3344.
Lumini, A., Nanni, L., and Ghidoni, S. (2016). Deep
featrues combined with hand-crafted features for face
recognition. International Journal of Computer Re-
search, 23(2):123.
Pedestrian Attribute Recognition with Part-based CNN and Combined Feature Representations
121