Search Results - "Poppe, Ronald"

A survey on vision-based human action recognition by Poppe, Ronald

“…Vision-based human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in…”
Get full text

Vision-based human motion analysis: An overview by Poppe, Ronald

“…Markerless vision-based human motion analysis has the potential to provide an inexpensive, non-obtrusive solution for the estimation of body poses. The…”
Get full text

A survey of variational and CNN-based optical flow techniques by Tu, Zhigang, Xie, Wei, Zhang, Dejun, Poppe, Ronald, Veltkamp, Remco C., Li, Baoxin, Yuan, Junsong

“…Dense motion estimations obtained from optical flow techniques play a significant role in many image processing and computer vision tasks. Remarkable progress…”
Get full text

Facing scalability: Naming faces in an online social network by Poppe, Ronald

“…Automatically naming faces in online social networks enables us to search for photos and build user face models. We consider two common weakly supervised…”
Get full text

To freeze or not to freeze: A culture-sensitive motion capture approach to detecting deceit by van der Zee, Sophie, Poppe, Ronald, Taylor, Paul J, Anderson, Ross

“…We present a new signal for detecting deception: full body motion. Previous work on detecting deception from body movement has relied either on human judges or…”
Get full text

Hands-on: deformable pose and motion models for spatiotemporal localization of fine-grained dyadic interactions by van Gemeren, Coert, Poppe, Ronald, Veltkamp, Remco C.

“…We introduce a novel spatiotemporal deformable part model for the localization of fine-grained human interactions of two persons in unsegmented videos. Our…”
Get full text

Learning Class-Specific Features with Class Regularization for Videos by Stergiou, Alexandros, Poppe, Ronald, Veltkamp, Remco C.

“…One of the main principles of Deep Convolutional Neural Networks (CNNs) is the extraction of useful features through a hierarchy of kernels operations. The…”
Get full text

AMAB: Automated measurement and analysis of body motion by Poppe, Ronald, Van Der Zee, Sophie, Heylen, Dirk K. J., Taylor, Paul J.

“…Technologies that measure human nonverbal behavior have existed for some time, and their use in the analysis of social behavior has become more popular…”
Get full text

Perceptual evaluation of backchannel strategies for artificial listeners by Poppe, Ronald, Truong, Khiet P., Heylen, Dirk

“…Artificial listeners are virtual agents that can listen attentively to a human speaker in a dialog. In this paper, we present two experiments where we…”
Get full text

AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling by Stergiou, Alexandros, Poppe, Ronald

“…Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of…”
Get full text

Analyzing human–human interactions: A survey by Stergiou, Alexandros, Poppe, Ronald

“…Many videos depict people, and it is their interactions that inform us of their activities, relation to one another and the cultural and social setting. With…”
Get full text

Learn to cycle: Time-consistent feature discovery for action recognition by Stergiou, Alexandros, Poppe, Ronald

“…•Discovery of features in 3D-CNNs with consistent temporal patterns.•Elegant gating mechanism based on temporal cyclic consistency.•State-of-the-art results on…”
Get full text

Refining activation downsampling with SoftPool by Stergiou, Alexandros, Poppe, Ronald, Kalliatakis, Grigorios

“…Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to…”
Get full text

Light Field Saliency Detection With Deep Convolutional Networks by Zhang, Jun, Liu, Yamei, Zhang, Shengping, Poppe, Ronald, Wang, Meng

“…Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light. The detection of salient…”
Get full text

Spatio-Temporal FAST 3D Convolutions for Human Action Recognition by Stergiou, Alexandros, Poppe, Ronald

“…Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive…”
Get full text

Multi-Dataset, Multitask Learning of Egocentric Vision Tasks by Kapidis, Georgios, Poppe, Ronald, Veltkamp, Remco C.

“…For egocentric vision tasks such as action recognition, there is a relative scarcity of labeled data. This increases the risk of overfitting during training…”
Get full text

Can’t see the wood for the trees? An assessment of street view- and satellite-derived greenness measures in relation to mental health by Helbich, Marco, Poppe, Ronald, Oberski, Daniel, Zeylmans van Emmichoven, Maarten, Schram, Raoul

“…•Greenness from remotely-sensed and street view images were moderately associated.•Measures of greenness may capture different aspects about…”
Get full text

Incremental Few-Shot Instance Segmentation by Ganea, Dan Andrei, Boom, Bas, Poppe, Ronald

“…Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate…”
Get full text

Weighted local intensity fusion method for variational optical flow estimation by Tu, Zhigang, Poppe, Ronald, Veltkamp, Remco C.

“…Estimating a dense motion field of successive video frames is a fundamental problem in image processing. The multi-scale variational optical flow method is a…”
Get full text

A Personal Model of Trumpery: Linguistic Deception Detection in a Real-World High-Stakes Setting by Van Der Zee, Sophie, Poppe, Ronald, Havrileck, Alice, Baillon, Aurélien

“…Language use differs between truthful and deceptive statements, but not all differences are consistent across people and contexts, complicating the…”
Get full text