Faceless person recognition: Privacy implications in social media

SJ Oh, R Benenson, M Fritz, B Schiele - … 11-14, 2016, Proceedings, Part III …, 2016 - Springer
As we shift more of our lives into the virtual domain, the volume of data shared on the web
keeps increasing and presents a threat to our privacy. This works contributes to the …

Pairwise similarity knowledge transfer for weakly supervised object localization

A Rahimi, A Shaban, T Ajanthan, R Hartley… - European conference on …, 2020 - Springer
Abstract Weakly Supervised Object Localization (WSOL) methods only require image level
labels as opposed to expensive bounding box annotations required by fully supervised …

Text co-detection in multi-view scene

C Wang, H Fu, L Yang, X Cao - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
Multi-view scene analysis has been widely explored in computer vision, including numerous
practical applications. The texts in multi-view scenes are often detected by following the …

Context-based abnormal object detection using the fully-connected conditional random fields

J Oh, HI Kim, RH Park - Pattern Recognition Letters, 2017 - Elsevier
The contextual information plays an important role in computer vision, particularly in object
detection and scene understanding. The existing contextual models use only the …

Learning to co-generate object proposals with a deep structured network

Z Hayder, X He, M Salzmann - Proceedings of the IEEE …, 2016 - openaccess.thecvf.com
Generating object proposals has become a key component of modern object detection
pipelines. However, most existing methods generate the object candidates independently of …

Exploiting context based on CNN and coding representations for pedestrian co-detection

L Jiang, J Ji, W Zhong, T Zhang, H **ong - Multimedia Tools and …, 2020 - Springer
The exploitation of contextual information among multiple images has been proven
significant to improve detection performance by object co-detection methods. In this paper …

Object codetection based on a higher-order conditional random field

L Jiang, W Zhong, J Ji, H **ong - Journal of Electronic Imaging, 2019 - spiedigitallibrary.org
In recent years, codetecting objects through the use of contextual information across multiple
images has attracted considerable attention. We introduce an object codetection method …

Improved Hough transform by modeling context with conditional random fields for partially occluded pedestrian detection

L Jiang, H **ong - Optical Engineering, 2018 - spiedigitallibrary.org
Traditional Hough transform-based methods detect objects by casting votes to object
centroids from object patches. It is difficult to disambiguate object patches from the …

[PDF][PDF] Deep Structured Models for Large Scale Object Co-detection and Segmentation

Z Hayder - 2017 - core.ac.uk
Structured decisions are often required for a large variety of image and scene understanding
tasks in computer vision, with few of them being object detection, localization, semantic …