Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

Human Activity Recognition (HAR) is an active research area due to its applications in pervasive computing, human-computer interaction, artificial intelligence, health care, and social sciences. Moreover, dynamic environments and anthropometric differences between individuals make it harder to recognize actions. This study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world applications. It uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural network. Moreover, the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification information. Six state-of-the-art pre-trained models are exploited to find the best model for spatial feature extraction. For temporal sequence, this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short Term Memory (BiLSTM) to capture long-term dependencies. Two state-of-the-art datasets, UCF101 and HMDB51, are used for evaluation purposes. In addition, seven state-of-the-art optimizers are used to fine-tune the proposed network parameters. Furthermore, this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network (CNN), where two streams use RGB data. In contrast, the other uses optical flow images. Finally, the proposed ensemble approach using max hard voting outperforms state-of-the-art methods with 96.30% and 90.07% accuracies on the UCF101 and HMDB51 datasets.     

ManiWordle: providing flexible control over Wordle

Among the multifarious tag-clouding techniques, Wordle stands out to the community by providing an aesthetic layout, eliciting the emergence of the participatory culture and usage of tag-clouding in the artistic creations. In this paper, we introduce ManiWordle, a Wordle-based visualization tool that revamps interactions with the layout by supporting custom manipulations. ManiWordle allows people to manipulate typography, color, and composition not only for the layout as a whole, but also for the individual words, enabling them to have better control over the layout result. We first describe our design rationale along with the interaction techniques for tweaking the layout. We then present the results both from the preliminary usability study and from the comparative study between ManiWordle and Wordle. The results suggest that ManiWordle provides higher user satisfaction and an efficient method of creating the desired "art work," harnessing the power behind the ever-increasing popularity of Wordle.     

Driving Automotive User Interface Research

Cars offer an interesting but challenging microcosm for pervasive computing research and, in particular, for interaction with pervasive computing systems. Increasingly, researchers are looking at interactive applications in the car and investigating human-car interaction from a computer science—rather than an ergonomics or mechanical engineering—perspective. This article reports on the International Conference on Automotive User Interfaces and Interactive Vehicular Applications, wherein participants shared presentations on topics such as aesthetics, user interaction and distraction, safety, and driver monitoring.     

Underdetermined Convolutive Blind Source Separation via Time–Frequency Masking

In this paper, we consider the problem of separation of unknown number of sources from their underdetermined convolutive mixtures via time-frequency (TF) masking. We propose two algorithms, one for the estimation of the masks which are to be applied to the mixture in the TF domain for the separation of signals in the frequency domain, and the other for solving the permutation problem. The algorithm for mask estimation is based on the concept of angles in complex vector space. Unlike the previously reported methods, the algorithm does not require any estimation of the mixing matrix or the source positions for mask estimation. The algorithm clusters the mixture samples in the TF domain based on the Hermitian angle between the sample vector and a reference vector using the well known k -means or fuzzy c -means clustering algorithms. The membership functions so obtained from the clustering algorithms are directly used as the masks. The algorithm for solving the permutation problem clusters the estimated masks by using k-means clustering of small groups of nearby masks with overlap. The effectiveness of the algorithm in separating the sources, including collinear sources, from their underdetermined convolutive mixtures obtained in a real room environment, is demonstrated.     

Principles and typical computational limitations of sparse speaker separation based on deterministic speech features

The separation of mixed auditory signals into their sources is an eminent neuroscience and engineering challenge. We reveal the principles underlying a deterministic, neural network-like solution to this problem. This approach is orthogonal to ICA/PCA that views the signal constituents as independent realizations of random processes. We demonstrate exemplarily that in the absence of salient frequency modulations, the decomposition of speech signals into local cosine packets allows for a sparse, noise-robust speaker separation. As the main result, we present analytical limitations inherent in the approach, where we propose strategies of how to deal with this situation. Our results offer new perspectives toward efficient noise cleaning and auditory signal separation and provide a new perspective of how the brain might achieve these tasks.     

Individual,social, and organizational contexts for active knowledge sharing in communities of practice

Firms that have implemented knowledge management initiatives are now interested in nurturing voluntary knowledge sharing organizations, called communities of practice (CoPs). Adopting the Triandis model on attitude formation, we identified and validated a set of organizational factors that was anticipated to have effects on knowledge sharing by CoP members such as perceived consequences, affect, social factors and facilitating conditions. One hundred and seventy-nine members from 70 CoPs of a large multinational electronics firm participated in this survey. Based on the PLS analysis, perceived consequences, affect, social factors, and facilitating conditions were found to significantly affect knowledge sharing in CoPs.     

Leveraging online communities in fostering adaptive schools

There has long been a call for schools to prepare students for the twenty-first century where skills and dispositions differ significantly from much of what has historically characterized formal education. The knowledge based economy calls for policy and pedagogical efforts that would transform schools. Schools are to foster communities of learners. This paper suggests that para-communities may be points of leverage in the fostering of adaptive schools. A critical analysis is done on the differences between para-communities (such as online communities) and schools; and an argument is made that they each serve differing goals and should be left distinct because they achieve different societal and economic demands.