Video Background Research Articles

Cut-and-Paste: Subject-driven video editing with attention control

This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image. While the text-driven video editing has demonstrated remarkable ability to generate highly diverse videos following given text prompts, the fine-grained semantic edits are hard to control by plain textual prompt only in terms of object details and edited region, and cumbersome long text descriptions are usually needed for the task. We therefore investigate subject-driven video editing for more precise control of both edited regions and background preservation, and fine-grained semantic generation. We achieve this goal by introducing an reference image as supplementary input to the text-driven video editing, which avoids racking your brain to come up with a cumbersome text prompt describing the detailed appearance of the object. To limit the editing area, we refer to a method of cross attention control in image editing and successfully extend it to video editing by fusing the attention map of adjacent frames, which strikes a balance between maintaining video background and spatio-temporal consistency. Compared with current methods, the whole process of our method is like “cut” the source object to be edited and then “paste” the target object provided by reference image. We demonstrate that our method performs favorably over prior arts for video editing under the guidance of text prompt and extra reference image, as measured by both quantitative and subjective evaluations.

816. BRONCHIAL INJURY AND REPAIR DURING MINIMALLY INVASIVE ESOPHAGECTOMY

Abstract Background Video Assisted Thoracoscopy (VATS) is the preferred approach to Esophagectomy thanks to the improved short term outcomes without any compromise on the oncological outcomes. VATS Esophagectomy is technically difficult and has a steep learning curve, with several potential complications. Description This is the video of a patient with early esophageal cancer (T1N0M0) who underwent VATS esophagectomy in the semi-prone position with capnothorax. There was an inadvertent injury to the membranous wall of the left bronchus which was sutured using monofilament absorbable sutures. The omentum was wrapped around and sutured to the anterior wall of the stomach tube, which reinforced the sutures once it was pulled up into the thorax. Patient had an uneventful postoperative recovery. Importance This video, apart from stressing on the need for careful dissection around the bronchial tree, shows that such an injury can be managed with minimal invasive techniques. https://1drv.ms/v/s!AmL6SI2dDeQVh9AzGMuncYi8GT3nIQ?e=IcjfNd

Temporally Coherent Video Cartoonization for Animation Scenery Generation

The automatic transformation of short background videos from real scenarios into other forms with a visually pleasing style, like those used in cartoons, holds application in various domains. These include animated films, video games, advertisements, and many other areas that involve visual content creation. A method or tool that can perform this task would inspire, facilitate, and streamline the work of artists and people who produce this type of content. This work proposes a method that integrates multiple components to translate short background videos into other forms that contain a particular style. We apply a fine-tuned latent diffusion model with an image-to-image setting, conditioned with the image edges (computed with holistically nested edge detection) and CLIP-generated prompts to translate the keyframes from a source video, ensuring content preservation. To maintain temporal coherence, the keyframes are translated into grids and the style is interpolated with an example-based style propagation algorithm. We quantitatively assess the content preservation and temporal coherence using CLIP-based metrics over a new dataset of 20 videos translated into three distinct styles.

Human pose estimation in complex background videos via Transformer-based multi-scale feature integration

Human posture estimation is still a hot research topic. Previous algorithms based on traditional machine learning have difficulties in feature extraction and low fusion efficiency. To address these problems, we proposed a Transformer-based method. We combined three techniques, namely the Transformer-based feature extraction module, the multi-scale feature fusion module, and the occlusion processing mechanism, to capture the human pose. The Transformer-based feature extraction module uses the self-attention mechanism to extract key features from the input sequence, the multi-scale feature fusion module fuses feature information of different scales to enhance the perception ability of the model, and the occlusion processing mechanism can effectively handle occlusion in the data and effectively remove background interference. Our method has shown excellent performance through verification on the standard dataset Human3.6M and the wild video dataset, achieving accurate pose prediction in both complex actions and challenging samples.

Let's Take a Look at the Tape: The Impact of ERAS Video Prompts on Interview Offerings for Orthopaedic Surgery Residency Applicants: A Prospective Observational Study.

Matching into an orthopaedic surgery residency consistently reinforces a competitive landscape, challenging the applicants and programs. A group of orthopaedic surgery residency programs implemented video prompts asking applicants to respond to a standardized question by video recording. Assessing the impact of this video on the decision to offer an interview can help guide programs and applicants through the interview process. Twenty residency applications to one institution requiring video prompts were randomly selected and deidentified. Thirteen experienced faculty from various orthopaedic surgery programs served as applicant reviewers. The reviewers evaluated the electronic residency application service (ERAS) application and determined whether they would grant the applicant an interview ("no," "maybe," or "yes") before and after watching the video prompt. The reviewer also scored the impact of the applicant's dress, facial presentation, and video background distractions on their evaluation of the video. Multivariable logistic regressions were conducted using a group of applicants where interview status was not impacted by the video compared with the group of applicants where the interview status changed after video review. An alpha value of 0.05 was used to define significance. The video prompt impacted the decision to offer an interview 29.3% of the time; 15.8% were switched from "yes" or "maybe" to "no" and 13.5% were switched from "no" or "maybe" to "yes." For the positively impacted applicants, facial presentation score was significantly higher (P = 0.005). No recorded variables were associated with decreased chance of interview. Video prompts impacted the decision to offer interviews to orthopaedic surgery applicants approximately one-third of the time, with a similar number of applicants being positively and negatively impacted. Facial presentation score was associated with increased chance of interview, and no variables were associated with decreased chance of interview. Thus, the answer to the videos presumably negatively impacted applicants.

Audio–Visual Segmentation based on robust principal component analysis

Audio–Visual Segmentation (AVS) aims to extract the sounding objects from a video. The current learning-based AVS methods are often supervised, which rely on specific task data annotations and expensive model training. Recognizing that the video background captured by a static camera is represented as a low-rank matrix, we introduce the non-convex robust principal component analysis into AVS task in this paper. This approach is unsupervised and only relies on input data patterns. Specifically, the proposed method decomposes each modality into the sum of two parts: the low-rank part that represents the background audio and visual information, and the sparse part that represents the foreground information. Furthermore, CUR decomposition is employed at each iteration to reduce the computational complexity in optimization. The experimental results also show that the proposed AVS outperforms the supervised methods on AVS-Bench Single-Source datasets.

Studying Provider’s Satisfaction on Video Consultation by Ain Shams University Virtual Hospital

Abstract Background Video consultations were developed to allow long-distance patient and clinician contact, care, advice and monitoring which has been shown to improve patient health status. When rural settings, lack of transport, a lack of mobility, decreased funding, or a lack of staff restrict access to care, video consultation may bridge the gap. Objective To measure satisfaction of physicians involved in video consultations services provided at Ain Shams Virtual Hospitals (AVH). To identify the main factors affecting satisfaction of physicians involved in such video consultations services provided at AVH. Methods A descriptive cross-sectional study was conducted to measure satisfaction of a sample of providers of video consultations at AVH from December 2020 to March 2021. Results Total 37 physicians were included in the study, 29 physicians responded (78.3%). The mean age ±SD is 37.97 ±6.3 and their main specialties were neuropsychiatry (40.7%), internal medicine subspecialties (40.7%), and surgical specialties (18.5%). About 83% were confident with their diagnoses in video consultations and (13.8%, 75.9%) of the physicians reported that they always/sometimes suffered from bad quality of image/sound respectively. More than half of the physicians (53.5%) thought that lack of physical examination would affect the accuracy of the diagnoses and 53.5% of the physicians thought that video consultation would be suitable for follow-up patients post operatively. Conclusion Two thirds of the physicians had a positive experience and were satisfied with using video consultations in their clinical practices. Recommendations It is recommended to use video consultations in following-up of patients. It is also recommended to monitor provider`s satisfaction over time.

Pengolahan Citra Berbasis Video Proccesing dengan Metode Frame Difference untuk Deteksi Gerak

This study discusses the detection of motion of objects in video by utilizing the Frame difference method which aims to process video so as to produce Frames on moving objects. The use of mobile cameras produces video data that is used as test data, the test data is processed with the Frame difference method so as to produce a number of Frames on moving objects in order to detect moving objects in the video because the function of this method is a form of video background reduction that is simplified by a number of pixels in the video. This method process is based on the difference between two consecutive frames in the video aimed at finding differences that occur during the detection process. When processed for detection, the absolute value in the pixel is greater than the predetermined threshold value, it will be considered as a moving object, so that the detection results from the motion detection process will form a box object on the moving object. In this study, the test data used used 20 video data samples with descriptions, 10 test data with bright quality (daytime) and 10 unlit test data (night) with the aim of being able to see how much the level of performance accuracy of the Frame difference method. The test results obtained 16 out of 20 test data that were successfully detected correctly (True Positive), there were 2 test data that resulted in a False Positive error, and 2 test data that resulted in a False Negative error. This shows that the Frame difference method can provide a fairly high level of accuracy in detecting moving objects in the video. The percentage level of accuracy with confussion matrix testing has a precission value of 88%, recal 88% and an accuracy value of 80%.

The Impact of Pop Music on Teenagers' Music Aesthetics under Short Video

Popular music, also known as "popular music", has developed rapidly in China in recent years and is deeply loved by the public. With the popularity of smart phones and the development of the Internet, short video software has gradually emerged. The platform represented by Tiktok has brought a new path to the development of popular music. A batch of popular music that is popular with short videos has set off a boom in all age groups. Teenagers account for the largest proportion of Internet users. This paper briefly discusses the impact of short videos on teenagers and popular music, analyzes the aesthetic characteristics of teenagers' music, and takes Tiktok "Subject 3" as an example, the characteristics of popular music under the background of short videos and its positive aesthetic impact on teenagers, and provides reference and suggestions for cultivating teenagers' aesthetic appreciation of music.

Multi-media Image and Video Overlay Text Extraction Based on Bayesian Classification Algorithm

With the continuous development of Internet technology, using multimedia for virtual application has become a new way. In this paper, by introducing the bayesian classification algorithm, multimedia graphics and video for carding, testing and implementation of edge image of fine processing, matching the corresponding text for quick positioning, at the same time use the filter for image and video background picture, further classification, distinguish between background and text, the extraction of superposition character. Simulation results show that the bayesian classification algorithm is effective and improves the efficiency and accuracy of image and video processing.

Webcraft AI

WebCraft AI is a user-friendly website builder that allows users to create an online presence with minimal effort and creative freedom. It offers features like online storage, e-commerce tools, video backgrounds, title animations, mobile apps, and a free service tier. The platform offers hundreds of template choices, many of which are free, and includes options for text, media, social media widgets, buttons, and shapes. Users can edit template designs with ease, using right-click context menus to change images or edit text. The platform also allows users to customize page design, add new pages, and change the site's navigation hierarchy. WebCraft AI offers nearly 20 top-level site types, each with subcategories, and a free service tier. Users can choose to use a site template or have WebCraft AI automatically create a site using Artificial Design Intelligence (ADI). Keywords: Free website templates, Easy web design, Customizable page design, User-friendly website builder

Multidimensional Data Processing With Bayesian Inference via Structural Block Decomposition.

How to handle large multidimensional datasets, such as hyperspectral images and video information, efficiently and effectively plays a critical role in big-data processing. The characteristics of low-rank tensor decomposition in recent years demonstrate the essentials in describing the tensor rank, which often leads to promising approaches. However, most current tensor decomposition models consider the rank-1 component simply to be the vector outer product, which may not fully capture the correlated spatial information effectively for large-scale and high-order multidimensional datasets. In this article, we develop a new novel tensor decomposition model by extending it to the matrix outer product or called Bhattacharya-Mesner product, to form an effective dataset decomposition. The fundamental idea is to decompose tensors structurally in a compact manner as much as possible while retaining data spatial characteristics in a tractable way. By incorporating the framework of the Bayesian inference, a new tensor decomposition model on the subtle matrix unfolding outer product is established for both tensor completion and robust principal component analysis problems, including hyperspectral image completion and denoising, traffic data imputation, and video background subtraction. Numerical experiments on real-world datasets demonstrate the highly desirable effectiveness of the proposed approach.

Investigating the effect of tourism short video background music congruence on viewers’ travel intention

ABSTRACT Short video promotion has become increasingly popular in tourism marketing, yet there is scant academic research on how it influences tourists’ travel intention. This study investigates how congruence between tourism short video background music and video content (i.e. BGM congruence) affects viewers’ travel intention. Through an experimental study and a survey study, this research indicates that BGM congruence significantly enhances viewers’ travel intention, mediated by flow experience and destination attitude. Furthermore, viewers’ familiarity with the BGM in short videos positively moderates the relationship between BGM congruence and travel intention. This study contributes to the literature in the field of short video promotion in tourism.

Optimizing Dynamic Mode Decomposition for Video Denoising via Plug-and-Play Alternating Direction Method of Multipliers

Dynamic mode decomposition (DMD) is a powerful tool for separating the background and foreground in videos. This algorithm decomposes a video into dynamic modes, called DMD modes, to facilitate the extraction of the near-zero mode, which represents the stationary background. Simultaneously, it captures the evolving motion in the remaining modes, which correspond to the moving foreground components. However, when applied to noisy video, this separation leads to degradation of the background and foreground components, primarily due to the noise-induced degradation of the DMD mode. This paper introduces a novel noise removal method for the DMD mode in noisy videos. Specifically, we formulate a minimization problem that reduces the noise in the DMD mode and the reconstructed video. The proposed problem is solved using an algorithm based on the plug-and-play alternating direction method of multipliers (PnP-ADMM). We applied the proposed method to several video datasets with different levels of artificially added Gaussian noise in the experiment. Our method consistently yielded superior results in quantitative evaluations using peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared to naive noise removal methods. In addition, qualitative comparisons confirmed that our method can restore higher-quality videos than the naive methods.

Exploring the Impact of Gaming Habits on Sleep Patterns Among Young Adults in Saudi Arabia: A Cross-Sectional Study.

Background Video gaming is increasingly popular among young adults, potentially affecting health and daily routines, especially sleep patterns. In Al-Ahsa, Saudi Arabia, the impact of video gaming on sleep and health among young adults is not well understood. This study aims to explore this relationship, focusing on how video gaming habits influence sleep patterns and associated health outcomes. Methods This cross-sectional survey utilized an adapted online questionnaire to gather data on demographics, video gaming habits, sleep patterns, and body mass index from young adults in Al-Ahsa. Statistical analysis, including descriptive statistics, chi-square tests, and multivariable logistic regression, was applied to examine the associations between video gaming habits and sleep sufficiency. Results The study included 302 participants, including 165 (54.6%) females. A majority reported playing video games for less than one hour daily (36.1%), with 82.5% preferring online gaming. Notably, 54.3% of participants slept more than six hours nightly, yet challenges with sleep initiation were evident, as 48.0% went to bed past midnight. Multivariable logistic regression highlighted significant factors affecting sleep sufficiency: participants who played games after completing tasks had 80% lower odds of sleep insufficiency compared to those who played before tasks. Overweight participants were found to be 7.7 times more likely to experience sleep insufficiency compared to their underweight peers. Conclusion The study underscores a complex relationship between video gaming habits and sleep patterns among young adults in Al-Ahsa, with significant health implications. It suggests the necessity for interventions promoting balanced gaming habits and improved sleep hygiene to mitigate adverse health outcomes.

CUR and Generalized CUR Decompositions of Quaternion Matrices and their Applications

Low-rank approximations of quaternion matrices have garnered interest across various applications, such as color images and signal processing. In this paper, we propose the CUR and generalized CUR decompositions of quaternion matrices and utilize the CUR decomposition of the quaternion matrix to solve the robust quaternion principal component analysis (RQPCA) problem. Through the discrete empirical interpolation method (DEIM) for the subset selection, we present the error analysis of the approximation of the CUR and the generalized CUR decompositions of quaternion matrices. The error bound depends on the conditioning of sampling submatrices. Next, we employ the alternating projection and adopt the CUR decomposition of the quaternion matrix to tackle the RQPCA. The non-convex algorithm runs fast and significantly reduces computational complexity. The performance advantages of our algorithms have been experimentally verified on artificial datasets. The RQCUR significantly affects color video background subtraction in the experiment.

Transform-Equivariant Consistency Learning for Temporal Sentence Grounding

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the dataset distribution bias. To alleviate these limitations, we introduce a novel Equivariant Consistency Regulation Learning (ECRL) framework to learn more discriminative query-related frame-wise representations for each video, in a self-supervised manner. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted under various video-level transformations. Concretely, we first design a series of spatio-temporal augmentations on both foreground and background video segments to generate a set of synthetic video samples. In particular, we devise a self-refine module to enhance the completeness and smoothness of the augmented video. Then, we present a novel self-supervised consistency loss (SSCL) applied on the original and augmented videos to capture their invariant query-related semantic by minimizing the KL-divergence between the sequence similarity of two videos and a prior Gaussian distribution of timestamp distance. At last, a shared grounding head is introduced to predict the transform-equivariant query-guided segment boundaries for both the original and augmented videos. Extensive experiments on three challenging datasets (ActivityNet, TACoS, and Charades-STA) demonstrate both effectiveness and efficiency of our proposed ECRL framework.

Interpretable Neural Networks for Video Separation: Deep Unfolding RPCA with Foreground Masking.

We present two deep unfolding neural networks for the simultaneous tasks of background subtraction and foreground detection in video. Unlike conventional neural networks based on deep feature extraction, we incorporate domain-knowledge models by considering a masked variation of the robust principal component analysis problem (RPCA). With this approach, we separate video clips into low-rank and sparse components, respectively corresponding to the backgrounds and foreground masks indicating the presence of moving objects. Our models, coined ROMAN-S and ROMAN-R, map the iterations of two alternating direction of multipliers methods (ADMM) to trainable convolutional layers, and the proximal operators are mapped to non-linear activation functions with trainable thresholds. This approach leads to lightweight networks with enhanced interpretability that can be trained on limited data. In ROMAN-S, the correlation in time of successive binary masks is controlled with side-information based on ℓ1-ℓ1 minimization. ROMAN-R enhances the foreground detection by learning a dictionary of atoms to represent the moving foreground in a high-dimensional feature space and by using reweighted-ℓ1-ℓ1 minimization. Experiments are conducted on both synthetic and real video datasets, for which we also include an analysis of the generalization to unseen clips. Comparisons are made with existing deep unfolding RPCA neural networks, which do not use a mask formulation for the foreground, and with a 3D U-Net baseline. Results show that our proposed models outperform other deep unfolding networks, as well as the untrained optimization algorithms. ROMAN-R, in particular, is competitive with the U-Net baseline for foreground detection, with the additional advantage of providing video backgrounds and requiring substantially fewer training parameters and smaller training sets.

Application and Research of Music Generation System Based on CVAE and Transformer-XL in Video Background Music

Application and Research of Music Generation System Based on CVAE and Transformer-XL in Video Background Music

Video Echoed in Harmony: Learning and Sampling Video-Integrated Chord Progression Sequences for Controllable Video Background Music Generation

Video Echoed in Harmony: Learning and Sampling Video-Integrated Chord Progression Sequences for Controllable Video Background Music Generation