Abstract: Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to provide excellent results for gender and action recognition. The performance of semantic pyramids approach relies on robust image description and is therefore limited due to the use of shallow local features. In the context of object recognition [2] and object detection [3], convolutional neural networks (CNNs) or deep features have shown to improve the performance over the conventional shallow features.
We propose deep semantic pyramids for human attributes and action recognition. The method works by constructing spatial pyramids based on CNNs of different part locations. These pyramids are then combined to obtain a single semantic representation. We validate our approach on the Berkeley and 27 Human Attributes datasets for attributes classification. For action recognition, we perform experiments on two challenging datasets: Willow and PASCAL VOC 2010. The proposed deep semantic pyramids provide a significant gain of 17.2%, 13.9%, 24.3% and 22.6% compared to the standard shallow semantic pyramids on Berkeley, 27 Human Attributes, Willow and PASCAL VOC 2010 datasets respectively. Our results also show that deep semantic pyramids outperform conventional CNNs based on the full bounding box of the person. Finally, we compare our approach with state-of-the-art methods and show a gain in performance compared to best methods in literature.

Abstract: Projector-camera systems are designed to improve the projection quality by comparing original images with their captured projections, which is usually complicated due to high photometric and geometric variations. Many research works address this problem using their own test data which makes it extremely difficult to compare different proposals. This paper has two main contributions. Firstly, we introduce a new database of acquired image projections (DAcImPro) that, covering photometric and geometric conditions and providing data for ground-truth computation, can serve to evaluate different algorithms in projector-camera systems. Secondly, a new object recognition scenario from acquired projections is presented, which could be of a great interest in such domains, as home video projections and public presentations. We show that the task is more challenging than the classical recognition problem and thus requires additional pre-processing, such as color compensation or projection area selection.

Abstract: Computational intelligent systems could reduce polyp miss rate in colonoscopy for colon cancer diagnosis and, thus, increase the efficiency of the procedure. One of the main problems of existing polyp localization methods is a lack of spatio-temporal stability in their response. We propose to explore the response of a given polyp localization across temporal windows in order to select
those image regions presenting the highest stable spatio-temporal response.
Spatio-temporal stability is achieved by extracting 3D watershed regions on the
temporal window. Stability in localization response is statistically determined by analysis of the variance of the output of the localization method inside each 3D region. We have explored the benefits of considering spatio-temporal stability in two different tasks: polyp localization and polyp detection. Experimental results indicate an average improvement of 21:5% in polyp localization and 43:78% in polyp detection.

Abstract: Detecting social interaction in videos relying solely on visual cues is a valuable task that is receiving increasing attention in recent years. In this work, we address this problem in the challenging domain of egocentric photo-streams captured by a low temporal resolution wearable camera (2fpm). The major difficulties to be handled in this context are the sparsity of observations as well as unpredictability of camera motion and attention orientation due to the fact that the camera is worn as part of clothing. Our method consists of four steps: multi-faces localization and tracking, 3D localization, pose estimation and analysis of f-formations. By estimating pair-to-pair interaction probabilities over the sequence, our method states the presence or absence of interaction with the camera wearer and specifies which people are more involved in the interaction. We tested our method over a dataset of 18.000 images and we show its reliability on our considered purpose. © (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.