Don’t Look at the Camera: Achieving eye contact in video conferencing platforms

Eye contact and gaze are important social cues as they convey information about attention, awareness, emotion and intent. For single subjects photographed by a camera, conventional wisdom tells us that looking directly into the camera achieves eye contact. Is this actually correct? The answer is fundamental in times of increasingly intensive use of video conferencing platforms like Zoom, Microsoft Teams and Google Meet, where, in the absence of in-person non verbal cues, eye-contact can promote positive social interaction. In this study we used subjective and objective measures to assess where subjects should direct their gaze relative to a camera lens to optimize perception of eye contact by an external observer (e.g., a person on the other side of a video call). We collected pictures of 4 actors looking at 11 vertically displaced points (including straight-ahead at the camera) and verified their point of gaze using an eye-tracker. These pictures were then presented to 17 participants who were asked to rate their subjective perception of eye contact as well as whether the actor seemed to be looking up or down. Results suggest that looking just below the camera (~2°) appears to be ideal for achieving the perception of eye contact. We discuss the implications of the current study, offer insights into future directions and explore considerations for correcting for the perception of eye contact in video conferencing platforms.

Authors

Institutions

Publication Details

Journal
Journal of Vision
Published
2024-09-15
DOI
https://doi.org/10.1167/jov.24.10.1094
Primary Topic
Virtual Reality Applications and Impacts
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Don’t Look at the Camera: Achieving eye contact in video conferencing platforms

Samyukta Jayakumar, Brian Curless, Steve Seitz, Aaron R. Seitz et al.
Journal of Vision
Virtual Reality Applications and Impacts
article

Don’t Look at the Camera: Achieving eye contact in video conferencing platforms

Samyukta Jayakumar, Brian Curless, Steve Seitz, Aaron R. Seitz, Alice L. L. Gao, Marcello Maniglia, Ira Kemelmacher
article en

Abstract

Eye contact and gaze are important social cues as they convey information about attention, awareness, emotion and intent. For single subjects photographed by a camera, conventional wisdom tells us that looking directly into the camera achieves eye contact. Is this actually correct? The answer is fundamental in times of increasingly intensive use of video conferencing platforms like Zoom, Microsoft Teams and Google Meet, where, in the absence of in-person non verbal cues, eye-contact can promote positive social interaction. In this study we used subjective and objective measures to assess where subjects should direct their gaze relative to a camera lens to optimize perception of eye contact by an external observer (e.g., a person on the other side of a video call). We collected pictures of 4 actors looking at 11 vertically displaced points (including straight-ahead at the camera) and verified their point of gaze using an eye-tracker. These pictures were then presented to 17 participants who were asked to rate their subjective perception of eye contact as well as whether the actor seemed to be looking up or down. Results suggest that looking just below the camera (~2°) appears to be ideal for achieving the perception of eye contact. We discuss the implications of the current study, offer insights into future directions and explore considerations for correcting for the perception of eye contact in video conferencing platforms.

Journal of VisionVol. 24(10)
University of California, Riverside (US), Northeastern University (US), University of Washington (US), Seattle University (US)
Reduced inequalities
Openalex Percentile: Top 84%
Virtual Reality Applications and Impacts
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.