Coert van Gemeren

• Dr.
• Researcher Computer Vision and AI at University of Applied Sciences Utrecht

We propose a method for detecting dyadic interactions: fine-grained, coordinated interactions between two people. Our model is capable of recognizing interactions such as a hand shake or a high five, and locating them in time and space. At the core of our method is a pictorial structures model that additionally takes into account the fine-grained m...

We present an evaluation of tools for assessing the impact of AI in the Dutch media sector. Our evaluation of the ECP AIIA tool shows the need for clear guidelines in the adoption of various AI applications within Dutch media organisations. We conclude that the adoption of impact assessment tools, such as the ECP AIIA, is not held back by common me...

The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in neuroscience, lies in the comp...

We introduce a novel spatiotemporal deformable part model for the localization of fine-grained human interactions of two persons in unsegmented videos. Our approach is the first to classify interactions and additionally provide the temporal and spatial extent of the interaction in the video. To this end, our models contain part detectors that suppo...

The most popular optical flow algorithms rely on optimizing the energy function that integrates a data term and a smoothness term. In contrast to this traditional framework, we derive a new objective function that couples optical flow estimation and image restoration. Our method is inspired by the recent successes of edge-aware constraints (EAC) in...

We introduce a novel spatio-temporal deformable part model for offline detection of fine-grained interactions in video. One novelty of the model is that part detectors model the interacting individuals in a single graph that can contain different combinations of feature descriptors. This allows us to use both body pose and movement to model the coo...

This paper focuses on recognizing image concepts by introducing the ISTOP model. The model parses the images from scene to object׳s parts by using a context sensitive grammar. Since there is a gap between the scene and object levels, this grammar proposes the “Visual Term” level to bridge the gap. Visual term is a higher concept level than the obje...

Median filtering the intermediate flow fields during optimization has been demonstrated to be very useful for improving the estimation accuracy. By formulating the median filtering heuristic as non-local term in the objective function, and modifying the new term to include flow and image information that according to spatial distance, color similar...

Measuring a person’s behavior in any kind of domain by a computer system, starts with measuring and analyzing that person’s movements. Video technology provides an unobtrusive way of capturing this information. In this paper, we will focus on articulated tracking, which is the field of estimating and tracking the body pose of a person. A pose consi...

We present a novel combined post-filtering (CPF) method to improve the accuracy of optical flow estimation. Its attractive advantages are that outliers reduction is attained while discontinuities are well preserved, and occlusions are partially handled. Major contributions are the following: First, the structure tensor (ST) based edge detection is...