Flowing convnets for human pose estimation in videos
The objective of this work is human pose estimation in videos, where multiple frames are
available. We investigate a ConvNet architecture that is able to benefit from temporal context …
available. We investigate a ConvNet architecture that is able to benefit from temporal context …
Taking a deeper look at pedestrians
The only goal of the abstract is to the answer the question: why should I read this paper? In
this paper we study the use of convolutional neural networks (convnets) for the task of …
this paper we study the use of convolutional neural networks (convnets) for the task of …
Context-aware CNNs for person head detection
Person detection is a key problem for many computer vision tasks. While face detection has
reached maturity, detecting people under full variation of camera view-points, human poses …
reached maturity, detecting people under full variation of camera view-points, human poses …
Actions and attributes from wholes and parts
We investigate the importance of parts for the tasks of action and attribute classification. We
develop a part-based approach by leveraging convolutional network features inspired by …
develop a part-based approach by leveraging convolutional network features inspired by …
Poselet-based contextual rescoring for human pose estimation via pictorial structures
In this paper we propose a contextual rescoring method for predicting the position of body
parts in a human pose estimation framework. A set of poselets is incorporated in the model …
parts in a human pose estimation framework. A set of poselets is incorporated in the model …
Multisensory information processing for enhanced human-machine symbiosis
FD Gregory, L Dai - Human Interface and the Management of Information …, 2015 - Springer
Multisensory information processing is a basic feature of neural systems and has been
exploited to facilitate development of Army systems that augment Soldier performance …
exploited to facilitate development of Army systems that augment Soldier performance …
Quality scores for deep regression systems
Deep methods based on Convolutional Neural Networks serve as accurate facial points and
body parts detectors. However, most methods do not provide a confidence score for the …
body parts detectors. However, most methods do not provide a confidence score for the …
Learning visual models for person detection and action prediction
TH Vu - 2018 - inria.hal.science
Résumé In this thesis, we address person detection and action prediction in visual data. We
develop models that learn representations for visual data and the structure in the output …
develop models that learn representations for visual data and the structure in the output …
Human pose estimation using DirectionMaps
W Zhuang, S Xia, Y Wang - 2018 33rd Youth Academic Annual …, 2018 - ieeexplore.ieee.org
In this paper, we propose a novel approach to detect human pose in a wild image. The
approach uses a nonparametric representation, which we refer as DirectionMaps, to learn …
approach uses a nonparametric representation, which we refer as DirectionMaps, to learn …
Navigating information as a Cityscape
CP Rainsford, MIY Williams - Proceedings Second Australasian …, 2001 - ieeexplore.ieee.org
Recent years have seen a continued growth in the amount of information populating
information systems. Meanwhile, the proliferation of computer-based communications and …
information systems. Meanwhile, the proliferation of computer-based communications and …