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.

Few-shot action recognition aims to learn a model that can be easily adapted to identify novel action classifications using only a few labeled samples. Recent methods primarily focus on visual features and fail to fully utilize the available classification title of the video. In addition, they capture higher-order temporal relationships among video frames through averaging, which neglects the long-range dependencies information of the video. To address these issues, we designed a novel cross-modal guided spatio-temporal enrichment network (X-STEN) for few-shot action recognition. The model includes a cross-modal spatial enrichment module (X-SEM), a temporal enrichment module (TEM), and a non-parametric metrics module (NMM). Firstly, we extract and fuse multi-modal feature representations of videos. Then, we enhance the spatial context information of the video using the X-SEM and model the temporal context information of the video using the TEM. Finally, we generate the query and support prototypes and measure the similarity between them. Extensive experiments demonstrate that our X-STEN achieve excellent results on few-shot splits of Kinetics, HMDB51 and UCF101. Importantly, our method outperforms prior work on Kinetics by a wide margin (13.9%). [ABSTRACT FROM AUTHOR]

This study focused on the perception of the students on the video tutorials as a learning tool used in teaching Bread and Pastry production and its relationship with their baking performance. The descriptive-correlational research approach has been employed that uses video tutorials and survey questionnaires. The respondents are Grade 10 students in San Antonio National High School at San Antonio, Quezon during the school year 2023-2024. In identifying the respondents of the study, total enumeration of the population was considered, thus, no sampling technique was applied. The respondents generally perceived the video tutorials positively with favorable responses on objectives, content, instructions, audio and visual quality, and frequency of use. Similarly, their baking performances received positive feedback, particularly in presentation, taste and texture, time management, and food safety and hygiene. The study found out that the video tutorials in terms of its components such as objective, content, and instructions do not significantly related to students baking technical skills performance. Moreover, in significant relationship also exerted between students' baking performance and the video tutorial audio quality, visual quality and frequency of use. On the other hand, the students' average baking performance was associated with video tutorials visual quality and frequency of use. [ABSTRACT FROM AUTHOR]

Since the evolution of technology, it created a growing importance in the education sector. The use of video graphics or multimedia tools becomes a useful instrument in learning and teaching in the education industry. This study determined the correlation between the utilization of video graphics in teaching Hairdressing and the students' performance. A descriptive method of research was applied to accomplish this study. A total of thirty-three (33) Grade Eleven TVL students served as the respondents of this study. The researcher used a survey questionnaire in checklist format as the main research instrument to gather needed data. Statistics tools such as mean, standard deviation mean scores, and frequencies were used. The significance was tested at the 0.05 probability level. Based on the data collected, the perception of the students to the utilization of video graphics in teaching Hairdressing has an overall interpretation of "highly observed". It was revealed that there is a significant difference between the pre and post-test exams, considering the delivery of the lesson, teacher's mastery, efficiency, and feedback. The results indicate no significant relationship except for efficiency and performing hair treatment, audio, and post-service activities. The results also showed a positive learning development in terms of lesson adaptation through pre- and post-test scores and performance scores based on what the students knew before and after exposure to the video graphics. [ABSTRACT FROM AUTHOR]

Macro-expression spotting is an important prior step in many dynamic facial expression analysis applications. It automatically detects the onset and offset image frames of a macro-expression in the video. The state-of-the-art methods of macro-expression spotting characterize the movement of facial muscle through explicit analysis of the optical flow map and have achieved promising results. However, optical flow map estimation and expression spotting in these methods are performed in two separate and successive stages. In this paper, we propose a new dual-branch network to achieve unified optimization for expression spotting and optical flow estimation tasks. The proposed dual-branch network implicitly learns optical flow during training and enriches the feature representation with motion information. During inference, we use only the encoder of the optical flow estimation network for motion feature extraction and integrate it with expression spotting into a one-stage framework. The proposed method eliminates the need to construct optical flow maps explicitly during inference and significantly reduces the computational cost. We also apply a consistency constraint on the global- and local-level semantic features of the clip to guide the model to focus on the category-consistent regions of the video. We evaluate the proposed methods extensively on two popular facial expression spotting datasets, CAS(ME) 2 and SAMM Long Videos. The experimental results show that compared with the state-of-the-art methods, the proposed method improves the F1-scores for MaE spotting by 5.81 % and 1.57 % on the CAS(ME) 2 and SAMM Long Videos datasets respectively. [ABSTRACT FROM AUTHOR]

This research paper addresses an important challenge in book digitization, i.e., accurately predicting frames where text visibility is optimal. Existing models often suffer from high computational complexity, resulting in inefficiencies in automation and accuracy. In contrast, our proposed models offer a solution with lower complexity and higher accuracy. Leveraging a diverse dataset of book flipping videos, we introduce three novel models: the Regular CNN LeNet-5 Model, the Custom LSTM Model, and the 3D CNN Model. Evaluation reveals that our 3D CNN Model achieves an accuracy score of 99.01%, with 377,921 parameters. These models demonstrate a significant increase in efficiency in terms of accuracy metric with significantly less number of parametrers. Thereby the proposed approach enhances the process of identifying frames of interest. Our findings highlight the transformative potential of these models in streamlining book digitization workflows and improving accessibility to digitized textual content. This study contributes valuable insights at the intersection of computer vision, machine learning, and digitization efforts, offering a promising avenue for enhancing the usability of digitized textual resources. [ABSTRACT FROM AUTHOR]

This study investigates how affect is manifested in the pragmeme of delivering a health directive in the Covid-19 context and how affect co-participates in the pragmeme. This research draws on theoretical insights from pragmeme theory, relevance theory, and the recent distributed language view, with the aim of contributing to the development of a language-body-environment perspective on pragmatic acts. By way of illustration, two videos used in BBC reports were analyzed, one featuring the UK Prime Minister Boris Johnson's order to the British people to stay at home and the other being an unofficial, self-made video that also appeals to the public to remain at home. This paper argues that affect in its various manifestations embodies affective potential, which should be regarded as being part and parcel of the pragmeme. [ABSTRACT FROM AUTHOR]

Low‐light image/video enhancement is a challenging task when images or video are captured under harsh lighting conditions. Existing methods mostly formulate this task as an image‐to‐image conversion task via supervised or unsupervised learning. However, such conversion methods require an extremely large amount of data for training, whether paired or unpaired. In addition, these methods are restricted to specific training data, making it difficult for the trained model to enhance other types of images or video. In this paper, we explore a novel, fast and flexible, zero‐shot, low‐light image or video enhancement framework. Without relying on prior training or relationships among neighboring frames, we are committed to estimating the illumination of the input image/frame by a well‐designed network. The proposed zero‐shot, low‐light image/video enhancement architecture includes illumination estimation and residual correction modules. The network architecture is very concise and does not require any paired or unpaired data during training, which allows low‐light enhancement to be performed with several simple iterations. Despite its simplicity, we show that the method is fast and generalizes well to diverse lighting conditions. Many experiments on various images and videos qualitatively and quantitatively demonstrate the advantages of our method over state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Audio‐driven talking face generation is essentially a cross‐modal mapping from audio to video frames. The main challenge lies in the intricate one‐to‐many mapping, which affects lip sync accuracy. And the loss of facial details during image reconstruction often results in visual artifacts in the generated video. To overcome these challenges, this paper proposes to enhance the quality of generated talking faces with a new spatio‐temporal consistency. Specifically, the temporal consistency is achieved through consecutive frames of the each phoneme, which form temporal modules that exhibit similar lip appearance changes. This allows for adaptive adjustment in the lip movement for accurate sync. The spatial consistency pertains to the uniform distribution of textures within local regions, which form spatial modules and regulate the texture distribution in the generator. This yields fine details in the reconstructed facial images. Extensive experiments show that our method can generate more natural talking faces than previous state‐of‐the‐art methods in both accurate lip sync and realistic facial details. [ABSTRACT FROM AUTHOR]

Video anomaly detection is always formulated as frame prediction task which only learned on normal data and detects deviations as anomalies. However, previous methods lack sufficient spatiotemporal constraints on moving objects, making it difficult to learn compact normal distributions and anomalies near the boundary will be misclassified as normal. Besides, the inadequate exploration of diverse normal patterns results in mode missing and unlearned normal patterns will be misclassified as anomalies. To address these problems, we propose an object-level Diverse Motion-conditioned Adversarial Predictive Network for video anomaly detection which combines conditional variational generation with adversarial learning to mitigate false detection. We design a motion-guided generator that controls the generation process conditioned on optical flows to accurately memorize spatiotemporal correlations of normal data. We employ the diversity regularization strategy which explicitly preserves the recurrent structure of normal data in continuous latent space to ensure full utilization of diverse patterns. Additionally, we combine an input clip with the object it generates to synthesize an anomaly near the boundary, then employ a video discriminator to perceive subtle differences between normal and abnormal data, making them more distinguishable. Extensive experiments conducted on public datasets illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Due to the fuzziness of anomaly definition and the complexity of scenes in real video data, video anomaly detection is still a challenging task. In this work, we explored a novel lightweight dual branch convolution neural architecture that can separate appearance-motion representations to capture spatial and temporal information, respectively, since abnormal events are usually different from normal cases in appearance or motion behavior. Considering the channel redundancy problem in the traditional neural network, and the feature information processed by different branches is different, the corresponding channel attenuation is carried out, which greatly improves the speed of anomaly detection while maintaining the performance of the model. In order to improve the utilization of key features, we exploited a Channel Squeeze and Excitation module and insert it into the encoder part of the network to focus on the channel correlation and adaptively recalibrate the characteristic response of the channel. The importance of each feature channel is automatically acquired through learning, and then according to the importance, the useful channels are promoted and the channels that are not useful for the current task are suppressed. In addition, in order to increase the reconstruction error of the motion encoder and consider the diversity of the normal patterns, we propose to use a memory module to augment the motion U-Net, where the items in the memory record the prototype mode of the normal data. The experiments on three benchmark datasets, UCSD Ped2, CHUK Avenue, and ShanghaiTech, demonstrate that our method achieves AUC scores of 96.3%, 87.4%, and 73.5%, respectively. The experimental speed reaches 55fps, showing a competitive performance relative to the current state of research. [ABSTRACT FROM AUTHOR]

Latent diffusion models (LDMs) have demonstrated remarkable success in generative modeling. It is promising to leverage the potential of diffusion priors to enhance performance in image and video tasks. However, applying LDMs to video super‐resolution (VSR) presents significant challenges due to the high demands for realistic details and temporal consistency in generated videos, exacerbated by the inherent stochasticity in the diffusion process. In this work, we propose a novel diffusion‐based framework, Temporal‐awareness Latent Diffusion Model (TempDiff), specifically designed for real‐world video super‐resolution, where degradations are diverse and complex. TempDiff harnesses the powerful generative prior of a pre‐trained diffusion model and enhances temporal awareness through the following mechanisms: 1) Incorporating temporal layers into the denoising U‐Net and VAE‐Decoder, and fine‐tuning these added modules to maintain temporal coherency; 2) Estimating optical flow guidance using a pre‐trained flow net for latent optimization and propagation across video sequences, ensuring overall stability in the generated high‐quality video. Extensive experiments demonstrate that TempDiff achieves compelling results, outperforming state‐of‐the‐art methods on both synthetic and real‐world VSR benchmark datasets. Code will be available at https://github.com/jiangqin567/TempDiff [ABSTRACT FROM AUTHOR]

Temporal action localization plays a significant role in video understanding, which aims to recognize action category as well as temporal interval in untrimmed videos. Most of previous transformer-based methods employ a feature space of single-temporal granularity. However, low-level temporal features can not provide enough semantic information for action recognition while high-level temporal features lack rich details for boundary localization. To address the above issue, we propose a multi-granularity transformer fusion framework (MGTF) to localize temporal actions in videos. Specifically, the MGTF builds a multi-granularity feature fusion pipeline based on transformer, and uses a direct set prediction strategy to generate action instances. Through top-down cross-granularity attention interaction, the low-level features of boundary details and high-level semantic information can be combined to improve the feature discrimination. To reduce computation cost, we design temporal shift attention to adaptively focus on a sparse set of key segments. In addition, actionness regression head is utilized to refine the confidence score of different candidate instances. As a self-contained system, MGTF achieves state-of-the-art performance on THUMOS'14 and comparable performance on ActivityNet-1.3. Ablation studies and qualitative visualization also demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Video presentation has become ubiquitous in paradigms investigating the neural and behavioral responses to observed actions. In spite of the great interest in uncovering the processing of observed bodily movements and actions in neuroscience and cognitive science, at present, no standardized set of video stimuli for action observation research in neuroimaging settings exists. To facilitate future action observation research, we developed an open-access database of 135 high-definition videos of a male actor performing object-oriented actions. Actions from 3 categories: kinematically natural and goal-intact (Normal), kinematically unnatural and goal-intact (How), or kinematically natural and goal-violating (What), directed toward 15 different objects were filmed from 3 angles. Psychometric evaluation of the database revealed high video recognition accuracy (Mean accuracy = 88.61 %) and substantial inter-rater agreement (Fleiss' Kappa = 0.702), establishing excellent validity and reliability. Videos' exact timing of motion onset was identified using a custom motion detection frame-differencing procedure. Based on its outcome, the videos were edited to assure that motion begins at the second frame of each video. The videos' timing of category recognition was also identified using a novel behavioral up-down staircase procedure. The identified timings can be incorporated in future experimental designs to counteract jittered stimulus onsets, thus vastly improving the sensitivity of neuroimaging experiments. All videos, their psychometric evaluations, and the timing of their frame of category recognition, as well as our custom programs for performing these evaluations on our, or on other similar video databases, are available at the Open Science Framework (https://osf.io/zexc4/). [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]

With the growing diverse student population in U.S. public schools, an increased focus on cultural-related matters has surfaced in education. As a result, consultation training must prepare novice consultants with the knowledge and skills needed to provide multicultural consultation. Technology can be used to develop novice consultants' multicultural consultation skills. This conceptual paper presents four strategies that can be used with technological applications to prepare novice consultants to deliver multicultural consultation services. Specific attention to how graduate-level training can infuse technology into existing educational practices, such as structured supervision, cross-university dialogs, video simulations, and virtual-based service learning to strengthen multicultural consultation skill development. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the multi-target tracking (MOT) task in satellite videos. To achieve efficient and accurate tracking, we propose a transformer-distillation-based end-to-end joint detection and tracking (JDT) method. Specifically, (1) considering that targets in satellite videos usually have small scales and are shot from a bird's-eye view, we propose a pixel-wise transformer-based feature distillation module through which useful object representations are learned via pixel-wise distillation using a strong teacher detection network; (2) targets in satellite videos, such as airplanes, ships, and vehicles, usually have similar appearances, so we propose a temperature-controllable key feature learning objective function, and by highlighting the learning of similar features during distilling, the tracking accuracy for such objects can be further improved; (3) we propose a method that is based on an end-to-end network but simultaneously learns from a highly precise teacher network and tracking head during training so that the tracking accuracy of the end-to-end network can be improved via distillation without compromising efficiency. The experimental results on three recently released publicly available datasets demonstrated the superior performance of the proposed method for satellite videos. The proposed method achieved over 90% overall tracking performance on the AIR-MOT dataset. [ABSTRACT FROM AUTHOR]

High-quality video object segmentation is a challenging visual computing task. Interactive segmentation can improve segmentation results. This paper proposes a multi-round interactive dynamic propagation instance-level video object segmentation network based on click interaction. The network consists of two parts: a user interaction segmentation module and a bidirectional dynamic propagation module. A prior segmentation network was designed in the user interaction segmentation module to better segment objects of different scales that users click on. The dynamic propagation network achieves high-precision video object segmentation through the bidirectional propagation and fusion of segmentation masks obtained from multiple rounds of interaction. Experiments on interactive segmentation datasets and video object segmentation datasets show that our method achieves state-of-the-art segmentation results with fewer click interactions. [ABSTRACT FROM AUTHOR]

Thermal videos provide a privacy-preserving yet information-rich data source for remote health monitoring, especially for respiration rate (RR) estimation. This paper introduces an end-to-end deep learning approach to RR measurement using thermal video data. A detection transformer (DeTr) first finds the subject's facial region of interest in each thermal frame. A respiratory signal is estimated from a dynamically cropped thermal video using 3D convolutional neural networks and bi-directional long short-term memory stages. To account for the expected phase shift between the respiration measured using a respiratory effort belt vs. a facial video, a novel loss function based on negative maximum cross-correlation and absolute frequency peak difference was introduced. Thermal recordings from 22 subjects, with simultaneous gold standard respiratory effort measurements, were studied while sitting or standing, both with and without a face mask. The RR estimation results showed that our proposed method outperformed existing models, achieving an error of only 1.6 breaths per minute across the four conditions. The proposed method sets a new State-of-the-Art for RR estimation accuracy, while still permitting real-time RR estimation. [ABSTRACT FROM AUTHOR]

Collaboration among road agents, such as connected autonomous vehicles and roadside units, enhances driving performance by enabling the exchange of valuable information. However, existing collaboration methods predominantly focus on perception tasks and rely on single-frame static information sharing, which limits the effective exchange of temporal data and hinders broader applications of collaboration. To address this challenge, we propose CoPnP, a novel collaborative joint perception and prediction system, whose core innovation is to realize multi-frame spatial–temporal information sharing. To achieve effective and communication-efficient information sharing, two novel designs are proposed: (1) a task-oriented spatial–temporal information-refinement model, which filters redundant and noisy multi-frame features into concise representations; (2) a spatial–temporal importance-aware feature-fusion model, which comprehensively fuses features from various agents. The proposed CoPnP expands the benefits of collaboration among road agents to the joint perception and prediction task. The experimental results demonstrate that CoPnP outperforms existing state-of-the-art collaboration methods, achieving a significant performance-communication trade-off and yielding up to 11.51%/10.34% Intersection over union and 12.31%/10.96% video panoptic quality gains over single-agent PnP on the OPV2V/V2XSet datasets. [ABSTRACT FROM AUTHOR]

Hyperspectral video provides rich spatial and spectral information, which is crucial for object tracking in complex scenarios. Despite extensive research, existing methods often face an inherent trade-off between rich spectral information and redundant noisy information. This dilemma arises from the efficient utilization of hyperspectral image data channels. To alleviate this problem, this paper introduces a hierarchical spectral attention network for hyperspectral object tracking. We employ a spectral band attention mechanism with adaptive soft threshold to examine the correlations across spectral bands, which integrates the information available in various spectral bands and eliminates redundant information. Moreover, we integrate spectral attention into a hierarchical tracking network to improve the integration of spectral and spatial information. The experimental results on entire public hyperspectral competition dataset WHISPER2020 show the superior performance of our proposed method compared with that of several related methods in visual effects and objective evaluation. [ABSTRACT FROM AUTHOR]

Increases in display resolution, frame rate, and bit depth, particularly with advances in stereoscopic 3D (S3D) displays, have increased demand for efficient compression throughout the imaging pipeline. To meet such requirements, typically the aim is to reduce bandwidth while presenting content that is visually indistinguishable from the original uncompressed versions. Subjective image quality assessment is essential and multiple methods have been proposed. Of these, the ISO/IEC 29170‐2 flicker paradigm is a rigorous method used to define visually lossless performance. However, it is possible that the enhanced sensitivity to artifacts in the presence of flicker does not predict visibility under natural viewing conditions. Here, we test this prediction using high‐dynamic range S3D images and video under flicker and non‐flicker protocols. As hypothesized, sensitivity to artifacts was greater when using the flicker paradigm, but no differences were observed between the non‐flicker paradigms. Results were modeled using the Pyramid of Visibility, which predicted artifact detection driven by moderately low spatial frequencies. Overall, our results confirm the flicker paradigm is a conservative estimate of visually lossless behavior; it is highly unlikely to miss artifacts that would be visible under normal viewing. Conversely, artifacts identified by the flicker protocol may not be problematic in practice. [ABSTRACT FROM AUTHOR]

Temporal inconsistency is the annoying artifact that has been commonly introduced in low-light video enhancement, but current methods tend to overlook the significance of utilizing both data-centric clues and model-centric design to tackle this problem. In this context, our work makes a comprehensive exploration from the following three aspects. First, to enrich the scene diversity and motion flexibility, we construct a synthetic diverse low/normal-light paired video dataset with a carefully designed low-light simulation strategy, which can effectively complement existing real captured datasets. Second, for better temporal dependency utilization, we develop a Temporally Consistent Enhancer Network (TCE-Net) that consists of stacked 3D convolutions and 2D convolutions to exploit spatial-temporal clues in videos. Last, the temporal dynamic feature dependencies are exploited to obtain consistency constraints for different frame indexes. All these efforts are powered by a Spatial-Temporal Compatible Learning (STCL) optimization technique, which dynamically constructs specific training loss functions adaptively on different datasets. As such, multiple-frame information can be effectively utilized and different levels of information from the network can be feasibly integrated, thus expanding the synergies on different kinds of data and offering visually better results in terms of illumination distribution, color consistency, texture details, and temporal coherence. Extensive experimental results on various real-world low-light video datasets clearly demonstrate the proposed method achieves superior performance to state-of-the-art methods. Our code and synthesized low-light video database will be publicly available at https://github.com/lingyzhu0101/low-light-video-enhancement.git. [ABSTRACT FROM AUTHOR]

To validate the Manipal Bedside Swallowing Screening Test (MBSST) for assessing aspiration in individuals with tracheostomy using Video Fluoroscopic Swallow Study (VFSS). A total of 53 tracheostomized participants were screened for aspiration at bedside and VFSS across different consistencies. Penetration Aspiration Scale (PAS) was used to substantiate the severity of aspiration if present. The test demonstrated both high sensitivity (91%; 95% confidence interval = 70.8–98.9) and diagnostic accuracy (96%; 95% confidence interval = 87.0-99.5) for detecting aspiration in individuals with tracheostomy. The Manipal Bedside Swallowing Screening Test is an easy to administer tool that has sufficient sensitivity to detect aspiration in individuals with tracheostomy. The MBSST will be an easy to administer tool and will help in screening for aspiration at bedside without any instrumental examination. [ABSTRACT FROM AUTHOR]

Both visual and haptic softness perception have recently been shown to have multiple dimensions, such as deformability, granularity, fluidity, surface softness, and roughness. During haptic exploration, people adjust their hand motions (exploratory procedures, EPs) based on the material qualities of the object and the particular information they intend to acquire. Some of these EPs are also shown to be associated with perceived softness dimensions, for example, stroking a silk blouse or applying pressure to a pillow. Here, we aimed to investigate whether we can manipulate observers' judgments about softness attributes through exposure to videos of others performing various EPs on everyday soft materials. In two experiments, participants watched two videos of the same material: one with a corresponding EP and the other without correspondence; then, they judged these materials based on 12 softness-related adjectives (semantic differentiation method). The results of the second experiment suggested that when the EP is congruent with the dimension from which the material is chosen, the ratings for the adjectives from the same dimension are higher than the incongruent EP. This study provides evidence that participants can assess material properties from optic and mechanical cues without needing haptic signals. Additionally, our findings indicate that manipulating the hand motion can selectively facilitate material-related judgments. [ABSTRACT FROM AUTHOR]

This qualitative study examines the use of the Video Timeline-Anchored Comment (VTC) tool in asynchronous online courses to explore students' discussion during video-based lectures. Applying this recently available tool of human-computer interaction (HCI) for asynchronous online video discussions enables students to watch video-based lectures while timely commenting on the content, and peers' thoughts, or asking questions. Thirty students from two graduate-level adult education courses at a US institution participated in the study. The findings demonstrate that the VTC tool helps engage online students in asynchronous video-based lecture discussions and increases their interactions with the content, peers, and their instructor. Our research suggests a model that encourages interactive engagement to enhance learners' cognitive presence. This could help bridge the gap between online lectures and offline social networks in an asynchronous learning setting by facilitating real-time connections. We conclude by integrating the HCI tool with the interactive discussion model, students' online interactions during video lecture discussions can be improved and sustained. [ABSTRACT FROM AUTHOR]

Previous studies have investigated which context-sharing interfaces are effective in improving task performance; however, consistent results have yet to be found. In this study, we developed a convenient remote collaboration system that provides multiple context-sharing interfaces in a single platform (2D video, 360° video, and 3D reconstruction view). All interfaces can reflect live updates of environmental changes, and we aimed to clarify the effect of the interface on the quality of remote collaboration. Thirty participants were recruited to perform a target-finding-and-placing scenario. Using both objective and subjective metrics, we compared the task performance among the three interface conditions. The results showed that participants completed the task faster and reported a better collaborative experience in the 3D interface condition. Moreover, we found a strong preference for the 3D view interface. These results suggest that providing 3D reconstructed spatial information can enable remote experts to instruct local workers more effectively. [ABSTRACT FROM AUTHOR]

Given the wealth of research available on what components to include in a syllabus and how that affects instructor perception, there is a lack of research on how to present the syllabus to engage students in learning about the course. Our study examined the implementation of two multimedia syllabi developed for large lecture math courses: a graphic syllabus and a video version. After reviewing their respective syllabi, students were given a syllabus content quiz and course perception survey. Findings indicate no significant difference between students' syllabus quiz performance and overall survey responses between groups. Students responded favorably to the survey regardless of syllabus type. Last, there was no observed relationship between the length of each syllabus segment video and the frequency at which students watched each segment. Implications of this study will address engagement with the syllabus and provide additional considerations for syllabus development. [ABSTRACT FROM AUTHOR]

This article presents a study that examines the effectiveness of prerecorded video lectures compared to traditional in-person lectures. The study focuses on a college physics course and surveys students who experienced both types of lectures in the same semester. The survey data reveals that students generally found the video lectures to be effective and felt that they learned the subject material. However, they expressed a preference for in-person lectures and disagreed with the idea of having all lectures delivered solely through video. The results suggest that while video lectures are convenient, students still value the benefits of in-person lectures, such as immediate interaction and the ability to ask questions. Future research will explore ways to enhance student engagement with video lectures, such as offering virtual office hours. Overall, the findings indicate that while students are open to learning from video lectures, they still prefer in-person lectures. [Extracted from the article]

This paper proposes a new Dynamic hAnd gesTurE (DATE) dataset for dynamic hand gestures. The DATE dataset contains 13,500 videos of 22 different subjects. The subjects wear different clothes, have different backgrounds, and are filmed from various camera angles. Two different benchmarks for our self-built DATE dataset are also proposed. The first one is the high accuracy approach, while the second benchmark is the lightweight approach. The operation of our benchmarks has two phases. In the first phase, videos are preprocessed with detection or segmentation tasks. Then, the processed data are classified by customized cutting-edge deep learning models in the second phase. Experimental results showed that our benchmarks obtained high accuracies in both the self-build dataset and a publicly recognized dataset. [ABSTRACT FROM AUTHOR]

With an increasing number of videos integrating instructor's visuals on screen, we know little about the impacts of this design on mind wandering. The study aims to investigate a) how instructor visibility impacts mind wandering; b) the relationship between mind wandering and retention performance; c) how visual behaviour during video-watching influences mind wandering. Each participant watched a video with or without instructor visibility, while their visual behaviour was recorded by an eye tracker. Retention performance was measured at the completion of the video. Mind wandering was inferred via global self-report measure and objective eye tracking measure. Both measures of mind wandering indicated the instructor visible video resulted in less mind wandering. Findings suggested mind wandering impaired retention performance. Additionally, visual attention to the instructor was associated with less mind wandering. [ABSTRACT FROM AUTHOR]

The objective of deep learning-based object detection is to accurately localize and recognize objects of interest from images or videos using neural networks. However, the detection and localization of non-salient objects pose challenges due to their small proportions, low contrast, and occlusion in images. To address this, we propose an improved object detection method, namely hierarchical coordinate attention (HCA)-YOLO, based on the YOLOv8 architecture. Specifically, we enhance the model's attention towards non-salient objects by introducing HCA, building upon the optimized YOLOv8 baseline. Additionally, we propose a novel object regression loss metric, β-VIoU, to improve YOLOv8's perception of non-salient object positions. Our method achieves competitive results on multiple metrics with two widely adopted open-source datasets, MS COCO 2017 and CrowdHuman. Compared to the YOLOv8x baseline model, HCA-YOLO improves the average precision (mAP) by 3.3% and 3.7% on these two datasets, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Current Research in Dental Sciences is the property of Ataturk University Coordinatorship of Scientific Journals 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.)

Technology is an essential component of modern education, and teachers use various types of technology to improve classroom performance. Meanwhile, statistics is one of the seemingly difficult courses according to students across levels. This study experimental aimed to determine if video explainer and e-module improve students' performance in statistics. There were 78 graduate school students participated and used video explainer, e-module, or both as an intervention. A 100-item performance test in statistics was used. The statistical techniques employed were mean, standard deviation and analysis of covariance (ANCOVA). Results revealed that students' pre-test performance was "average". Additionally, their posttest performance was "high", regardless of the intervention utilized. Significant differences emerged between groups who utilized both video explainer and e-module and those who used simply video explainer or e-module. Video explainer and e-modules should be integrated carefully into the instruction, helping graduate students develop a solid understanding of statistics. The results of the study suggest that studying statistics is more successful when one uses these interventions because it integrates visuals, audio, real-world applications, accessibility and flexibility towards various learning styles. Learning stakeholders should cooperate to ensure seamless integration of these materials into the curriculum and provide ample support to educators in generating and managing content. [ABSTRACT FROM AUTHOR]

Online learning, including in higher education, is an active part of the modern educational landscape. Spherical video-based immersive virtual reality (SV-IVR) is useful in this field. This study aimed to determine the impact of teaching with the use of SV-IVR on the critical thinking and cognitive load of 140 students. The findings of the study revealed that students exhibited low levels of mental effort and mental load based on the observed indicators. Compared to the traditional teaching method, the SV-IVR model had a better effect on improving students' critical thinking skills. The findings can help teachers develop new learning models using video-based virtual reality. [ABSTRACT FROM AUTHOR]

The importance of video remote interpreting (VRI) for providing interpreting services has drastically increased over the last decade. Empirical research has shown, however, that interpreting through video link may have a significant impact on the interaction and the interpreting performance in dialogue interpreting contexts. The present study contributes to this growing field of research by focusing on interpreters' repair initiations in the context of VRI. Although repairs are an important mechanism for addressing problems in communication, very little research has been devoted to the study of interpreter-initiated repair in dialogue settings. Based on a corpus of video-recorded interpreted interactions (Dutch-Russian), where the interpreter is either present onsite or connected through video link, we analyse interpreters' repair initiations and related risk taking behaviour. More specifically, we examine how interpreters manage a specific type of repair initiations in video remote interpreting, namely postponed repairs. The analysis reveals differences in repair patterns between video remote and onsite interpreting and we propose that these differences result from differential risk management in the two settings. [ABSTRACT FROM AUTHOR]

Temporal action detection is an important and fundamental video understanding task that aims to locate the temporal regions where human actions or events may occur and to identify the classes of actions in untrimmed videos. The main challenge of temporal action detection is that videos are usually of different durations and untrimmed. Although existing methods have achieved better results in recent years, there are still some challenges, such as a lack of full utilisation of video context features, insufficient accuracy of generated action boundaries and failure to consider the relationship between proposals. To address the above issues, this paper proposes a Multi-branch Boundary Generation Network (MBGNet) with temporal context aggregation. It improves the performance of temporal action proposal generation by exploiting rich temporal context features and complementary boundary generators.First, we propose a multi-path temporal context feature aggregation (MTCA) module to exploit "local and global" contextual temporal features for the generation of temporal action proposals. Second, in order to generate accurate action boundaries, we design a multi-branch temporal boundary detector (MBG) to optimise the prediction results by exploiting the complementary relationship between the two boundary detectors.In addition, to accurately predict the confidence of densely distributed proposals, we design a proposal relation-aware module (PRAM) that exploits global correlation for proposal relationship modelling. Experiments on the popular datasets ActivityNet1.3, THUMOS14, and HACS demonstrate the effectiveness of the method proposed in this paper on the task of temporal action proposal generation, which can generate action proposals with high precision and recall. Moreover, combining with existing action classifiers can also achieve better performance in temporal action detection.These results demonstrate the effectiveness of the method in this paper in improving the accuracy of temporal action proposal generation and detection. [ABSTRACT FROM AUTHOR]

The current paradigm of joint detection and tracking still requires a large amount of instance-level trajectory annotation, which incurs high annotation costs. Moreover, treating embedding training as a classification problem would lead to difficulties in model fitting. In this paper, we propose a new self-supervised multi-object tracking based on the real-time joint detection and embedding (JDE) framework, which we termed as self-supervised multi-object tracking (SS-MOT). In SS-MOT, the short-term temporal correlations between objects within and across adjacent video frames are both considered as self-supervised constraints, where the distances between different objects are enlarged while the distances between same object of adjacent frames are brought closer. In addition, short trajectories are formed by matching pairs of adjacent frames using a matching algorithm, and these matched pairs are treated as positive samples. The distances between positive samples are then minimized for futher the feature representation of the same object. Therefore, our method can be trained on videos without instance-level annotations. We apply our approach to state-of-the-art JDE models, such as FairMOT, Cstrack, and SiamMOT, and achieve comparable results to these supevised methods on the widely used MOT17 and MOT20 challenges. [ABSTRACT FROM AUTHOR]

Short videos are very popular in China. The provincial TV stations in China use short videos to disseminate information. Curiosity about the influence of short video news is the primary motivation of this study. This paper integrates theories of news and place, focuses on local visibility, explores how short videos can serve as media infrastructure to report news, construct local visibility and change public life. Taking a sample of official short videos from 31 provincial TV stations in China, this paper uses the narrative analysis method to decode the videos. It is found that short videos create a unique news space which are reflected in narrative language, narrative framework and narrative theme, respectively. This study argues that the short video platform has shaped a place with public vitality, participated in local image management, and built the "visible community". This has innovated the existing theoretical relationship between news and place, and the short video media practice of TV stations in various provinces has provided the world with the Chinese experience of creating place. [ABSTRACT FROM AUTHOR]

In this study, we revisit the fundamental setting of face-swapping models and reveal that only using implicit supervision for training leads to the difficulty of advanced methods to preserve the source identity. We propose a novel reverse pseudo-input generation approach to offer supplemental data for training face-swapping models, which addresses the aforementioned issue. Unlike the traditional pseudo-label-based training strategy, we assume that arbitrary real facial images could serve as the ground-truth outputs for the face-swapping network and try to generate corresponding input pair data. Specifically, we involve a source-creating surrogate that alters the attributes of the real image while keeping the identity, and a target-creating surrogate intends to synthesize attribute-preserved target images with different identities. Our framework, which utilizes proxy-paired data as explicit supervision to direct the face-swapping training process, partially fulfills a credible and effective optimization direction to boost the identity-preserving capability. We design explicit and implicit adaption strategies to better approximate the explicit supervision for face swapping. Quantitative and qualitative experiments on FF++, FFHQ, and wild images show that our framework could improve the performance of various face-swapping pipelines in terms of visual fidelity and ID preserving. Furthermore, we display applications with our method on re-aging, swappable attribute customization, cross-domain, and video face swapping. Code is available under https://github.com/ ICTMCG/CSCS. [ABSTRACT FROM AUTHOR]

In video action recognition, effective spatiotemporal modeling is crucial. However, traditional two-stream methods face challenges in integrating spatial information from RGB images and temporary information from optical flow without long-range temporal modelling. To address these limitations, we propose the Deep Fusion Module (DFM), which focuses on the deep fusion of spatial and temporal information and consists of two components. First, we propose an Attention Fusion Module (AFM) to effectively fuse the shallow features obtained from a two-stream network, thereby facilitating the integration of spatial and temporal information. Next, we incorporate a SpatioTemporal Module (STM), comprising a ConvGRU and a 1×1 convolution, to model long-range temporal dependency and fuse spatial-temporal features. Experiments on the UCF101 dataset show that our method achieves 96.5% accuracy, outperforming baseline two-stream models by 0.3%. [ABSTRACT FROM AUTHOR]

Background: Tentorial dural arteriovenous fistulas (dAVFs) are categorized based on venous drainage and location. Although their angioarchitecture may initially appear intimidating, once "decodified," treatment is straightforward. Posteromedial tentorial dAVFs have an arterialized draining vein that emanates from the inferior tentorium along the posterior third of the straight sinus, just slightly off the midline. Method: With the aid of anatomical dissections, intraoperative photos, and operative videos, we outline the key steps for surgical treatment of posteromedial tentorial dAVFs. Conclusion: Posteromedial tentorial dAVFs constitute a precise and well-defined subtype of tentorial dAVF for which surgical ligation has an important role. [ABSTRACT FROM AUTHOR]

Unsupervised video anomaly detection approaches often demand complex models and substantial computational resources for effective performance. In contrast, we introduce a supervised and end-to-end trainable deep learning approach that leverages both performance and computational efficiency by harnessing frame-level annotated data. The framework begins with the utilization of an Inception encoder network in the initial stage to learn feature representations. Notably, the Inception network's proficiency in capturing intricate and high-level features in frames seamlessly extends to the analysis of video data. By using these extracted features, the model excels in identifying deviations from learned patterns, making it highly adept at detecting anomalies in video sequences. The subsequent stage involves a sequence of fully connected layers followed by a classifier that is responsible for classifying input frames as either normal or anomalous based on the extracted features. To thoroughly validate this methodology, extensive experiments are carried out on widely used benchmark datasets. These evaluations involved comprehensive comparisons with contemporary approaches in the field. The experimental findings consistently validate the efficacy and efficiency of the proposed approach, underscoring its outstanding accuracy in identifying anomalies. Additionally, the approach operates with significantly reduced computational overhead, rendering it an appealing solution for real-world applications that demand timely and precise anomaly detection. [ABSTRACT FROM AUTHOR]