Set Of Videos Research Articles

Video Recommendation Method Based on Deep Learning of Group Evaluation Behavior Sequences

Massive video resources satisfy the interests of users on online video platforms but have led to the problem of the “explosion” of video resources. Meanwhile, some problems will also occur such as the sparse data, difficulty in extracting deep features and dynamic changes in user interests in video recommendation. Aiming at the problems, a video recommendation method is proposed based on the deep learning of group evaluation behavior. Using the Word2Vec word vector model, a video is mapped into a high-dimensional feature vector in an evaluation behavior sequence, a video feature vector library is generated, and a feature vector model of the video sequence is established. The convolutional neural networks (CNN), residual networks, and attention mechanisms are integrated to learn the deep connections between video feature vectors and to predict the candidate video sets. The candidate set is expanded by cosine similarity, and a dynamic interest model is established to filter and sort it. Experiments on the Movie-1M dataset show that this method can effectively improve the accuracy and recall rate of video recommendation, which verifies the feasibility and effectiveness of the method.

Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos.

We present the outcomes of a recent large-scale subjective study of Mobile Cloud Gaming Video Quality Assessment (MCG-VQA) on a diverse set of gaming videos. Rapid advancements in cloud services, faster video encoding technologies, and increased access to high-speed, low-latency wireless internet have all contributed to the exponential growth of the Mobile Cloud Gaming industry. Consequently, the development of methods to assess the quality of real-time video feeds to end-users of cloud gaming platforms has become increasingly important. However, due to the lack of a large-scale public Mobile Cloud Gaming Video dataset containing a diverse set of distorted videos with corresponding subjective scores, there has been limited work on the development of MCG-VQA models. Towards accelerating progress towards these goals, we created a new dataset, named the LIVE-Meta Mobile Cloud Gaming (LIVE-Meta-MCG) video quality database, composed of 600 landscape and portrait gaming videos, on which we collected 14,400 subjective quality ratings from an in-lab subjective study. Additionally, to demonstrate the usefulness of the new resource, we benchmarked multiple state-of-the-art VQA algorithms on the database. The new database will be made publicly available on our website: https://live.ece.utexas.edu/research/LIVE-Meta-Mobile-Cloud-Gaming/index.html.

Videoconferencing psychotherapy from a psychodynamic point of view. A qualitative analysis.

There is a growing interest in delivering videoconferencing psychotherapy (VCP) due to the enormous impact of the COVID-19 pandemic on our lives since the beginning of severe restrictions worldwide in March 2020. Scientific literature has provided interesting results about the transition to remote sessions and its implications, considering different psychotherapy orientations. Less is known about whether and how VCP affects psychodynamic psychotherapeutic approaches and reports on remote work with severe and complex mental health problems such as severe personality disorders are still scarce. The aim of the study was to examine the experiences of psychodynamic psychotherapists, mainly delivering Transference-Focused Psychotherapy (TFP), with the transition and delivery of VCP during the first wave of the COVID-19 pandemic. Four hundred seventy-nine licensed psychotherapists completed an online survey during the peak of the pandemic. Survey data were analyzed using qualitative analysis. Results are presented and discussed concerning advantages and disadvantages regarding the access to psychotherapy, the specificity of the online video setting, bodily aspects, the quality of the therapeutic relationship, the therapeutic process including technical aspects and therapist's experience. Furthermore, we analyzed and discussed the statements concerning transference and countertransference reactions differentiating between high-level borderline and neurotic patients and low-level borderline patients. Our results support the importance to identify patients who potentially benefit from VCP. Further research including more prospective randomized controlled trials are needed to investigate the therapeutic implications of the findings.

Review on Human Activity Recognition for Military Restricted Areas

Abstract: Human Activity Recognition(HAR) is an active field of research and scientific development in which various models have been proposed using different methods for identification and categorization of activities using Machine Learning. HAR has reached a remarkable milestone in the area of computer vision. Except for applications in human-computer interactions, surveillance systems and robotics, lately it has extended its applicability in the fields of healthcare, multimedia retrieval, social networking, and education as well. It aims to bring latest technologies together to develop complex assistive system with adaptive capability and learning behaviour. HAR interprets human motion using computer and machine vision technologies to identify and detect simple and complex actions in real-world. This paper presents research made for surveillance of restricted military areas. Our scope is to develop a live monitoring system for tracking the illegal activities done in the restricted area for border security, which is an issue of concern since decades. In this we have introduced a deep learning model that learns to classify human actions without having prior knowledge. The features of image or video set are extracted and detected for detected for classifying whether the activity is illegal or not. Many harmful actions can be avoided or at least have their negative effects reduced as a result of the adoption of this concept. Finally, the activity recognition rate showed a good performance as a result of these findings

A Large Video Set of Natural Human Actions for Visual and Cognitive Neuroscience Studies and Its Validation with fMRI.

The investigation of the perception of others' actions and underlying neural mechanisms has been hampered by the lack of a comprehensive stimulus set covering the human behavioral repertoire. To fill this void, we present a video set showing 100 human actions recorded in natural settings, covering the human repertoire except for emotion-driven (e.g., sexual) actions and those involving implements (e.g., tools). We validated the set using fMRI and showed that observation of the 100 actions activated the well-established action observation network. We also quantified the videos' low-level visual features (luminance, optic flow, and edges). Thus, this comprehensive video set is a valuable resource for perceptual and neuronal studies.

An examination of collegiate musicians’ ability to discern conductor intent

The purpose of this two-experiment study was to examine collegiate musicians’ ability to discern conductor intent. In Experiment 1, participants ( N = 44) viewed two videos of Sir Simon Rattle conducting an ensemble performing an excerpt of the Finale to Gustav Mahler’s Symphony No. 2. One video featured the original performance, whereas the other video was synchronized with a different audio recording from a video of a performance led by Leonard Bernstein. When asked whether any of the two videos were mismatched, results indicated that the proportion of correct responses among our participants differed significantly from chance. In Experiment 2, participants ( N = 127) watched two sets of videos, either matched (unaltered) or mismatched versions of videos featuring Sir Simon Rattle and Leonard Bernstein, and were asked to rate how well the musical intent of the conductor matched the performance of the ensemble they viewed. Although we found a nonsignificant overall result ( p = .053) when comparing the matched and mismatched videos, we found a significant difference in participants’ ratings between the matched and mismatched Rattle videos, but not for those featuring Bernstein. Our findings suggest that a conductor’s visual contribution to the performance can enhance or detract from the observers’ musical experience.

Application of QBA to Assess the Emotional State of Horses during the Loading Phase of Transport.

To identify feasible indicators to evaluate animals' emotional states as a parameter to assess animal welfare, the present study aimed at investigating the accuracy of free choice profiling (FCP) and fixed list (FL) approach of Qualitative Behaviour Assessment (QBA) in horses during the loading phase of transport. A total of 13 stakeholders were trained to score 2 different sets of videos of mixed breed horses loaded for road transport, using both FCP and FL, in 2 sessions. Generalized Procustes Analysis (GPA) consensus profile explained a higher percentage of variation (80.8%) than the mean of 1000 randomized profiles (41.2 ± 1.6%; p = 0.001) for the FCP method, showing an excellent inter-observer agreement. GPA identified two main factors, explaining 65.1% and 3.7% of the total variation. Factor 1 ranging from 'anxious/ to 'calm/relaxed', described the valence of the horses' emotional states. Factor 2, ranging from 'bright' to 'assessing/withdrawn', described the arousal. As for FL, Principal Component Analysis (PCA) first and second components (PC1 and PC2, respectively), explaining on average 59.8% and 12.6% of the data variability, had significant agreement between observers. PC1 ranges from relaxed/confident to anxious/frightened, while PC2 from alert/inquisitive to calm. Our study highlighted the need for the use of descriptors specifically selected, throughout a prior FCP process for the situation we want to evaluate to get a good QBA accuracy level.

Continuous real-time cow identification by reading ear tags from live-stream video

In precision dairy farming there is a need for continuous and real-time availability of data on cows and systems. Data collection using sensors is becoming more common and it can be difficult to connect sensor measurements to the identification of the individual cow that was measured. Cows can be identified by RFID tags, but ear tags with identification numbers are more widely used. Here we describe a system that makes the ear tag identification of the cow continuously available from a live-stream video so that this information can be added to other data streams that are collected in real-time. An ear tag reading model was implemented by retraining and existing model, and tested for accuracy of reading the digits on cows ear tag images obtained from two dairy farms. The ear tag reading model was then combined with a video set up in a milking robot on a dairy farm, where the identification by the milking robot was considered ground-truth. The system is reporting ear tag numbers obtained from live-stream video in real-time. Retraining a model using a small set of 750 images of ear tags increased the digit level accuracy to 87% in the test set. This compares to 80% accuracy obtained with the starting model trained on images of house numbers only. The ear tag numbers reported by real-time analysis of live-stream video identified the right cow 93% of the time. Precision and sensitivity were lower, with 65% and 41%, respectively, meaning that 41% of all cow visits to the milking robot were detected with the correct cow’s ear tag number. Further improvement in sensitivity needs to be investigated but when ear tag numbers are reported they are correct 93% of the time which is a promising starting point for future system improvements.

Preliminary feasibility of animated video education designed to empower patients' referral to kidney transplantation.

Referral for kidney transplantation is influenced by patient education; digital technologies can enhance broad information accessibility. This single-group study tested the feasibility and acceptability of patient-centered self-directed educational animated videos to improve mediators of kidney transplant referral. Community-based adults with chronic kidney disease stage ≥4 invited from a clinical registry or self-responding to flyers viewed eight sequential videos (19:36min total duration) remotely on their own device. Change in kidney transplant knowledge, concerns, and confidence talking about kidney transplantation to doctors was assessed with self-report surveys before and immediately after viewing. Program feedback was assessed by survey and self-selected exit interview. Viewers of the video set (n=50) demonstrated increases in mean kidney transplantation knowledge by +22%, confidence discussing with their doctor by +6%, and reductions in concerns by -2%. Knowledge results were consistent across age, race, and literacy level. Over 90% indicated positive ratings on understanding, engaging, and helpfulness. In post-study interviews viewers indicated the videos promoted confidence in obtaining a kidney transplant and none reported that the 19-min duration of the home education was too long. The animated video education is promising to improve diverse individuals' knowledge, concerns, and communication confidence about kidney transplantation and is highly acceptable.

Scale Up Project Evaluating Responsiveness to Home Exercise And Lifestyle Tele-Health (SUPER-HEALTH): Preliminary Findings

<h3>Research Objectives</h3> To evaluate the effectiveness of a home-based movement-to-music (M2M) exercise program for increasing physical activity among adults with mobility disabilities. <h3>Design</h3> Preliminary analysis of data from an RCT. <h3>Setting</h3> All outcome measures and delivery of the interventions were entirely performed online. <h3>Participants</h3> 200 participants (mean age of 52±12) completed (1) the 24-week intervention and (2) the baseline and 24-week physical activity recall questionnaire. The participants predominantly consisted of women (80%) and Caucasians (60%). The participants presented various types of disability (e.g., multiple sclerosis, arthritis, spinal cord injury) and a wide range of mobility limitations. <h3>Interventions</h3> The 48-week study consisted of a 24-week M2M program (48 to 150 minutes/week for 3x/week) and a 12-week follow-up period. The M2M program was designed to improve fitness and function. A series of movements with music targeted specific training components (flexibility, muscle strength, cardiorespiratory fitness, balance). Three levels of functional variations were provided for standing, seated, and hemiparesis. Participants received a tablet that contains a customized study app. The app released a set of pre-recorded exercise videos each week. <h3>Main Outcome Measures</h3> Physical activity was measured using the health contribution score of the Godin Leisure-Time Exercise Questionnaire (a sum of the weighted moderate and vigorous physical activity scores). <h3>Results</h3> The effect of the M2M intervention on physical activity post-trial was determined using analysis of covariance with condition (group: intervention or control) as the between-subject factor, and corresponding pre-trial outcome scores were the covariate. There was a significant effect of the intervention on physical activity outcome (intervention: 18.15±19.71, n=127; control: 12.29±14.81, n=73; p=0.014). <h3>Conclusions</h3> Our results provide preliminary evidence that the M2M intervention might improve physical activity (moderate-to-vigorous intensity) in people with mobility disabilities. Such findings are important considering that physical activity is a modifiable behavior with the potential long-term benefits for the prevention and management of secondary health conditions and comorbidities among those with mobility disabilities. <h3>Author(s) Disclosures</h3> The authors declared no potential conflicts of interest with respect to the research, authorship and/or publication of this abstract.

Video speeding can be efficient and speeding-induced preference cost can be lessened by selective speeding.

Over the past decade, screen-captured instructional videos have become popular tools for learning. Viewers wanting to learn efficiently can play these videos at faster-than-normal speeds, a feature offered by hosting services such as YouTube. Although previous research suggests that moderate speeding may not lessen learning, little research has tested this form of media for speeding-induced learning impairments. Further, even if learning is not impaired by speeding, the degree to which users find speed increases taxing and/or unpleasant is unknown. We therefore created a set of screen-captured instructional videos and tested whether speeding them by up to 250% affected learning, perceived workload, and preferences. Speed increases of up to 200% minimally affected learning, but even modest 150% speed increases substantially increased perceived workload and reduced viewer preferences. However, we were able to create videos that were more selectively speeded by concentrating speeding on pauses and relatively unimportant and slow speech. These videos were just as time efficient as the 150% speeded videos, but viewers preferred them. Our findings demonstrate that speeded instructional videos have the potential to facilitate efficient learning, and they suggest techniques such as selective speeding that may be used to support efficiency while lessening viewer preference costs. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Shared decision-making during childbirth in maternity units: the VIP mixed-methods study

BackgroundNHS policy emphasises shared decision-making during labour and birth. There is, however, limited evidence concerning how decision-making happens in real time.ObjectivesOur objectives were as follows – create a data set of video- and audio-recordings of labour and birth in midwife-led units; use conversation analysis to explore how talk is used in shared decision-making; assess whether or not women’s antenatal expectations are reflected in experiences and whether or not the interactional strategies used (particularly the extent to which decisions are shared) are associated with women’s postnatal satisfaction; and disseminate findings to health-care practitioners and service users to inform policy on communication in clinical practice.DesignThis was a mixed-methods study. The principal method was conversation analysis to explore the fine detail of interaction during decision-making. Derived from the conversation analysis, a coding frame was developed to quantify interactions, which were explored alongside questionnaire data concerning women’s antenatal expectations and preferences, and women’s experiences of, and postnatal satisfaction with, decision-making. Semistructured interviews with health-care practitioners explored factors shaping decision-making.Setting and participantsThe study took place in midwife-led units at two English NHS trusts. A total of 154 women (aged ≥ 16 years with low-risk pregnancies), 158 birth partners and 121 health-care practitioners consented to be recorded. Of these participants, 37 women, 43 birth partners and 74 health-care practitioners were recorded.Key findingsMidwives initiate the majority of decisions in formats that do not invite women’s participation (i.e. beyond consenting). The extent of optionality that midwives provide varies with the decision. Women have most involvement in decisions pertaining to pain relief and the third stage of labour. High levels of satisfaction are reported. There is no statistically significant relationship between midwives’ use of different formats of decision-making and any measures of satisfaction. However, women’s initiation of decisions, particularly relating to pain relief (e.g. making lots of requests), is associated with lower satisfaction.LimitationsOur data set is explored with a focus on decision initiation and responses, leaving other important aspects of care (e.g. midwives’ and birth partners’ interactional techniques to facilitate working with pain) underexplored, which might be implicated in decision-making. Despite efforts to recruit a diverse sample, ethnic minority women are under-represented.ConclusionsPolicy initiatives emphasising patient involvement in decision-making are challenging to enact in practice. Our findings illustrate that women are afforded limited optionality in decision-making, and that midwives orient to guidelines/standard clinical practice in pursuing particular decisional outcomes. Nonetheless, the majority of women were satisfied with their experiences. However, when women needed to pursue decisions, particularly concerning pain relief, satisfaction is lower. Conversation analysis demonstrates that such ‘women-initiated’ decision-making occurs in the context of midwives’ avoiding pharmacological methods of pain relief at particular stages of labour.Future researchWe suggest that future research address the following – the barriers to inclusion of ethnic minority research participants, decision-making in obstetric units, systematic understanding of how pain relief decisions are pursued/resolved, conversation analysis of interactional elements beyond the specific decision-making context, interactional ‘markers’ of the emotional labour and inclusion of antenatal encounters.Trial registrationThis trial is registered as ISRCTN16227678 and National Institute for Health and Care Research (NIHR) CRN Portfolio (CMPS):32505 and IRAS:211358.FundingThis project was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme and will be published in full inHealth and Social Care Delivery Research; Vol. 10, No. 36. See the NIHR Journals Library website for further project information.

Developing a video expert panel as a reference standard to evaluate respiratory rate counting in paediatric pneumonia diagnosis: protocol for a cross-sectional study

IntroductionManual counting of respiratory rate (RR) in children is challenging for health workers and can result in misdiagnosis of pneumonia. Some novel RR counting devices automate the counting of RR...

Egocentric video co-summarization using transfer learning and refined random walk on a constrained graph

In this paper, we address the problem of egocentric video co-summarization. We show how a shot level accurate summary can be obtained in a time-efficient manner using random walk on a constrained graph in transfer learned feature space with label refinement. While applying transfer learning, we propose a new loss function capturing egocentric characteristics in a pre-trained ResNet on the set of auxiliary egocentric videos. Transfer learning is used to generate i) an improved feature space and ii) a set of labels to be used as seeds for the test egocentric video. A complete weighted graph is created for a test video in the new transfer learned feature space with shots as the vertices. We derive two types of cluster label constraints in form of Must-Link (ML) and Cannot-link (CL) based on the similarity of the shots. ML constraints are used to prune the complete graph which is shown to result in substantial computational advantage, especially, for the long duration videos. We derive expressions for the number of vertices and edges for the ML-constrained graph and show that this graph remains connected. Random walk is applied to obtain labels of the unmarked shots in this new graph. CL constraints are applied to refine the cluster labels. Finally, shots closest to individual cluster centres are used to build the summary. Experiments on the short duration videos as in CoSum and TVSum datasets and long duration videos as in ADL and EPIC-Kitchens datasets clearly demonstrate the advantage of our solution over several state-of-the-art methods.

Real-Time Ship Segmentation in Maritime Surveillance Videos Using Automatically Annotated Synthetic Datasets.

This work proposes a new system capable of real-time ship instance segmentation during maritime surveillance missions by unmanned aerial vehicles using an onboard standard RGB camera. The implementation requires two stages: an instance segmentation network able to produce fast and reliable preliminary segmentation results and a post-processing 3D fully connected Conditional Random Field, which significantly improves segmentation results by exploring temporal correlations between nearby frames in video sequences. Moreover, due to the absence of maritime datasets consisting of properly labeled video sequences, we create a new dataset comprising synthetic video sequences of maritime surveillance scenarios (MarSyn). The main advantages of this approach are the possibility of generating a vast set of images and videos, being able to represent real-world scenarios without the necessity of deploying the real vehicle, and automatic labels, which eliminate human labeling errors. We train the system with the MarSyn dataset and with aerial footage from publicly available annotated maritime datasets to validate the proposed approach. We present some experimental results and compare them to other approaches, and we also illustrate the temporal stability provided by the second stage in missing frames and wrong segmentation scenarios.

An efficient fire and smoke detection algorithm based on an end-to-end structured network

Detection transformer (DETR) combines convolutional neural network (CNN) with transformer, providing a more advanced idea. In this paper, an object detection model based on DETR is proposed for fire and smoke detection. Compared with other methods that based on deep learning, the proposed one simplifies the pipeline of detection and builds an end-to-end detector. At the same time, the original DETR model usually requires long training time and large amount of computation, resulting in relatively poor performance in detection speed and accuracy, and it shows to be not friendly for small or early fire detection. Therefore, when designing the proposed network model, a normalization-based attention module is added in the feature extraction stage to highlight the effective features, being beneficial to the process of encoding. A multiscale deformable attention is also used in the encoder–decoder structure, accelerating therefore, the process of convergence during the training of the model, which includes the enhancement of the detection of small objects. Also, considering the cost of computation, the number of layers in the encoder–decoder structure is redefined to reduce the complexity of the model, and that also reduces the requirements of the application equipment. Detailed experiments are conducted on three self-built datasets and two public video sets. The results show that, the proposed method has an excellent performance on all of the datasets considered here.

TikTok on the clock but the #fitspo don’t stop: The impact of TikTok fitspiration videos on women’s body image concerns

Fitspiration is a popular social media trend that aims to inspire individuals to improve their health and fitness through diet and exercise. However, viewing fitspiration content on Instagram has been identified as a contributor to negative body image, especially for young women. With the growing popularity of the video sharing platform TikTok and concerns over its content, the present study aimed to experimentally examine the effect of exposure to fitspiration TikTok videos on young women’s body dissatisfaction, appearance comparison and mood. The roles of state appearance comparison as a mediator and trait fit ideal internalisation as a moderator were also considered. Young women (18–25, N = 120) from Australia were randomly allocated to view a set of fitspiration videos or a set of art control videos from TikTok. Results indicated that exposure to fitspiration TikTok videos increased state appearance comparison and state negative mood relative to art TikTok videos but did not directly increase state body dissatisfaction. State appearance comparison significantly mediated the effect of TikTok videos on body dissatisfaction and mood, however, there was no moderating effect of trait fit ideal internalisation. These findings highlight the importance of state appearance comparison in relation to viewing fitspiration content on TikTok.

Video-Based Automatic Wrist Flexion and Extension Classification

A computer vision method was developed to automatically measure wrist flexion and extension from a 2-D video for occupational health and safety research. Marker-less tracked skeletal joints of the elbow, wrist, and hand estimated the wrist flexion/extension angle between the hand and forearm. Based on the estimated angles, wrist posture was classified as flexion (palmar bending), neutral (no bending), or extension (dorsal bending) for each cycle of hand movement. Applying to a set of laboratory videos of a simulated repetitive motion task, we demonstrated the feasibility of using this algorithm for assessing the state of hand activities during manual work. Tested on 1464 frames from 61 recorded videos for 16 participants, the algorithm achieved an average performance of 72.40% correct, per-class accuracy. The sensitivity and specificity for flexion were 66.16% and 91.47%, respectively. The sensitivity and specificity for extension were 77.12% and 89.72%, respectively. This compared favorably against a previously reported consistency rate of 57% between human analyst estimates and wrist electrogoniometer measured wrist flexion/extension angles. We also applied this technique to 262 video frames of hand flexion instances selected from industrial field video data. For these videos, the average correct per-class accuracy was 76.03% in comparison to human observers. The sensitivity and specificity for flexion were 69.23% and 94.17%, respectively, and the sensitivity and specificity for extension were 91.95% and 80.57%, respectively.

Multiview PCA: A Methodology of Feature Extraction and Dimension Reduction for High-Order Data.

Facing with rapidly increasing demands for analyzing high-order data or multiway data, feature-extracting methods become imperative for analysis and processing. The traditional feature-extracting methods, however, either need to overly vectorize the data and smash the original structure hidden in data, such as PCA and PCA-like methods, which is unfavorable to the data recovery, or cannot eliminate the redundant information very well, such as tucker decomposition (TD) and TD-like methods. To overcome these limitations, we propose a more flexible and more powerful tool, called the multiview principal components analysis (Multiview-PCA) in this article. By segmenting a random tensor into equal-sized subarrays called sections and maximizing variations caused by orthogonal projections of these sections, the Multiview-PCA finds principal components in a parsimonious and flexible way. In so doing, two new operations on tensors, the S -direction inner/outer product, are introduced to formulate tensor projection and recovery. With different segmentation ways characterized by section depth and direction, the Multiview-PCA can be implemented many times in different ways, which defines the sequential and global Multiview-PCA, respectively. These multiple Multiview-PCA take the PCA and PCA-like, and TD and TD-like as the special cases, which correspond to the deepest section depth and the shallowest section depth, respectively. We propose an adaptive depth and direction selection algorithm for the implementation of Multiview-PCA. The Multiview-PCA is then tested in terms of subspace recovery ability, compression ability, and feature extraction performance when applied to a set of artificial data, surveillance videos, and hyperspectral imaging data. All numerical results support the flexibility, effectiveness, and usefulness of Multiview-PCA.

Cocreating with Young Fathers: Producing Community-Informed Training Videos to Foster more Inclusive Support Environments

Our contribution draws upon a collaborative project called ‘Diverse Dads’, which ran between October 2020 and April 2021, during the 2020–2021 COVID-19 pandemic. The team comprised members of the North East Young Dads and Lads (NEYDL) Project, advisors from support organisations that champion inclusivity, and the Following Young Fathers Further (FYFF) research team. ‘Diverse Dads’ sought to identify and address gaps in service provision for young minoritised dads in the North East, and to promote cross-sector conversations concerning inclusive support for young dads from diverse communities. With support provided remotely by the FYFF team, peer research was undertaken by three young men from NEYDL. Our work highlights how methods of coproduction and cocreation were achieved during the pandemic. NEYDL is also embarking on an ambitious new digital service journey with partners DigiDAD, producing digital outputs that are made by and for young fathers. Working collaboratively, the peer research team and DigiDAD produced a set of videos designed to support training for professionals in mainstream, family, and statutory services. Showcasing one of these creative outputs, our contribution will discuss the continued value of coproduction and cocreation with young people and using creative, digital methods to support productive discussions between young fathers, professionals, and researchers.