What do parents think of using informational videos to support recruitment for parenting trials? A qualitative study

Background Lower than expected recruitment and retention rates are common challenges in parenting trials—particularly for community-based trials targeting parents of young children that rely on face-to-face recruitment by frontline workers. Recruitment requires parental informed consent, yet information sheets have been criticized for being lengthy and complex, and particularly challenging for parents with low literacy. Recent innovations include ‘talking head’ information videos. This paper aims to explore parent perceptions of using a ‘talking head’ video to support informed consent, recruitment, and retention procedures in parenting trials. Methods We conducted semi-structured interviews with a sample of 24 mothers recruited after their final follow-ups in two different parenting trials in Denmark. Before consenting to participate in the trials, parents were invited to view a video of a member of the study team giving information about the study, and again before the interviews for the current study. The audio data was transcribed and thematic analysis was conducted. Results We identified three overarching themes: (1) general impression of the video, (2) thoughts on participation in research, and (3) recruitment and retention. Participants were generally positive in their appraisal of the two talking head informational videos. We found that participants felt that a mix of paper-based and video-based sources of information would enable them to make an informed choice about whether to participate in a research study. We also found that a professionally produced video featuring a key member of the study team produced a feeling of commitment to the study that could impact retention rates. Conclusions Informational videos are acceptable to parents; however, co-production or participant/patient involvement in the development of such videos is recommended. Informational videos may not increase recruitment but have the potential for improving retention. Key design recommendations are to ensure a ‘professional’ look to the video, to supplement videos with paper-based information, to keep the length to < 3 min, and for the ‘talking head’ part to feature a key member of the study team.

Produce Informative Research Videos

Researchers can usefully produce a spectrum of videos, from simple ones created with a smartphone, to professional-quality video news releases. To be effective, technical videos should be brief, often including links to further information. They should still, however, adhere to high production standards. News videos also have specific length and technical requirements, whether a finished video news release or B roll. Video releases should observe ethical requirements to avoid the appearance of being infomercials. Lecture videos should only be considered if they offer more than a talking head but include engaging and informative visuals. Field research makes a useful subject for both lay and technical videos. All videos should observe basic principles of production quality, planning, scripting, shooting, and editing. Videos can also be syndicated widely to numerous free websites.

Iterative Text-Based Editing of Talking-Heads Using Neural Retargeting

We present a text-based tool for editing talking-head video that enables an iterative editing workflow. On each iteration users can edit the wording of the speech, further refine mouth motions if necessary to reduce artifacts, and manipulate non-verbal aspects of the performance by inserting mouth gestures (e.g., a smile) or changing the overall performance style (e.g., energetic, mumble). Our tool requires only 2 to 3 minutes of the target actor video and it synthesizes the video for each iteration in about 40 seconds, allowing users to quickly explore many editing possibilities as they iterate. Our approach is based on two key ideas. (1) We develop a fast phoneme search algorithm that can quickly identify phoneme-level subsequences of the source repository video that best match a desired edit. This enables our fast iteration loop. (2) We leverage a large repository of video of a source actor and develop a new self-supervised neural retargeting technique for transferring the mouth motions of the source actor to the target actor. This allows us to work with relatively short target actor videos, making our approach applicable in many real-world editing scenarios. Finally, our, refinement and performance controls give users the ability to further fine-tune the synthesized results.

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. In this work, we tackle two key challenges: (i) producing natural head motions that match speech prosody, and (ii)} maintaining the appearance of a speaker in a large head motion while stabilizing the non-face regions. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN). In this way, the predicted head poses act as the low-frequency holistic movements of a talking head, thus allowing our latter network to focus on detailed facial movement generation. To depict the entire image motions arising from audio, we exploit a keypoint based dense motion field representation. Then, we develop a motion field generator to produce the dense motion fields from input audio, head poses, and a reference image. As this keypoint based representation models the motions of facial regions, head, and backgrounds integrally, our method can better constrain the spatial and temporal consistency of the generated videos. Finally, an image generation network is employed to render photo-realistic talking-head videos from the estimated keypoint based motion fields and the input reference image. Extensive experiments demonstrate that our method produces videos with plausible head motions, synchronized facial expressions, and stable backgrounds and outperforms the state-of-the-art.

The Accidental Talking Head: Working with the Media During a Pandemic

Most doctoral programs do not train you to work with the media, though local and national media are the venue through which most timely information is shared with the public. This narrative offers advice on how to prepare yourself for media interviews, shares some best practices, and aims to demystify the process of audio, video, and print media contributions by public health professionals.