Search

What drives the liking of video advertisements? The authors analyzed neural signals during ad exposure from three functional magnetic resonance imaging (fMRI) data sets (113 participants from two countries watching 85 video ads) with automated meta-analytic decoding (Neurosynth). These brain-based measures of psychological processes—including perception and language (information processing), executive function and memory (cognitive functions), and social cognition and emotion (social-affective response)—predicted subsequent self-report ad liking, with emotion and memory being the earliest predictors after the first three seconds. Over the span of ad exposure, while the predictiveness of emotion peaked early and fell, that of social cognition had a peak-and-stable pattern, followed by a late peak of predictiveness in perception and executive function. At the aggregate level, neural signals—especially those associated with social-affective response—improved the prediction of out-of-sample ad liking compared with traditional anatomically based neuroimaging analysis and self-report liking. Finally, early-onset social-affective response predicted population ad liking in a behavioral replication. Overall, this study helps delineate the psychological mechanisms underlying ad processing and ad liking and proposes a novel neuroscience-based approach for generating psychological insights and improving out-of-sample predictions. [ABSTRACT FROM AUTHOR]

As social media influencer endorsement gains significance in marketing communication, an increasing number of influencers have started to incorporate product information into their sponsored content. This study examines the effectiveness of product attribute description in the context of sponsored videos. Using a field dataset of 598 sponsored videos, we demonstrate that influencers' use of product attribute description as an endorsement strategy has a negative impact on video engagement, and this effect is stronger for trial versus awareness campaigns. However, the negative impact is reversed to a positive one when product attribute description is employed for utilitarian products but not for hedonic products. These results reveal that the effectiveness of product attribute description depends on the nature of the product and the campaign objectives. Overall, this study contributes to the understanding of influencer marketing effectiveness and sheds light on the nuances of endorsement strategies. Practical implications on how to optimise endorsement effectiveness and video performance are discussed. [ABSTRACT FROM AUTHOR]

The purpose of this study was to assess the immediate effect of video feedback on the regulation and control of the standing back tuck somersault in the absence of vision. Two groups of male parkour athletes performed the standing back tuck somersault under both open and closed eyes conditions. The first group received video feedback, while the second group received verbal feedback. Concurrent analysis, including kinetic data from a force plate (Kistler Quattro-Jump) and kinematic data in two-dimensional by Kinovea freeware, was employed for motion and technical performance analysis. The results indicate that the loss of vision during the standing back tuck somersault affected only the take-off and ungrouping angle, as well as the vertical velocity and displacement. These effects were consistent regardless of the type of feedback provided (i.e., video feedback or verbal feedback). Furthermore, a significant Vision × Feedback interaction was observed at the level of technical performance. This suggests that the use of video feedback enabled the parkour athletes to maintain a high level of technical performance both with and without vision (i.e., 13.56 vs. 13.00 points, respectively, p >.05 and d = 2.233). However, the verbal feedback group technical performance declined significantly under the no-vision condition compared with the vision condition (13.14 vs. 10.25 points, respectively, with and without vision, p <.001 and d = 2.382). We concluded that when the movement is proprioceptively controlled (i.e., without vision), the video feedback enables the athletes to globally assess the technical deficiencies arising from the lack of vision and to correct them. These findings are discussed based on parkour athletes' ability to evaluate the kinematic parameters of the movement. [ABSTRACT FROM AUTHOR]

Although in-stream video advertising is common, its effects on advertisement (ad) information encoding remain unclear. We investigated the effects of in-stream video advertising by comparing two groups: those watching mid-roll (between the program) ads and those watching pre- and post-roll (before and after the program, respectively) ads. To elucidate how advertising content is encoded in the context of in-stream video advertising, we integrated two theoretical frameworks: the negative emotion–memory model (NEMM) and the limited capacity model of motivated–mediated message processing (LC4MP). We used electroencephalography (EEG) to assess negative emotions and bottom-up attention during advertisement viewing. The findings indicate that the first mid-roll ad induced negative emotions, but these feelings were attenuated during subsequent mid-rolls. In addition, negative emotions induced by mid-roll ads attenuated the role of bottom-up attention in the information encoding process. However, the pre- and post-roll ads were not accompanied by negative emotions; thus, bottom-up attention played a major role in the information encoding of these ads. The results also suggest that despite the negative emotions experienced during mid-rolls, such transient negative reactions did not affect purchase intention for the advertised products. [ABSTRACT FROM AUTHOR]

This research examines when and how the speed of video ads influences consumers' perceptions of luxuriousness and their subsequent behaviors toward products or brands featured in the ads. Across 12 experiments (total N = 27,227, five preregistered), the authors demonstrate that when a video ad depicts a product in slow motion (vs. regular speed), consumers perceive the featured product or brand as more luxurious. The effect emerges across various product categories (chocolate, shampoo, mineral water, wine) and in different countries (United States, United Kingdom, France). Tests of mediation and moderation suggest that the effect occurs because viewing a slow-motion ad increases feelings of immersion, which lead consumers to expect greater hedonic value from the featured product and thus view it as more luxurious. Consistent with this account, the effect weakens when video blurriness or buffering impairs the immersive viewing experience afforded by slow motion, and the effect attenuates among consumers who are very weakly or very strongly predisposed to experience immersion. Finally, by enhancing perceptions of luxuriousness, slow motion subsequently boosts consumers' desire for the featured product or brand (as manifested by higher willingness to pay, purchase intentions, and ad click rates), particularly when the goal to consume luxury is salient (vs. not). [ABSTRACT FROM AUTHOR]

This paper describes the SocialVidStim-a database of video stimuli available to the scientific community depicting positive and negative social evaluative and neutral statements. The SocialVidStim comprises 53 diverse individuals reflecting the demographic makeup of the USA, ranging from 9 to 41 years old, saying 20-60 positive and 20-60 negative social evaluative statements (e.g. 'You are a very trustworthy/annoying person'), and 20-60 neutral statements (e.g. 'The sky is blue'), totaling 5793 videos post-production. The SocialVidStim are designed for use in behavioral and functional magetic resonance imaging paradigms, across developmental stages, in diverse populations. This study describes stimuli development and reports initial validity and reliability data on a subset videos (N = 1890) depicting individuals aged 18-41 years. Raters perceive videos as expected: positive videos elicit positively valenced ratings, negative videos elicit negatively valenced ratings and neutral videos are rated as neutral. Test-retest reliability data demonstrate intraclass correlations in the good-to-excellent range for negative and positive videos and the moderate range for neutral videos. We also report small effects on valence and arousal that should be considered during stimuli selection, including match between rater and actor sex and actor believability. The SocialVidStim is a resource for researchers and we offer suggestions for using the SocialVidStim in future research.

Existing video instance segmentation (VIS) approaches generally follow a closed-world assumption, where only seen category instances are identified and spatio-temporally segmented at inference. Open-world formulation relaxes the close-world static-learning assumption as follows: (a) first, it distinguishes a set of known categories as well as labels an unknown object as 'unknown' and then (b) it incrementally learns the class of an unknown as and when the corresponding semantic labels become available. We propose the first open-world VIS approach, named OW-VISFormer, that introduces a novel feature enrichment mechanism and a spatio-temporal objectness (STO) module. The feature enrichment mechanism based on a light-weight auxiliary network aims at accurate pixel-level (unknown) object delineation from the background as well as distinguishing category-specific known semantic classes. The STO module strives to generate instance-level pseudo-labels by enhancing the foreground activations through a contrastive loss. Moreover, we also introduce an extensive experimental protocol to measure the characteristics of OW-VIS. Our OW-VISFormer performs favorably against a solid baseline in OW-VIS setting. Further, we evaluate our contributions in the standard fully-supervised VIS setting by integrating them into the recent SeqFormer, achieving an absolute gain of 1.6% AP on Youtube-VIS 2019 val. set. Lastly, we show the generalizability of our contributions for the open-world detection (OWOD) setting, outperforming the best existing OWOD method in the literature. Code, models along with OW-VIS splits are available at https://github.com/OmkarThawakar/OWVISFormer. [ABSTRACT FROM AUTHOR]

This paper presents research on a posthumanist approach for reframing community-engaged pedagogy. We employ posthumanist theory as a way to examine the educational possibilities of ethically engaging with technologies and materials as a means to build and sustain community partnerships for social justice. This research project employs a diffractive inquiry involving interview encounters with 20 college writing instructors. The posthumanist approach presented in this paper provides a window into understanding how a myriad of human-material assemblages, response-able designs, and affective encounters shape and transform community-engaged pedagogy. In the context of community-engaged writing, the posthumanist approach oftentimes coincides with the use of multiple modes of communication, such as text, image, sound, and video, to foreground marginalized communities and their perspectives. Through allowing for the expression of multiple voices and perspectives, including those of non-human entities, this approach further challenges and disrupts traditional human-centric and dualistic views of community-engaged pedagogy. [ABSTRACT FROM AUTHOR]

Vision-based reinforcement learning (RL) is a generalizable way to control an agent because it is agnostic of specific hardware configurations. As visual observations are highly entangled, attempts for vision-based RL rely on scene representation that discerns individual entities and establishes intuitive physics to constitute the world model. However, most existing works on scene representation learning cannot successfully be deployed to train an RL agent, as they are often highly unstable and fail to sustain for a long enough temporal horizon. We propose ASIMO, a fully unsupervised scene decomposition to perform interaction-rich tasks with a vision-based RL agent. ASIMO decomposes agent-object interaction videos of episodic-length into the agent, objects, and background, predicting their long-term interactions. Further, we explicitly model possible occlusion in the image observations and stably track individual objects. Then, we can correctly deduce the updated positions of individual entities in response to the agent action, only from partial visual observation. Based on the stable entity-wise decomposition and temporal prediction, we formulate a hierarchical framework to train the RL agent that focuses on the context around the object of interest. We demonstrate that our formulation for scene representation can be universally deployed to train different configurations of agents and accomplish several tasks that involve pushing, arranging, and placing multiple rigid objects. [ABSTRACT FROM AUTHOR]

• Parents submitted YouTube videos recently viewed by their children aged 0 to 8. • In-depth educational videos were rare, yet problematic depictions were common. • Parents reported that children experienced many positive responses from viewing. • Positive responses included feelings of joy and strengthened social bonds. • Some viewing patterns varied by age. Guided by uses and gratifications theory, the current project invited parents (N = 358) to submit YouTube videos (N = 973) recently viewed by their children aged 0 to 8. Parents rated each video for its perceived impact on their child, while coders evaluated each video for its content. Results indicated that in-depth educational lessons were rare in these videos, and potentially harmful depictions were common (e.g., physical aggression). Despite these issues, parents reported that these videos often evoked children's joy, fostered social bonding, and allowed children to explore niche interests. Some patterns varied by age, such that older (vs. younger) children viewed fewer educational videos, and they experienced fewer emotional gratifications from viewing. However, older children also viewed more videos with peers, and parents reported that those experiences facilitated peer bonding. Collectively, these findings replicate some concerning patterns found in previous research while also hinting at positive aspects of YouTube exposure that are neglected in discourse about children's experiences online. [ABSTRACT FROM AUTHOR]

The rapid development of short video platforms poses new challenges for traditional recommendation systems. Recommender systems typically depend on two types of user behavior feedback to construct user interest profiles: explicit feedback (interactive behavior), which significantly influences users' short-term interests, and implicit feedback (viewing time), which substantially affects their long-term interests. However, the previous model fails to distinguish between these two feedback methods, leading it to predict only the overall preferences of users based on extensive historical behavior sequences. Consequently, it cannot differentiate between users' long-term and short-term interests, resulting in low accuracy in describing users' interest states and predicting the evolution of their interests. This paper introduces a video recommendation model called CAT-MF Rec (Cross Attention Transformer-Mixed Feedback Recommendation) designed to differentiate between explicit and implicit user feedback within the DIEN (Deep Interest Evolution Network) framework. This study emphasizes the separate learning of the two types of behavioral feedback, effectively integrating them through the cross-attention mechanism. Additionally, it leverages the long sequence dependence capabilities of Transformer technology to accurately construct user interest profiles and predict the evolution of user interests. Experimental results indicate that CAT-MF Rec significantly outperforms existing recommendation methods across various performance indicators. This advancement offers new theoretical and practical insights for the development of video recommendations, particularly in addressing complex and dynamic user behavior patterns. [ABSTRACT FROM AUTHOR]

This study examines the influence of title length and the number of words in titles on the view counts of YouTube videos, with a focus on optimizing title characteristics to enhance viewer engagement. Using a dataset of 12,466 Microsoft Excel tutorial videos published between January 2006 and November 2023, the analysis identifies significant patterns in title characteristics that affect viewership. The results reveal a bell-shaped relationship, with both mean and median view counts peaking at specific title lengths and word counts, emphasizing the importance of striking a balance between informativeness and brevity. Furthermore, the study highlights the critical role of visual information (character count) compared to semantic information (word count) in driving video engagement. By providing actionable insights, this research offers practical, costefficient guidelines for creators to optimize their video titles, ultimately contributing to more effective content strategies on digital platforms. [ABSTRACT FROM AUTHOR]

Video forgery detection is crucial to combat misleading content, ensuring trust and credibility. Existing methods encounter challenges such as diverse manipulation techniques, dataset variation, real-time processing demands, and maintaining a balance between false positives and negatives. The research focuses on leveraging a Two-Layer Hybridized Deep CNN classifier for the detection of video forgery. The primary objective is to enhance accuracy and efficiency in identifying manipulated content. The process commences with the collection of input data from a video database, followed by diligent data pre-processing to mitigate noise and inconsistencies. To streamline computational complexity, the research employs key frame extraction to select pivotal frames from the video. Subsequently, these key frames undergo YCrCb conversion to establish feature maps, a step that optimizes subsequent analysis. These feature maps then serve as the basis for extracting significant features, incorporating Haralick features, Local Ternary Pattern, Scale-Invariant Feature Transform (SIFT), and light coefficient features. This multifaceted approach empowers robust forgery detection. The detection is done using the proposed Two-Layer Hybridized Deep CNN classifier that identifies the forged image. The outputs are measured using accuracy, sensitivity, specificity and the proposed Two-Layer Hybridized Deep CNN achieved 96.76%, 96.67%, 96.21% for dataset 1, 96.56%, 96.79%, 96.61% for dataset 2, 95.25%, 95.76%, 95.58% for dataset 3, which is more efficient than other techniques. [ABSTRACT FROM AUTHOR]

There is a growing interest in understanding the factors that influence a user's perception and preferences for video quality. This study specifically focuses on how various factors, including video content, display settings, viewer characteristics, and the ambient environment, affect the subjective video quality assessment (VQA) of TV displays. To investigate these factors, two psychophysical experiments were conducted, and the results indicate that all four factors have a significant impact on video quality perception in different ways. This study is beneficial for researchers and developers who aim to improve display and environmental settings to provide viewers with the best possible viewing experience. [ABSTRACT FROM AUTHOR]

Video has become a widespread tool for capturing naturalistic behavioral data. While mixed methods show great potential in understanding the active nature of children's interaction, only a few studies have developed mixed methods for video-based interaction research. This paper presents a mixed methods embodied interaction model appropriate for studying complex embodied interaction and draws on methodological insights from a mixed methods project to capture changes in children's interaction with touchscreen technologies. The paper details how integrated mixed methods analysis was needed to fully explain the results and how mono-method studies would provide misleading results. The theoretical advancements generated during the project illustrate how mixed methods for video-based studies have valuable properties for understanding complex interactional phenomena, such as learning. [ABSTRACT FROM AUTHOR]

As a key technical equipment for improving coal quality, efficiency and promoting clean and efficient utilization, it is important for vibrating screens to detect their faults quickly and accurately. Traditional vibrating screen fault detection methods usually rely on the vibration signals collected by sensors, and identify the faults through spectral analysis, time domain feature extraction, etc. However, these methods face the problems of inaccurate detection, insufficient real-time performance and poor adaptability to environmental changes under complex working conditions. To address this limitation, this paper proposes a video frame prediction model, DST-UNet, to detect the operation of vibrating screens through video. The model combines convolutional units with different kernel sizes to simultaneously extract local detail information and global structural information in the operation of vibrating screens; uses ECA as a temporal attention mechanism to improve the model’s understanding and sensitivity to temporal sequences and employs convolutional units to generate spatio-temporal weights to dynamically fuse spatial and temporal features. In addition, an evaluation metric MTR is proposed to assess the model performance. The experimental results show that, compared with models such as SimVP, 3D convolution and PredRNN, the method improves the sensitivity, accuracy and processing speed of fault detection while reducing the model complexity and can realize efficient detection with limited data sets, which helps to identify equipment faults quickly and reduce the risk of damage. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusion Laparoscopic cholecystectomy is one of the most commonly performed surgeries worldwide. With the rise of online platforms like YouTube and WebSurg, surgical videos have become popular educational tools. However, the quality of these videos varies, raising concerns about their reliability. This study evaluates the changes in the quality of laparoscopic cholecystectomy videos over two decades and compares the educational value of YouTube and WebSurg videos.Twenty‐four videos were analyzed and divided into four groups: older YouTube, older WebSurg, newer YouTube, and newer WebSurg. Six videos from each group were selected based on relevance and popularity. Three independent surgeons assessed them using standardized scoring systems, including the JAMA Benchmark Score, Global Quality Score (GQS), LAP‐VEGaS, and a new Laparoscopic Cholecystectomy‐Specific Score (LAP Chole‐SS). Video characteristics such as duration, uploader type, and viewer engagement were also considered. Statistical comparisons were made between the groups.The analysis showed that although newer videos were longer, the difference was not statistically significant (P = 0.74). Newer videos had significantly better image quality (P < 0.001). WebSurg videos consistently outperformed YouTube videos across all evaluation criteria. WebSurg scored higher in the JAMA Benchmark (2.62 versus 1.66), GQS (3.58 versus 2.63), LAP‐VEGaS (13.7 versus 6.58), and LAP Chole‐SS (4.08 versus 2.33).In conclusion, WebSurg provides higher‐quality, peer‐reviewed content, making it more reliable for surgical education, while YouTube offers accessibility but often lacks educational rigor. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) 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.)

In video encoding rate control, adaptive selection of the initial quantization parameter (QP) is a critical factor affecting both encoding quality and rate control precision. Due to the diversity of video content and the dynamic nature of network conditions, accurately and efficiently determining the initial QP remains a significant challenge. The optimal setting of the initial QP not only influences bitrate allocation strategies but also impacts the encoding efficiency and output quality of the encoder. To address this issue in the H.266/VVC standard, this paper proposes a novel hierarchical reinforcement learning-based method for adaptive initial QP selection. The proposed method introduces a hierarchical reinforcement learning framework that decomposes the initial QP selection task into high-level and low-level strategies, handling coarse-grained and fine-grained QP decisions, respectively. The high-level strategy quickly determines a rough QP range based on global video features and network conditions, while the low-level strategy refines the specific QP value within this range to enhance decision accuracy. This framework integrates spatiotemporal video complexity, network conditions, and rate control objectives to form an optimized model for adaptive initial QP selection. Experimental results demonstrate that the proposed method significantly improves encoding quality and rate control accuracy compared to traditional methods, confirming its effectiveness in handling complex video content and dynamic network environments. [ABSTRACT FROM AUTHOR]

Short video applications are popular nowadays. Typically, a short video may be played for a few seconds or swiped away by users at any time. Due to this uncertain user behavior, video chunks should be preloaded to ensure a smooth viewing process for users. In other words, the short video preloading scheme is crucial to the quality of experience (QoE) of users and revenue. Specifically, the short video preloading scheme should determine which video chunk to download, when to download it, and at what bitrate. Existing schemes either fail to consider all these factors together or find it hard to make the best decision. In this work, we argue that the selection of downloaded video chunks is the foremost task due to the uncertain user behaviors and the corresponding huge number of possible playing sequences of video chunks. As a step further, we propose the playing time-aware chunk selection (PaCs) scheme, which downloads the video chunk with the smallest expected playing time first. After the selection of the video chunk, the bitrate is selected according to the classic MPC algorithm and then whether the downloading process is paused or executed is discussed. In total, PaCs can improve the score consisting of the QoE of downloaded video chunks and the utilized network bandwidth under different conditions. Simulations confirm that PaCs achieves a higher score than the existing scheme Dashlet proposed in NSDI 2024. [ABSTRACT FROM AUTHOR]

We report the case of DT, a man in his fifties who suffered a large right fronto-parietal hemorrhage, resulting in a dense left weakness and a persistent anosognosia for the resultant hemiplegia. DT engaged in several video-feedback sessions. Video feedback therapy has been successful in previously reported cases of anosognosia, resulting in immediate and lasting resolution. In the current case, similarly dramatic effects were observed, but with a subsequent recurrence of the anosognosic ideation. The present case sheds light on the interplay of neurologic and psychological mechanisms involved in anosognosia and on some of the pragmatic emotional considerations of engaging in this form of rehabilitative therapy. [ABSTRACT FROM AUTHOR]

This study analyses the use of TikTok by Spanish universities as an institutional communication tool, focusing on viral trends and their impact on engagement. From the 60 universities with a presence on TikTok, the 10 with the highest engagement were selected for a content analysis (N = 100) of their most popular videos. A mixed methodology, combining deductive and inductive coding, was used to classify content types and measure engagement rates. The results highlight the effectiveness of short videos aligned with viral trends. [ABSTRACT FROM AUTHOR]

This study presents a detailed characterization of iterative steganography, a unique class of information-hiding techniques, and proposes a formal mathematical model for their description. A novel quantitative measure, the Incremental Information Function (IIF), is introduced to evaluate the process of information gain in iterative steganographic methods. The IIF offers a comprehensive framework for analyzing the step-by-step process of embedding information into a cover medium, focusing on the cumulative effects of each iteration in the encoding and decoding cycles. The practical application and efficacy of the proposed method are demonstrated using detailed case studies in video steganography. These examples highlight the utility of the IIF in delineating the properties and characteristics of iterative steganographic techniques. The findings reveal that the IIF effectively captures the incremental nature of information embedding and serves as a valuable tool for assessing the robustness and capacity of steganographic systems. This research provides significant insights into the field of information hiding, particularly in the development and evaluation of advanced steganographic methods. The IIF emerges as an innovative and practical analytical tool for researchers, offering a quantitative approach to understanding and optimizing iterative steganographic techniques. [ABSTRACT FROM AUTHOR]

In recent years, the rapid growth of video data posed challenges for storage and transmission. Video compression techniques provided a viable solution to this problem. In this study, we proposed a bidirectional coding video compression model named DeepBiVC, which was based on two-stage learning. Firstly, we conducted preprocessing on the video data by segmenting the video flow into groups of continuous image frames, with each group comprising five frames. Then, in the first stage, we developed an image compression module based on an invertible neural network (INN) model to compress the first and last frames of each group. In the second stage, we designed a video compression module that compressed the intermediate frames using bidirectional optical flow estimation. Experimental results indicated that DeepBiVC outperformed other state-of-the-art video compression methods regarding PSNR and MS-SSIM metrics. Specifically, on the VUG dataset at bpp = 0.3, DeepBiVC achieved a PSNR of 37.16 and an MS-SSIM of 0.98. [ABSTRACT FROM AUTHOR]

Moving object detection (MOD) plays an important role in many applications that aim to identify regions of interest in videos. However, most existing MOD methods ignore the variability brought by time-varying information. Additionally, many network frameworks primarily focus on low-level feature learning, neglecting the higher-level contextual understanding required for accurate detection. To solve the above issues, we propose a symmetric Dynamic-Aware Network (DAN) for MOD. DAN explores the interactions between different types of information via structural design and feature optimization. To locate the object position quickly, we build a Siamese convolutional network to emphasize changes in the scene. Subsequently, a Change-Aware Module (CAM) is designed, which can maximize the perception of object change cues by exploiting complementary depth-varying features and different levels of disparity information, thereby enhancing the feature discrimination capability of the network. Moreover, to reinforce the effective transfer between features, we devise a Motion-Attentive Selection Module (MASM) to construct an autonomous decoder for augmenting detail representation. Experimental results on benchmark datasets indicate the rationality and validity of the proposed approach. [ABSTRACT FROM AUTHOR]

Video moment retrieval as a downstream task relies on the ability of pre trained models to extract features. Recent studies have shown that image-language pre-training models represented by CLIP (comparative language-image pre-training) have learned effective and universal semantic knowledge on large-scale datasets, thus demonstrating strong transfer and zero- shot capabilities in tasks such as image classification. However, its transfer to video retrieval tasks still yields poor results. This paper proposed a video moment retrieval network (VMRNet) to solve the above problem's. It was based on CLIP pre- trained models with a video temporal enhancement module (VTEMo) to enhance the CLIP model's temporal modeling ability and cross-modal interaction ability. VTEMo adopted a bypass hierarchical structure and introduced visual prompts guided by query text to guide the visual encoder to learn the current query task concerned visual and temporal information. Conducting validation experiments on commonly used datasets such as QVHighlights and Charades STA, VMRNet's R1@0.5 metric increased by 0.83 and 1.27 on the two datasets respectively, demonstrating its overall performance superiority over other representative models. The experimental results fully demonstrate that the proposed VTEMo can effectively learn video visual and temporal features under the guidance of query text and VMRNet combined with VTEMo can achieve better performance in video temporal retrieval tasks. [ABSTRACT FROM AUTHOR]

Filmmaking is an inherently practical area of study. Not all students can access film school because of monetary, location and health issues. Options without schooling are online in the form of tutorial videos. 360° video offers a more interactive approach than traditional learning tools, and the technology can enhance learning and promote self-guided learning. Using constructivist grounded theory methodology through cyclic testing of mixed method data collection via six participant survey rounds, 360° video content was created and hosted on the online hub (). A technical workflow was developed to show that 360° technology can aid practical filmmaking study. Filmmaking students, alumni, academics, technical staff, and professionals tested the videos and found them to be interesting, informative, and immersive. Audio, direction, and video elements were found to be important. One 360° video has the potential for freedom of learning through unique viewpoints while reducing creator costs. Short five-minute videos can provide an accessible learning method for those with disabilities, with no barriers towards gender or ethnicity. The freedom to navigate the videos empowers the learner, enhancing their self-guided learning skills. The bridge between traditional and online learning can be opened using 360° video. [ABSTRACT FROM AUTHOR]

Early video processing tools present a compelling perspective through which to reconsider the integrated practice of Tokyo-based early video artist Nakajima Kō. The author examines Nakajima's practice through his concepts of animation, the development of his Animaker (1979) and Aniputer (1982), and his perspective on how video connects to Esoteric Buddhist thought. Concluding with Kō's 1986 video Mt. Fuji, the author illustrates how the work is representative of the hybrid, analog-digital view of video that leads Nakajima to posit video as a cosmic medium circa 1986. [ABSTRACT FROM AUTHOR]

Temporal action detection, a critical task in video activity understanding, is typically divided into two stages: proposal generation and classification. However, most existing methods overlook the importance of information transfer among proposals during classification, often treating each proposal in isolation, which hampers accurate label prediction. In this article, we propose a novel method for inferring semantic relationships both within and between action proposals, guiding the fusion of action proposal features accordingly. Building on this approach, we introduce the Proposal Semantic Relationship Graph Network (PSRGN), an end-to-end model that leverages intra-proposal semantic relationship graphs to extract cross-scale temporal context and an inter-proposal semantic relationship graph to incorporate complementary neighboring information, significantly improving proposal feature quality and overall detection performance. This is the first method to apply graph structure learning in temporal action detection, adaptively constructing the inter-proposal semantic graph. Extensive experiments on two datasets demonstrate the effectiveness of our approach, achieving state-of-the-art (SOTA). Code and results are available at http://github.com/Riiick2011/PSRGN. [ABSTRACT FROM AUTHOR]

Even if the scene before our eyes remains static for some time, we might explore it differently compared with how we examine static images, which are commonly used in studies on visual attention. Here we show experimentally that the top-down expectation of changes in natural scenes causes clearly distinguishable gaze behavior for visually identical scenes. We present free-viewing eye-tracking data of 20 healthy adults on a new video dataset of natural scenes, each mapped for its potential for change (PfC) in independent ratings. Observers looking at frozen videos looked significantly more often at the parts of the scene with a high PfC compared with static images, with substantially higher interobserver coherence. This viewing difference peaked right before a potential movement onset. Established concepts like object animacy or salience alone could not explain this finding. Images thus conceal experience-based expectations that affect gaze behavior in the potentially dynamic real world. [ABSTRACT FROM AUTHOR]

Tool use has been observed in over two dozen families of birds, though few wild birds outside of corvids have been observed using tools in acts of agonism; we present additional accounts of this behavior in both corvids and cardinals. On 9 June 2023 we observed and video-recorded a male Northern Cardinal (Cardinalis cardinalis) repeatedly pick up a pebble and strike the side-view mirror of a vehicle in a parking lot at Great Smoky Mountains National Park, Tennessee, USA. We searched YouTube and found several videos of wild birds attacking their reflection in a mirror or window. None appeared to use a pebble or other weapon to attack, but a White-winged Chough (Corcorax melanorhamphos) used a pebble to strike the windshield of a vehicle and a Common Raven (Corvus corvax) dropped a stone on a domestic dog. We interpret our observation as indicating tool use by a Northern Cardinal, one of the few accounts outside of corvids of a bird using a tool in an act of agonism. We also show that online videos can help researchers detect novel behaviors, including tool use and tooling, in wild birds. [ABSTRACT FROM AUTHOR]

In formal educational settings, such as online university lectures, instructional videos often consist of PowerPoint slides accompanied by a video or audio explanation from the instructor. It has been assumed that the social cues provided by the instructor's video may facilitate affective processes and affect learning outcomes. Research on instructor presence in instructional videos has focused primarily on laboratory and online studies that are not embedded in the courses in which learners are enrolled. Therefore, we present three field studies examining instructor presence in instructional videos embedded in higher education courses to strengthen external validity (exam-relevant topic, > 30 min long, personally known instructor). The results of these studies show positive effects of a visible instructor compared to no visible instructor on some affective measures: social presence in Study 1 (n = 18, d =.85) and well-being in Study 3 (n = 38, d = 1.01), but not on others (well-being in Studies 1 & 2 (n = 53); motivation in Studies 1–3, social presence in Studies 2 & 3). They also show no effects on extraneous processing or learning outcomes (Studies 1–3). Thus, no general effect of instructor presence can be shown for instructional videos embedded in university courses in higher education, but there are also no detrimental effects. This leads to implications for future research, teaching, and design practice. [ABSTRACT FROM AUTHOR]

A series of animations, videos and 3D models that were developed, filmed or built to teach the symmetry properties of crystals are described. At first, these resources were designed for graduate students taking a basic crystallography course, coming from different careers, at the National Autonomous University of Mexico. However, the COVID‐19 pandemic had the effect of accelerating the generation of didactic material. Besides our experience with postgraduate students, we have noted that 3D models attract the attention of children, and therefore we believe that these models are particularly useful for teaching children about the assembled arrangements of crystal structures. [ABSTRACT FROM AUTHOR]

Gastroesophageal reflux disease (GERD) is a global chronic disease. Short video platforms make it easy for patients with GERD to obtain medical information. However, the quality of information from these videos remains uncertain. This study aimed to systematically assess videos related to GERD on TikTok and Bilibili. We conducted a search and gathered 241 Chinese videos related to GERD and recorded the essential information. Two independent evaluators assessed each video based on the completeness of six components of the GERD guidelines, and assessed the quality and reliability of the information in the videos using recognition tools. Finally, videos from different sources were compared. The uploaders of most videos were medical professionals (86.7%, n = 209). The content was mainly about symptoms and treatment. The quality of the videos information varied depending on the sources. Among videos posted on Bilibili, those posted by medical professionals had a lower content score for definition (P  < 0.001). Videos produced by non-gastroenterologists had the highest mean modified DISCERN. (The DISCERN scoring tool was initially created for assessing written publications, but nowadays, it is frequently leveraged for appraising various health-related videos. Details can be found in the text) quality of the videos information was acceptable; however, the content varied significantly depending on the type of source used. Videos with broad content should be carefully screened to meet more needs. [ABSTRACT FROM AUTHOR]

Animation of hand‐drawn sketches is an adorable art. It allows the animator to generate animations with expressive freedom and requires significant expertise. In this work, we introduce a novel sketch animation framework designed to address inherent challenges, such as motion extraction, motion transfer, and occlusion. The framework takes an exemplar video input featuring a moving object and utilizes a robust motion transfer technique to animate the input sketch. We show comparative evaluations that demonstrate the superior performance of our method over existing sketch animation techniques. Notably, our approach exhibits a higher level of user accessibility in contrast to conventional sketch‐based animation systems, positioning it as a promising contributor to the field of sketch animation. https://graphics-research-group.github.io/SketchAnim/ [ABSTRACT FROM AUTHOR]

In recent years, deep-learning-based visual object tracking has obtained promising results. However, a drastic performance drop is observed when transferring a pre-trained model to changing weather conditions, such as hazy imaging scenarios, where the data distribution differs from that of a natural training set. This problem challenges the open-world practical applications of accurate target tracking. In principle, visual tracking performance relies on the discriminative degree of features between the target and its surroundings, rather than the image-level visual quality. To this end, we design a feature restoration transformer that adaptively enhances the representation capability of the extracted visual features for robust tracking in both natural and hazy scenarios. Specifically, a feature restoration transformer is constructed with dedicated self-attention hierarchies for the refinement of potentially contaminated deep feature maps. We endow the feature extraction process with a refinement mechanism typically for hazy imaging scenarios, establishing a tracking system that is robust against foggy videos. In essence, the feature restoration transformer is jointly trained with a Siamese tracking transformer. Intuitively, the supervision for learning discriminative and salient features is facilitated by the entire restoration tracking system. The experimental results obtained on hazy imaging scenarios demonstrate the merits and superiority of the proposed restoration tracking system, with complementary restoration power to image-level dehazing. In addition, consistent advantages of our design can be observed when generalised to different video attributes, demonstrating its capacity to deal with open-world scenarios. [ABSTRACT FROM AUTHOR]

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video. [ABSTRACT FROM AUTHOR]

Restoring clear frames from rainy videos poses a significant challenge due to the swift motion of rain streaks. Traditional frame-based visual sensors, which record dense scene content synchronously, struggle to capture the fast-moving rain information. Conversely, the novel bio-inspired event camera, known for its high temporal resolution and low latency, effectively records the motion trajectories of rapidly falling rain through asynchronously generated sparse event sequences. In light of these attributes, we introduce a novel event-driven convolutional spiking network for video deraining. For video restoration, we employ a Convolutional Neural Network as the backbone, extracting dense features from video sequences to map rain-soaked frames to clear ones. To remove rain, we meticulously design a bio-inspired Spiking Neural Network that adapts to the sparse event sequences, capturing features of falling rain. We then establish a bimodal feature fusion module that combines dense convolutional features with sparse spiking features. This fusion aids the backbone in accurately pinpointing rain streaks across spatiotemporal dimensions. Thus, our diverse network extracts and collaborates information from both events and videos, enhancing deraining performance. Experiments conducted on synthetic and real-world datasets prove that our network markedly surpasses existing video deraining techniques. [ABSTRACT FROM AUTHOR]

Our paper presents an adaptive multiscale retinex algorithm and a new wavelet energy metric to improve low-light video captured on mobile devices. Initially, we extract RGB frames from the video and convert them to hue-saturation-value (HSV) format, preserving the hue channel to prevent common RGB colour shifting issues. Saturation channel enhancement is achieved through histogram equalization (HE), extending the dynamic range. The adaptive retinex algorithm enhances the value channel, quantified by our new wavelet energy metric. Combining the modified value and saturation channels improves the contrast of the reconstructed image. As a final step, we transform the HSV video back to RGB and restore naturalness using a modified colour restoration technique. The proposed approach has been tested on over 300 images and videos. It is evident from the experimental results presented that the proposed method lowers noise and halo artifacts more effectively than existing methods. [ABSTRACT FROM AUTHOR]

The anomaly or abnormality detection in crowded scenes helps in identifying the violence and protecting the people from severe damage. Thus, there is a need to detect the anomalies with the classifier for learning information along with the usage of huge architectures. A new anomaly detection model is implemented in this model. The collected data is fed to optimal ensemble pattern extraction scheme through techniques like Local binary patterns (LBP), Local Gradient Pattern (LGP), and Local Tetra Pattern (LTrP). The weights are tuned by a new hybrid Spiral Search-based Black Widow Glowworm Swarm Optimization (SS-BWGSO) for getting the optimal ensemble patterns. Next, anomaly frame classification is carried out by optimized VGG16+ResNet technique, where the hyperparameters of VGG16 and ResNet are tuned by SS-BWGSO algorithm. Finally, anomaly detection is performed by the YOLOV3 classifier. Throughout the result analysis the higher performance of the designed technique is observed over the classical methods. [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]

Recently, Siamese network based approaches show promising results on visual object tracking. These methods typically handle the tracking task by per-frame object detection and thus fail to fully exploit the rich temporal contexts among successive frames, which are important for accurate and robust object tracking. To benefit from the temporal information, in this paper, we investigate a per-clip tracking scheme in the Siamese-based approach and present a novel spatio-temporal SiamFC method for high-performance visual tracking. More specifically, we incorporate a non-local 3D fully convolutional network into a Siamese framework, which allows the model to act directly on the inputs of multiple templates and search video clips and to extract features from both spatial and temporal dimensions, thereby capturing the temporal information encoded in multiple video frames. We then propose a multi-template matching module to learn a representative tracking model using spatio-temporal template features and propagate informative target cues from the template set to the search clip using attention, which facilitate the object searching in clips. During inference, we employ a confident search region cropping and a dynamic multi-template update mechanism for stable and robust per-clip tracking. Experiments on six benchmark datasets show that our spatio-temporal SiamFC achieves competitive performance compared to state-of-the-art while running at approximatively 60 FPS on GPU. Codes are available at https://github.com/liangminstu/STSiamFC. [ABSTRACT FROM AUTHOR]