Search

The limited domain generalization capability of contemporary video anomaly detection methods restricts their efficacy to specific datasets. To enhance the generalizability and portability of video anomaly detection models, we propose a domain adaptation network framework with robust generalization performance. The objective of the framework is to enable the video anomaly detection model to generalize from the source domain to the untrained target domain while mitigating the impact of missing labeled data on deep architectures. The framework incorporates a graph-based domain-invariant representation learning module and domain discriminator that enable the model to learn deep features with domain-invariant properties that remain unchanged across different domains by calculating the strength of the relationships among domain nodes. Notably, inspired by domain adversarial learning, the framework utilizes a gradient reversal layer acting on backpropagation that guides the parameters of optimal feature mapping in constructing the loss with opposing directions. To address the domain generalization problem in video anomaly detection, this framework applies graph convolution techniques. The framework leverages a novel adjacency matrix that encourages high coherence within the same domain while optimizing the mapping of low-level deep features from source to target domains to enhance the discriminative performance of the video anomaly detection model in the target domain. Simulation experiments were conducted on Avenue, UCSD-Ped1, UCSD-Ped2, ShanghaiTech, UCF-Crime, and TAD datasets, and labeled data from the source domain were utilized during the training process. Various testing results demonstrate that our framework enables models trained in one or more different scenes (domains) to perform well in unknown scenes (domains) with good cross-domain testing AUC performance. For example, in multidomain training generalization to the Avenue dataset for testing, our domain adversarial learning framework improves detection accuracy by 12.47%. Under severe single-domain generalization scenarios, the AUC performance on the target domain (e.g., UCF-Crime dataset) increase by 4.36%, 8.64%, and 3.68%, respectively. [ABSTRACT FROM AUTHOR]

Accurate mapping is crucial for the successful deployment of unmanned ground vehicles (UGVs) in navigation tasks. However, maps derived from as-designed models often lack realism and fail to reflect dynamic changes on construction sites. To address this issue, a premapping method leveraging prior construction progress video is proposed to create up-to-date navigation maps. This method proactively accounts for dynamic changes, particularly those caused by transient objects that are present only during the progress video collection phase and may not exist at the time of UGV deployment. The proposed approach involves detecting, tracking, and segmenting these transient objects, followed by their removal using a flow-guided model. The cleaned frames are used to reconstruct an updated point cloud, which serves as the basis for defining a two-dimensional (2D) navigation map. By considering these changes during the premapping process, the method ensures that the resulting map is consistent with the actual site conditions. Validation in an indoor construction setting demonstrated the necessity of the proposed method and highlighted the impacts of transient objects on path planning outcomes. This method is beneficial for routine monitoring scenarios, for which it can update and transform prior video into a navigation map, enabling efficient advanced planning. Practical Applications: The practical application of this study primarily lies in enhancing the deployment efficiency of unmanned ground vehicles for routine monitoring of construction sites. The proposed premapping method, which leverages prior construction progress video, offers two key practical benefits. Firstly, as an offsite premapping approach, it enables the creation of maps without interfering with ongoing construction activities, minimizing on-site operations. This enhances UGV acceptance on site and maintains regular site workflows. Secondly, by proactively considering the dynamic changes caused by transient objects, the method ensures that the created map is up-to-date and provides a more comprehensive basis for efficient initial planning. This premapping approach is particularly beneficial for routine monitoring scenarios, because it reduces operational efforts by providing effective and up-to-date maps derived from construction progress video. By doing so, it enhances both the efficiency of UGV deployment and the effectiveness of advanced planning in dynamic construction environments. [ABSTRACT FROM AUTHOR]

We examined the characteristics of video annotations frequently discussed during debriefing conversations as part of video-assisted coaching cycles. We also analyzed how mathematics coaches used written annotations to inject ideas into debriefing conversations when supporting teachers to reflect on important classroom events. Coaches and teachers asynchronously created the annotations based on what they noticed while watching video of an implemented lesson. Findings revealed annotations that were coach-created, focused on the teacher, contained content about goals and discourse, or contained connections were most frequently taken up during the debriefing conversation. In addition, we identified four unique ways coaches used annotation references to inject new ideas into the conversations. We present a rationale for continued research on the relationship between noticing artifacts from a lesson (i.e., video annotations) and subsequent reflective conversation between a coach and teacher. [ABSTRACT FROM AUTHOR]

This study aims to reveal how model eliciting principles are used in the process of designing, applying, and evaluating teacher candidates' model-eliciting activities. This study was conducted in three stages in a multi-tiered teaching experiment. Firstly, 15 teacher candidates designed activities for Grade 7 students after they were trained on mathematical modeling. In the second stage, these activities were performed with Grade 7 students and video recorded. In the third stage, teacher candidates watched the videos and evaluated how model-eliciting principles were executed during instruction and revise their activities. To collect data, we used focus group interviews with teacher candidates, field notes, and reports. The findings revealed the two principles of reality and model construction to be at the fore during the design stage. The teacher candidates who watched the application videos found some problems in the principles of 'reality' 'self-assessment' and 'model generalization'. Teacher candidates following the applications, for the new design, offered recommendations for 'reality' and 'model construction' principles although the other principles were somewhat neglected. They did express that by making the proper arrangements to the learning environment, students would be able to acquire the other principles over time. [ABSTRACT FROM AUTHOR]

Convolutional neural network-based image style transfer models often suffer from temporal inconsistency when applied to video. Although several video style transfer models have been proposed to improve temporal consistency, they often trade off processing speed, perceptual style quality, and temporal consistency. In this work, we propose a novel approach for fast continuous patch-based arbitrary video style transfer that achieves high-quality transfer results while maintaining temporal coherence. Our approach begins with stylizing the first frame as a standalone single image using patch propagation within the content activation. Subsequent frames are computed based on the key insight that optical flow field evaluated from neighboring content activations provides meaningful information to preserve temporal coherence efficiently. To address the problems introduced from optical flow stage, we additionally incorporate a correction procedure as a post-process to ensure a high-quality stylized video. Finally, we demonstrate our method can transfer arbitrary styles on a set of examples and illustrate that our approach exhibits superior performance both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

When photographing through a piece of glass, reflections usually degrade the quality of captured images or videos. In this paper, by exploiting periodically varying light flickering, we investigate the problem of removing strong reflections from contaminated image sequences or videos with a unified capturing setup. We propose a learning-based method that utilizes short-term and long-term observations of mixture videos to exploit one-side contextual clues in fluctuant components and brightness-consistent clues in consistent components for achieving layer separation and flickering removal, respectively. A dataset containing synthetic and real mixture videos with light flickering is built for network training and testing. The effectiveness of the proposed method is demonstrated by the comprehensive evaluation on synthetic and real data, the application for video flickering removal, and the exploratory experiment on high-speed scenes. [ABSTRACT FROM AUTHOR]

Video sequences exhibit significant nuisance variations (undesired effects) of speed of actions, temporal locations, and subjects' poses, leading to temporal-viewpoint misalignment when comparing two sets of frames or evaluating the similarity of two sequences. Thus, we propose Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE) for sequence pairs. In particular, we focus on 3D skeleton sequences whose camera and subjects' poses can be easily manipulated in 3D. We evaluate JEANIE on skeletal Few-shot Action Recognition (FSAR), where matching well temporal blocks (temporal chunks that make up a sequence) of support-query sequence pairs (by factoring out nuisance variations) is essential due to limited samples of novel classes. Given a query sequence, we create its several views by simulating several camera locations. For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW). Specifically, each support temporal block can be matched to the query temporal block with the same or adjacent (next) temporal index, and adjacent camera views to achieve joint local temporal-viewpoint warping. JEANIE selects the smallest distance among matching paths with different temporal-viewpoint warping patterns, an advantage over DTW which only performs temporal alignment. We also propose an unsupervised FSAR akin to clustering of sequences with JEANIE as a distance measure. JEANIE achieves state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II on supervised and unsupervised FSAR, and their meta-learning inspired fusion. [ABSTRACT FROM AUTHOR]

Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. The previous methods typically follow the tracking-by-match paradigm and develop sophisticated pipelines, which is an not effective solution. In this paper, rooted in Transformer sequence modeling, we propose a simple, yet effective end-to-end trainable video text DEtection, Tracking, and Recognition framework (TransDeTR), which views the VTS task as a direct long-range temporal modeling problem. TransDeTR mainly includes two advantages: (1) Different from the explicit match paradigm in the adjacent frame, the proposed TransDeTR tracks and recognizes each text implicitly by the different query termed 'text query' over long-range temporal sequence (more than 7 frames). (2) TransDeTR is the first end-to-end trainable video text spotting framework, which simultaneously addresses the three sub-tasks (e.g., text detection, tracking, recognition). Extensive experiments on four video text datasets (e.g., ICDAR2013 Video, ICDAR2015 Video) are conducted to demonstrate that TransDeTR achieves state-of-the-art performance with up to 11.0 % improvements on detection, tracking, and spotting tasks. Code can be found at: https://github.com/weijiawu/TransDETR. [ABSTRACT FROM AUTHOR]

The task of few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. How to better describe the action in each video and how to compare the similarity between videos are two of the most critical factors in this task. Directly describing the video globally or by its individual frames cannot well represent the spatiotemporal dependencies within an action. On the other hand, naively matching the global representations of two videos is also not optimal since action can happen at different locations in a video with different speeds. In this work, we propose a novel approach that describes each video using multiple types of prototypes and then computes the video similarity with a particular matching strategy for each type of prototypes. To better model the spatiotemporal dependency, we describe the video by generating prototypes that model the multi-level spatiotemporal relations via transformers. There are a total of three types of prototypes. The first type of prototypes are trained to describe specific aspects of the action in the video e.g., the start of the action, regardless of its timestamp. These prototypes are directly matched one-to-one between two videos to compare their similarity. The second type of prototypes are the timestamp-centered prototypes that are trained to focus on specific timestamps of the video. To deal with the temporal variation of actions in a video, we apply bipartite matching to allow the matching of prototypes of different timestamps. The third type of prototypes are generated from the timestamp-centered prototypes, which regularize their temporal consistency while serving as an auxiliary summarization of the whole video. Experiments demonstrate that our proposed method achieves state-of-the-art results on multiple benchmarks. [ABSTRACT FROM AUTHOR]

This study aims to develop a predictive model for predicting gifted students' engagement levels and to investigate the features that are important in such predictions. Features reflecting students' emotions, social-emotional learning skills, learning approaches and video-watching behaviours were used in the prediction models. The study group consisted of 36 gifted students between the ages of 12 and 14 who attended an information technologies course, where students engaged with Arduino-based learning tasks. Data related to only one task were analysed. Prediction models were developed using different machine learning algorithms, and information gain scores were used to investigate important features in the prediction models. The results show that all prediction models achieved a higher classification accuracy than the base model. The highest classification accuracy (83%) was achieved with the Support Vector Machine (SVM) algorithm. Students' self-reported emotions while performing the task were found to be the most important feature in predicting their level of engagement. Other important features in predicting engagement level were the students' social-emotional learning skills, deep and surface learning approaches and their video-watching behaviours. As a result, it was found that the engagement level of gifted students could be predicted with high accuracy. These results can be used to predict students' engagement levels and to develop interventions for low-engaged students. The obtained results are discussed within the scope of emotion-aware learning design and social-emotional learning. [ABSTRACT FROM AUTHOR]

Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing. Past efforts have invariantly involved training summarization models with annotated summaries or heuristic objectives. In this work, we reveal that features pre-trained on image-level tasks contain rich semantic information that can be readily leveraged to quantify frame-level importance for zero-shot video summarization. Leveraging pre-trained features and contrastive learning, we propose three metrics featuring a desirable keyframe: local dissimilarity, global consistency, and uniqueness. We show that the metrics can well-capture the diversity and representativeness of frames commonly used for the unsupervised generation of video summaries, demonstrating competitive or better performance compared to past methods when no training is needed. We further propose a contrastive learning-based pre-training strategy on unlabeled videos to enhance the quality of the proposed metrics and, thus, improve the evaluated performance on the public benchmarks TVSum and SumMe. [ABSTRACT FROM AUTHOR]

Due to the side effects of AI recommendation algorithms, there is a risk of users experiencing trauma when watching accident videos on video platforms. However, regulatory standards for accident videos are inadequate. This paper proposes a detection system that integrates four accident categories to effectively detect and regulate accident videos that can cause trauma on platforms like YouTube. The proposed system includes CNN-based fire and flood detection models, a two-stream learning-based violence detection model, and a YOLOv4-based car crash detection method. The fire, flood, and violence detection models achieved accuracies of 95%, 96%, and 97%, respectively, while the car crash detection method achieved a detection rate of 97.1% and a false alarm rate of 2.86%. This study aims to contribute to preventing user trauma and creating a safer media environment by detecting accident videos, which are not covered by existing regulations. [ABSTRACT FROM AUTHOR]

Temporal sentence grounding in videos (TSGV) aims to retrieve video segments from untrimmed videos that semantically matched a given query. Although existing methods have made significant progress in fine-grained intra- and inter-modal representations, they failed to comprehensively consider the redundancy of the entire video relative to the target segment and the fact that interactions could obscure crucial intra-modal information, which leads to the degradation of model performance. In this paper, we proposed a novel Parameterized Multi-Perspective Graph Learning Network for Temporal Sentence Grounding in Videos. Specifically, to effectively handle redundant information in video graphs, the concept of a parameterized network is introduced to dynamically construct new video graphs. Parameterizing the graph structure, making it adaptable to various video scenes while suppressing unnecessary redundant information. Furthermore, we designed a dual-path attention gating module that delves into cross-modal relationships while fully considering intra-modal information. The mechanism simultaneously considers the association between video and query from both inter- and intra-modal perspectives. This method allowed the model to better balance the local and global semantic consistency, further enhancing its representation capability for multimodal data. Extensive experiments on the ActivityNet Captions and Tacos benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Video‐sharing platforms commonly implement ad‐revenue‐sharing programs to incentivize UGC creators. This paper constructs a game‐theoretic model to examine a creator's optimal decisions on video‐generation and program‐participation. Results show that participating in the ad‐revenue‐sharing program is not always beneficial to creators. Creators with small follower sizes and moderate creation efficiency may experience reduced payoff when participating in that program because of the resultant substantial decrease in the promotion effort offered by the platform. Moreover, the ad‐revenue‐sharing program is not always effective in motivating creators to engage in video generation or incentivizing creators to improve the quality of their videos. [ABSTRACT FROM AUTHOR]

The human visual system can rapidly focus on prominent objects in complex scenes, significantly enhancing information processing efficiency. Salient object detection (SOD) mimics this biological ability, aiming to identify and segment the most prominent regions or objects in images or videos. This reduces the amount of data needed to process while enhancing the accuracy and efficiency of information extraction. In recent years, SOD has made significant progress in many areas such as deep learning, multi-modal fusion, and attention mechanisms. Additionally, it has expanded in real-time detection, weakly supervised learning, and cross-domain applications. Depth images can provide three-dimensional structural information of a scene, aiding in a more accurate understanding of object shapes and distances. In SOD tasks, depth images enhance detection accuracy and robustness by providing additional geometric information. This additional information is particularly crucial in complex scenes and occlusion situations. This survey reviews the substantial advancements in the field of RGB-Depth SOD, with a focus on the critical roles played by attention mechanisms and cross-modal fusion methods. It summarizes the existing literature, provides a brief overview of mainstream datasets and evaluation metrics, and quantitatively compares the discussed models. [ABSTRACT FROM AUTHOR]

Objective This study aimed to review literature from the past five years, focusing on the use of educational videos as a guidance tool for parents and guardians of children with lip and palate clefts. Source of data Conducted between April and July 2022, this integrative literature review was framed around the question: 'What is the evidence regarding the use of videos in health education for parents/guardians of children with cleft lip and palate? PICO strategy was used to develop the research. A literature search was undertaken across PubMed, Web of Science, Scopus, and the Virtual Health Library databases. Of the eight articles included in this review, four were sourced from the PubMed database, with three published in 2021. Summary of the findings The findings indicated that YouTube videos were moderately satisfactory and met the needs of parents or legal guardians to a partial extent. The majority of the videos analyzed in this review were characterized by a moderate level of informational content. One study particularly underscored that the content of these videos only partially satisfies the requirements of the parents or legal guardians of the children. Conclusions Nevertheless, such videos are considered viable alternatives for health education, offering numerous benefits yet facing challenges, primarily due to the scarcity of information on orofacial malformations. [ABSTRACT FROM AUTHOR]

Copyright of Canadian Journal of Anaesthesia / Journal Canadien d'Anesthésie is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Multimedia material, such as digital video, is utilized to conceal a secret message. Given the features of digital video, which has a large storage capacity, confidential data may be inserted. Three requirements must satisfy to grantee secure steganography system. These requirements include security, robustness, and imperceptibility. This paper proposes a steganography scheme to enhance the security of video steganography and attempt to meet the three requirements mentioned above. The security requirement is accomplished through two levels. In the first level, the secret message is encrypted before the embedding process using proposed encryption method based on a combination of chaotic and Arnold's map. In the second level, the secret message is embedded in the selected frames of the video. Instead of traditional LSB technique, we will use a modified LSB technique to meet the robustness requirement. A modified LSB technique is satisfied by embedding the secret message in the LSB of cover video in frequency domain after applying the integer wavelet transform (IWT). According to the experimental results, the stego video quality is like the original video where the obtained PSNR value was 61.922, so the third requirement, imperceptibility, was satisfied. [ABSTRACT FROM AUTHOR]

People with visual impairments faced great challenges during the COVID-19 pandemic, including a great sense of loneliness, negative feelings, and misinformation concerning the disease. This study describes and discusses the process of creating audio-visual content about vaccination against COVID-19 by and for teenagers with visual impairments. We carried out two working groups with students aged 14–18 years, who were enrolled in a school for the blind and visually impaired in Rio de Janeiro, Brazil. During meetings with these groups, we had informal conversations about how they experienced the pandemic. They then watched and evaluated videos related to COVID-19 vaccines and wrote scripts for animated videos on the importance of COVID-19 vaccination. The videos were produced by a specialized company, and the students evaluated the final product. The participants seemed to be well informed about the health crisis and were aware of the scientific recommendations. As a result, the two videos contained relevant information about COVID-19 vaccines and were intended to encourage different audiences to be vaccinated. Participants also prepared audio descriptions for the videos, which gave them the opportunity to discuss future job careers. The outcomes of activities designed according to participants' experiences and needs offered tangible evidence that meaningful activities have positive impacts on students' learning, as well as on their self-esteem. [ABSTRACT FROM AUTHOR]

Copyright of Bagcilar Medical Bulletin / Bağcılar Tıp Bülteni is the property of Galenos Yayinevi Tic. LTD. STI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Although we encounter objects from a particular perspective, what we perceive and remember are typically whole objects. In 'amodal completion' our mind automatically fills in objects' spatially occluded parts, and our memory then often discards information about the orientation from which the objects were perceived. An analogous phenomenon of 'event completion' has been demonstrated, which may be understood as the mind automatically filling in temporally occluded parts of events. Exemplifying typical experiments in this paradigm, Strickland and Keil (Strickland and Keil, Cognition 121:409–415, 2011) showed participants videos depicting a causal event (e.g., someone kicking a ball), which was edited so that a crucial part was missing (e.g., the moment of contact between foot and ball). Subjects were more likely to falsely remember having seen the moment of contact if (and only if) it was strongly implied by subsequent footage. We use this phenomenon of event completion as a test case for comparing different theories of reference in memory. We argue that event completion puts pressure on both pure causal and pure descriptive theories of reference, and favors more nuanced hybrids of causal and descriptive theories, which integrate insights from cognitive and epistemic approaches. [ABSTRACT FROM AUTHOR]

Current video generation models usually convert signals indicating appearance and motion received from inputs (e.g., image and text) or latent spaces (e.g., noise vectors) into consecutive frames, fulfilling a stochastic generation process for the uncertainty introduced by latent code sampling. However, this generation pattern lacks deterministic constraints for both appearance and motion, leading to uncontrollable and undesirable outcomes. To this end, we propose a new task called Text-driven Video Prediction (TVP). Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. Specifically, appearance and motion components are provided by the image and caption separately. The key to addressing the TVP task depends on fully exploring the underlying motion information in text descriptions, thus facilitating plausible video generation. In fact, this task is intrinsically a cause-and-effect problem, as the text content directly influences the motion changes of frames. To investigate the capability of text in causal inference for progressive motion information, our TVP framework contains a Text Inference Module (TIM), producing step-wise embeddings to regulate motion inference for subsequent frames. In particular, a refinement mechanism incorporating global motion semantics guarantees coherent generation. Extensive experiments are conducted on Something-Something V2 and Single Moving MNIST datasets. Experimental results demonstrate that our model achieves better results over other baselines, verifying the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

With the growing applications of video, ensuring its security has become of utmost importance. Selective encryption (SE) has gained significant attention in the field of video content protection due to its compatibility with video codecs, favorable visual distortion, and low time complexity. However, few studies consider SE security under cryptographic attacks. To fill this gap, we analyze the security concerns of encrypted bitstreams by SE schemes and propose two known plaintext attacks (KPAs). Then the corresponding defense is presented against the KPAs. To validate the effectiveness of the KPA, it is applied to attack two existing SE schemes with superior visual degradation in HEVC videos. Firstly, the video sequences are encoded using H.265/HEVC. During encoding, the selected syntax elements are recorded. Secondly, the recorded syntax elements are imported into the HEVC decoder. By utilizing the encryption parameters and the imported data in the decoder, it becomes possible to reconstruct a significant portion of the original syntax elements before encryption. Finally, the reconstructed syntax elements are compared with the encrypted syntax elements in the decoder, allowing the design of a pseudo-key stream (PKS) through the inverse of the encryption operations. The PKS is used to decrypt the existing SE scheme, and the experimental results provide evidence that the two existing SE schemes are vulnerable to the proposed KPAs. In the case of single bitstream estimation (SBE), the average correct rate of key stream estimation exceeds 93%. Moreover, with multi-bitstream complementation (MBC), the average estimation accuracy can be further improved to 99%. [ABSTRACT FROM AUTHOR]

We live in a world filled with never-ending streams of multimodal information. As a more natural recording of the real scenario, long form audio-visual videos (LFAVs) are expected as an important bridge for better exploring and understanding the world. In this article, we propose the multisensory temporal event localization task in long form videos and strive to tackle the associated challenges. To facilitate this study, we first collect a large-scale LFAV dataset with 5,175 videos and an average video length of 210 seconds. Each collected video is elaborately annotated with diversified modality-aware events, in a long-range temporal sequence. We then propose an event-centric framework for localizing multisensory events as well as understanding their relations in long form videos. It includes three phases in different levels: snippet prediction phase to learn snippet features, event extraction phase to extract event-level features, and event interaction phase to study event relations. Experiments demonstrate that the proposed method, utilizing the new LFAV dataset, exhibits considerable effectiveness in localizing multiple modality-aware events within long form videos. We hope that our newly collected dataset and novel approach serve as a cornerstone for furthering research in the realm of LFAV understanding. Project page: https://gewu-lab.github.io/LFAV/. [ABSTRACT FROM AUTHOR]

Smartphones have emerged as ubiquitous platforms for people to consume content in a wide range of consumption contexts (C2), e.g., over cellular or WiFi, playing back audio and video directly on phone or through peripheral devices such as external screens or speakers. In this article, we argue that a user's specific C2 is an important factor to consider in Adaptive Bitrate (ABR) streaming. We examine the current practices of using C2 in five popular ABR players, and identify various limitations in existing treatments that have a detrimental impact on network resource usage and user experience. We then formulate C2-cognizant ABR streaming as an optimization problem and develop practical best-practice guidelines to realize it. Instantiating these guidelines, we develop a proof-of-concept implementation in the widely used state-of-the-art ExoPlayer platform and demonstrate that it leads to significantly better tradeoffs in terms of user experience and resource usage. Last, we show that the guidelines also benefit dash.js player that uses an ABR logic significantly different from that of ExoPlayer. [ABSTRACT FROM AUTHOR]

Action segmentation consists of temporally segmenting a video and labeling each segmented interval with a specific action label. In this work, we propose a novel action segmentation method that requires no initial video analysis and no annotated data. Our proposal involves extracting features from videos using several pre-trained deep-learning models, including spatiotemporal and self-supervised methods. Data is then transformed using a positional encoder, and finally, a clustering algorithm is applied, where each produced cluster presumably corresponds to a different single and distinguishable action. For self-supervised features, we explored DINO, and for spatiotemporal features, we investigated I3D and SlowFast methods. Moreover, two different clustering algorithms (FINCH and KMeans) were investigated, and we also explored how varying the length of video snippets that generate the feature vectors affected the quality of the segmentation. Experiments show that our method produces competitive results on the Breakfast and INRIA Instructional Videos dataset benchmarks. Our best result was produced using a composition of self-supervised features generated by DINO, FINCH clustering, and positional encoding. [ABSTRACT FROM AUTHOR]

Widely adopted digital cameras and smartphones have generated a large number of videos, which have brought a tremendous workload to video editors. Recently, a variety of automatic/semi-automatic video editing methods have been proposed to tackle these issues in some specific areas. However, for the production of meeting recordings, the existing studies highly depend on extra equipment in the conference venues, such as the infrared camera or special microphone, which are not practical. In this article, we design and implement Meetor, a human-centered automatic video editing system for meeting recordings. The Meetor mainly contains three parts: an audio-based video synchronization algorithm, human-centered video content flaw detection algorithms, and an automatic video editing algorithm. Two main experiments are conducted from both objective and subjective aspects to evaluate the performance of the Meetor. The experimental results on a testbed illustrate that the proposed algorithms could achieve state-of-the-art (SOTA) performance in video content flaw detection. However, the conducted user study demonstrates that Meetor could generate meeting recordings with a satisfactory quality compared with professional video editors. Moreover, we also present a practical application of the Meetor in a university campus prototype, in which the Meetor is applied in the automatic editing of lecture recordings. All in all, the proposed Meetor can be utilized in practical applications to release the workload of professional video editors. [ABSTRACT FROM AUTHOR]

Video-based services have become popular. Clients often outsource their videos to the cloud to relieve local maintenance. However, privacy has become a major concern, since many videos contain sensitive information. Although retrieving (unencrypted) videos has been extensively investigated, retrieving encrypted multimedia has received relatively rare attention, at best in a limitation of image-based similarity searches. We initiate the study of scalable encrypted video search, enabling clients to query videos similar to an image search. Our modular framework leverages intrinsic attributes of videos, such as semantics and visuals, to effectively capture their contents. We propose a two-step approach whereby lightweight searchable encryption techniques are used for pre-screening, followed by an interactive approach for fine-grained search. Furthermore, we present three instantiations, including one centralized-writer instantiation and two distributed-writer instantiations, to effectively cater to varying needs and scenarios: (1) The centralized one employs forward and backward private searchable encryption [CCS 2017] over deep hashing [CVPR 2020]. (2) Motivated by distributed computing, the multi-writer instantiations building atop HSE [Usenix Security 2022] allows searching the relevant videos contributed by multiple intuitions collaboratively. Our experimental results illustrate their practical performance over multiple real-world datasets, whether in a centralized setting or distributed setting. [ABSTRACT FROM AUTHOR]

Drawing on Stanley Fish's concept of interpretive communities, this article explores the various transcultural interpretations of queer opacity, a Chinese variant of queerness within dan'gai web series. This study reveals that while viewers employ a shared interpretive strategy of queer reading to identify queer opacity, the effect of queer interpretation is contingent upon the queer interpretive subcommunities' familiarity with Chinese culture. Moreover, different cultures possess sub-strategies of queer reading: visibility reading is often practiced in the global northwest to initiate visibility politics in society, while opacity reading is used in the global southeast in an unconfrontational manner within fictional worlds. By examining a layered interpretive phenomenon that involves transcultural reaction videos towards the Chinese dan'gai web series The Untamed (TU), alongside the danmu from Chinese viewers on these videos, this study contributes to scholarship on transcultural queerness through the lenses of queer opacity and transcultural reader reception. [ABSTRACT FROM AUTHOR]

Abstract Background The internet is a common source of health information for patients and caregivers. To date, content and information quality of YouTube videos on sarcoidosis has not been studied. The aim of our study was to investigate the content and quality of information on sarcoidosis provided by YouTube videos. Methods Of the first 200 results under the search term “sarcoidosis,” all English-language videos with content directed at patients were included. Two independent investigators assessed the content of the videos based on 25 predefined key features (content score with 0–25 points), as well as reliability and quality (HONCode score with 0–8 points, DISCERN score with 1–5 points). Misinformation contained in the videos was described qualitatively. Results The majority of the 85 included videos were from an academic or governmental source (n = 63, 74%), and median time since upload was 33 months (IQR 10–55). Median video duration was 8 min (IQR 3–13) and had a median of 2,044 views (IQR 504 − 13,203). Quality assessment suggested partially sufficient information: mean HONCode score was 4.4 (SD 0.9) with 91% of videos having a medium quality HONCode evaluation. Mean DISCERN score was 2.3 (SD 0.5). Video content was generally poor with a mean of 10.5 points (SD 0.6). Frequently absent key features included information on the course of disease (6%), presence of substantial geographical variation (7%), and importance of screening for extrapulmonary manifestations (11%). HONCode scores were higher in videos from academic or governmental sources (p = 0.003), particularly regarding “transparency of sponsorship” (p

Objective: This study aimed to review literature from the past five years, focusing on the use of educational videos as a guidance tool for parents and guardians of children with lip and palate clefts. Source of data: Conducted between April and July 2022, this integrative literature review was framed around the question: 'What is the evidence regarding the use of videos in health education for parents/guardians of children with cleft lip and palate? PICO strategy was used to develop the research. A literature search was undertaken across PubMed, Web of Science, Scopus, and the Virtual Health Library databases. Of the eight articles included in this review, four were sourced from the PubMed database, with three published in 2021. Summary of the findings: The findings indicated that YouTube videos were moderately satisfactory and met the needs of parents or legal guardians to a partial extent. The majority of the videos analyzed in this review were characterized by a moderate level of informational content. One study particularly underscored that the content of these videos only partially satisfies the requirements of the parents or legal guardians of the children. Conclusions: Nevertheless, such videos are considered viable alternatives for health education, offering numerous benefits yet facing challenges, primarily due to the scarcity of information on orofacial malformations.

The authors posit that in an initial exposure to a broadcast video, hearing different voices narrate (in succession) a persuasive message encourages consumers' attention and processing of the message, thereby facilitating persuasion; this is referred to as the voice numerosity effect. Across four studies (plus validation and replication studies)—including two large-scale, real-world data sets (with more than 11,000 crowdfunding videos and over 3.6 million customer transactions, and more than 1,600 video ads) and two controlled experiments (with over 1,800 participants)—the results provide support for the hypothesized effect. The effect (1) has consequential, economic implications in a real-world marketplace, (2) is more pronounced when the message is easier to comprehend, (3) is more pronounced when consumers have the capacity to process the ad message, and (4) is mediated by the favorability of consumers' cognitive responses. The authors demonstrate the use of machine learning, text mining, and natural language processing to process and analyze unstructured (multimedia) data. Theoretical and marketing implications are discussed. [ABSTRACT FROM AUTHOR]

This study examines the results of the first phase of a multi-year programme to integrate the use of video to support induction coaches in a suburban school district. Seven coaches participated in a video club in which they analysed videos of both their coaching conversations and mentees' classrooms. A typological analysis of interview and video club meeting transcripts revealed perceived benefits of participation in the video club on the coaches' sense of professional community and the quality of coaching conversations. Coaches also noted reviewing video with mentees stimulated changes in their mentees' classroom practice. Positioning themselves as learners learning from video alongside mentees created a more egalitarian relationship between coach and mentee. The 'pragmatic' professional development design privileged coaches' autonomy and agency and emphasised developing coaching concepts rather than discrete routines. Obstacles to using video included logistical issues related to video capture as well as the time needed to establish trusting relationships with mentees. Further exploration of the video club model for teacher leader development will inform theories of teacher learning and professional development design. [ABSTRACT FROM AUTHOR]

Background: When watching educational online videos, learners need to determine whether the videos' contents are suitable for learning. Whereas this may induce metacognitive monitoring processes, it may also distract learners from the learning materials. Objectives: In the current set of experiments, we investigated whether asking participants to rate the suitability of three educational videos to impart knowledge (both experiments) and enabling participants to pause the video (Experiment 2) affects learning. Methods: Experiment 1 was conducted in the laboratory with a sample of university students. Participants were randomly assigned to one of two experimental conditions (rating task vs. viewing task). Experiment 2 was conducted online. Participants were randomly assigned to one of four conditions resulting from the two factors task (rating task vs. viewing task) and pause button (available vs. not available). Results and Conclusion: In Experiment 1, we observed detrimental effects of the rating task on learning outcomes, but more accurate judgements of learning. In Experiment 2, we did not find any effects of the rating task on learning outcomes and the accuracy of the participants' judgements of learning. However, the inclusion of a pause button did result in more accurate judgements of learning. Further, exploratory analyses revealed that older participants reported higher levels of intrinsic and germane cognitive load than the younger participants. This increased effort only translated into better learning outcomes in the condition in that participants could pause the video. Thus, age is introduced as a potential boundary condition that should be investigated in instructional design research. Lay Description: What is currently known about the subject matter?: Metacognitive monitoring and control are important for learning.It is yet unknown whether rating videos' suitability to convey knowledge affects metacognitive monitoring and learning.Pause buttons in dynamic presentations may facilitate learning.Researchers argue that available pause buttons help learners to avoid cognitive overload and induce monitoring processes. What this paper adds?: We investigated whether a task to rate videos' suitability to convey knowledge and the availability of a pause button improve metacognitive monitoring and learning outcomes.Whereas the rating task increased the accuracy of participants' judgements of learning but decreased learning outcomes in Experiment 1, there were no effects of the rating task in Experiment 2.The availability of a pause button benefitted learning outcomes for older participants, but not for younger participants.The pause button increased the accuracy of participants' judgements of learning independent of age. Implications of study findings for practitioners: Rating the suitability of learning materials to impart knowledge should be disentangled from the actual learning phase.It is useful to consider potential learners' age when applying instructional design principles. [ABSTRACT FROM AUTHOR]

In this article, we introduce a nonconvex tensor recovery approach, which employs the powerful ket augmentation technique to expand a low order tensor into a high‐order one so that we can exploit the advantage of tensor train (TT) decomposition tailored for high‐order tensors. Moreover, we define a new nonconvex surrogate function to approximate the tensor rank, and develop an auto‐weighted mechanism to adjust the weights of the resulting high‐order tensor's TT ranks. To make our approach robust, we add two mode‐unfolding regularization terms to enhance the model for the purpose of exploring spatio‐temporal continuity and self‐similarity of the underlying tensors. Also, we propose an implementable algorithm to solve the proposed optimization model in the sense that each subproblem enjoys a closed‐form solution. A series of numerical results demonstrate that our approach works well on recovering color images and videos. [ABSTRACT FROM AUTHOR]

Stories sometimes move us; this study examined the factors that strengthen the perception of core values based on the core value goodness hypothesis of being moved. Focusing on the infinity of core values, we hypothesised that the reaffirmation of the finite nature of human beings would emphasise core values. This study examined the factors that promote being moved: finitude salience and value orientation. The participants responded to a family value scale. Subsequently, a descrambling task to manipulate finitude salience was used. The participants composed sentences such as "Everything that exists in this world is finite" and primed finitude. Subsequently, they watched a video on the theme of family love and rated their feelings. From the results, we found that (a) the participants oriented towards the value themed in the video (i.e., love) were more strongly moved by it; and (b) when finitude was salient, people oriented towards the themed value in the video were moved more strongly by it than those who were not. This suggests that the feeling of being moved occurs when we recognise an infinite core value, in contrast to our finite existence. [ABSTRACT FROM AUTHOR]

Perceptual training enhances the ability to anticipate crucial information for decision‐making, for example, a soccer goalkeeper predicting penalty kick direction. However, it remains unclear whether perceptual practice alone (implicit method) is sufficient for optimal decision‐making improvement, or whether emphasising pertinent details during practice (explicit method) could yield better results. This study compared implicit and explicit methods of learning ball direction prediction during soccer penalties, involving both goalkeepers and non‐soccer players (novices). Participants engaged in a single training session, either through the explicit method (watching videos highlighting relevant information) or implicit method (watching regular videos). Specialised software was used to display penalty kick videos, mimicking the goalkeeper's viewpoint up to 200 ms before ball contact, and measuring reaction time and response choice. Both implicit and explicit training led to consistent performance gains for goalkeepers and novices alike, notably enhancing ball direction prediction accuracy. Reaction time was unaffected by training. This suggests that both explicit and implicit training methods exhibit similar effectiveness, applicable to soccer goalkeepers and novices. [ABSTRACT FROM AUTHOR]