Generic Videos Research Articles

Can a virtual learning module foster empathy in dental undergraduate students?

Empathy is an essential part of patient-centred health care, which positively benefits both patients and clinicians. Thereis little agreement regarding how best to design and deliver training for healthcare trainees to imparttheskills and behaviours of clinical empathy. The study aimed to inform the field by sharing an educational intervention where we aimed to improve empathy amongst dental undergraduate students in Trinity College Dublin using a virtual learning module. Adopting pre-post-repeat pre-experimental design, dental professional students completed the Jefferson Scale of Empathy (JSE) for Health Professional Students immediately prior to and after a three-week virtual programme designed to increase clinical empathy.Using a three-factor model described for the JSE in the literature, scores were evaluated for internal consistency and paired tests were performed on scores appropriate to their distributions. Seven-point Likert scales were scored to record student experience of training and technology, which are reported descriptively. Most of the 37 participants were female (76%) and represented dental science (N=27) and dental hygiene roles (N=7). Results revealed a mean JSE-HPS scale score rise from 110.0 (SD=10.4) to 116.4 (SD=11.1), which represented a rise of 5.8% (t (36)=3.6, p=0.001).The three factors associated with cognitive empathy, namely perspective-taking (T(36)=3.931, p<0.001;walking in the patient's shoes T(36)=2.093,p=0.043);and compassionate care (Z=2.469, p=0.014)were all found to have increased after the intervention.Students reported a positive experience of discipline-specific and generic videos as part of the module. The study demonstrated that a virtual educational module was associated with an increase in empathy amongst dental undergraduate students. The design ofablended module incorporatingtheMassive Open Online Course (MOOC) and virtual learning are beneficial and have a promising future.

DeepVS2.0: A Saliency-Structured Deep Learning Method for Predicting Dynamic Visual Attention

Deep neural networks (DNNs) have exhibited great success in image saliency prediction. However, few works apply DNNs to predict the saliency of generic videos. In this paper, we propose a novel DNN-based video saliency prediction method, called DeepVS2.0. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which provides sufficient data to train the DNN models for predicting video saliency. Through the statistical analysis of LEDOV, we find that human attention is normally attracted by objects, particularly moving objects or the moving parts of objects. Accordingly, we propose an object-to-motion convolutional neural network (OM-CNN) in DeepVS2.0 to learn spatio-temporal features for predicting the intra-frame saliency via exploring the information of both objectness and object motion. We further find from our database that human attention has a temporal correlation with a smooth saliency transition across video frames. Therefore, a saliency-structured convolutional long short-term memory network (SS-ConvLSTM) is developed in DeepVS2.0 to predict inter-frame saliency, using the extracted features of OM-CNN as the input. Moreover, the center-bias dropout and sparsity-weighted loss are embedded in SS-ConvLSTM, to consider the center-bias and sparsity of human attention maps. Finally, the experimental results show that our DeepVS2.0 method advances the state-of-the-art video saliency prediction.

Tablet computer-supported conversation between people with dementia and their carers: technology as interactional focus

The purpose of the study is to explore when and how technology becomes a topic in interactions involving people with dementia and their carers. Three dyads of older women with dementia and their carers participated in the study. The dyads interacted in the home environments of the persons with dementia using tablet computers and two web-based applications with generic pictures, videos, and music files (CIRCA) and personalized pictures and films (CIRCUS). The data included twenty-one video-recorded interactions. Topical episode analysis and transcripts of interaction were used to analyze and exemplify when and how technology was talked about in the dyads. The dyads were engaged in exploring the tablets, and six common ways of making technology a topic of conversation were identified: talk about tech problems, commenting actions, expressing uncertainty in navigation, instructing and explaining, expressing surprise, and talk about technical development. The dyads explored the tablets in ways that were reflected in the content of their conversations. If people with dementia and their carers should benefit from today’s technology, such as there is evidence for the interactions examined in this study, their homes and daily environments must be equipped with sufficient internet access and technical support.

Video Enhancement using Histogram Equalization with JND Model

The paper presents degraded Video contrast enhancement. These videosare taken by camera phones because of the improper illumination or limitation of the capturing devices. The existing enhancement approach may either flop to produce good and distortionless Videos. They do not enhance every area of interest properly, especially in face regions. The paperpropose histogram equalization method (HE) manipulating thenoticeable in difference model of the visual system represented as in JND-HE. This will be performed for generic frame that is contrast enhancement. In addition, the said method,JND-HE method is clubbed with the exposer correctivemethod represented by JND-HE-EC for video enhancement of face region. The EC method is to adjust the illumination of the video frame in the face region and obtain suitable illumination in the background. The demonstration result shows that generic videos and faces shallproduce pleasantvideosother than existing techniques.

Automatic analysis of broadcast football videos using contextual priors

The presence of standard video editing practices in broadcast sports videos, like football, effectively means that such videos have stronger contextual priors than most generic videos. In this paper, we show that such information can be harnessed for automatic analysis of sports videos. Specifically, given an input video, we output per-frame information about camera angles and the events (goal, foul, etc.). Our main insight is that in the presence of temporal context (camera angles) for a video, the problem of event tagging (fouls, corners, goals, etc.) can be cast as per frame multi-class classification problem. We show that even with simple classifiers like linear SVM, we get significant improvement in the event tagging task when contextual information is included. We present extensive results for 10 matches from the recently concluded Football World Cup, to demonstrate the effectiveness of our approach.

Beyond reminiscence: using generic video to elicit conversational language.

Videos and multimedia are increasingly used to stimulate reminiscence in dementia care. However, they are also valuable in eliciting a wide range of language patterns that are not necessarily keyed to reminiscence about self. Low-technology, home-made generic and personalized videos were tested with 2 samples of persons with dementia, to increase engagement and support the retention of identity. Participants showed a slight, though not significant, preference for looking first at personalized videos and produced a wider range of conversational language topics and phrasal patterns in response to the generic videos.

Background-Modeling-Based Adaptive Prediction for Surveillance Video Coding.

The exponential growth of surveillance videos presents an unprecedented challenge for high-efficiency surveillance video coding technology. Compared with the existing coding standards that were basically developed for generic videos, surveillance video coding should be designed to make the best use of the special characteristics of surveillance videos (e.g., relative static background). To do so, this paper first conducts two analyses on how to improve the background and foreground prediction efficiencies in surveillance video coding. Following the analysis results, we propose a background-modeling-based adaptive prediction (BMAP) method. In this method, all blocks to be encoded are firstly classified into three categories. Then, according to the category of each block, two novel inter predictions are selectively utilized, namely, the background reference prediction (BRP) that uses the background modeled from the original input frames as the long-term reference and the background difference prediction (BDP) that predicts the current data in the background difference domain. For background blocks, the BRP can effectively improve the prediction efficiency using the higher quality background as the reference; whereas for foreground-background-hybrid blocks, the BDP can provide a better reference after subtracting its background pixels. Experimental results show that the BMAP can achieve at least twice the compression ratio on surveillance videos as AVC (MPEG-4 Advanced Video Coding) high profile, yet with a slightly additional encoding complexity. Moreover, for the foreground coding performance, which is crucial to the subjective quality of moving objects in surveillance videos, BMAP also obtains remarkable gains over several state-of-the-art methods.

Activity-driven content adaptation for effective video summarization

In this paper, we present a novel method for content adaptation and video summarization fully implemented in compressed-domain. Firstly, summarization of generic videos is modeled as the process of extracted human objects under various activities/events. Accordingly, frames are classified into five categories via fuzzy decision including shot changes ( cut and gradual transitions), motion activities ( camera motion and object motion) and others by using two inter-frame measurements. Secondly, human objects are detected using Haar-like features. With the detected human objects and attained frame categories, activity levels for each frame are determined to adapt with video contents. Continuous frames belonging to same category are grouped to form one activity entry as content of interest (COI) which will convert the original video into a series of activities. An overall adjustable quota is used to control the size of generated summarization for efficient streaming purpose. Upon this quota, the frames selected for summarization are determined by evenly sampling the accumulated activity levels for content adaptation. Quantitative evaluations have proved the effectiveness and efficiency of our proposed approach, which provides a more flexible and general solution for this topic as domain-specific tasks such as accurate recognition of objects can be avoided.

Audio-visual atoms for generic video concept classification

We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at concept detection. We extract a novel local representation, Audio-Visual Atom (AVA), which is defined as a region track associated with regional visual features and audio onset features. We develop a hierarchical algorithm to extract visual atoms from generic videos, and locate energy onsets from the corresponding soundtrack by time-frequency analysis. Audio atoms are extracted around energy onsets. Visual and audio atoms form AVAs, based on which discriminative audio-visual codebooks are constructed for concept detection. Experiments over Kodak's consumer benchmark videos confirm the effectiveness of our approach.

Techniques for movie content analysis and skimming: tutorial and overview on video abstraction techniques

With the proliferation of digital video, video summarization and skimming has become an indispensable tool of any practical video content management system. This paper provides a tutorial on the existing abstraction work for generic videos and presents state-of-the-art techniques for feature film skimming. The paper also describes the authors' recent work on movie skimming using audiovisual tempo analysis and specific cinematic rules. With the maturity of the movie genre classification, content understanding and video abstraction techniques, an automatic movie content analysis system that facilitates navigation, browsing, and search of desired movie content is possible in the near future