What are they looking for?

1969

Citations in the corpus

• Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Mutual gaze estimation [54,150–152,172,176] and gaze following [37,65,111,186] are also relevant.”
• Dual Attention Guided Gaze Target Detection in the Wild (2021, methodology): “Existing methods [37, 28, 5, 6, 46] typically reason about salient objects in the scene conditioned on an estimated gaze orientation.”
• Oops! Predicting Unintentional Action in Video (2019, background): “Moreover, performance is comparatively low when the person in the video has limited visibility, such as due to occlusions, which motivates further work in gaze estimation [47, 29], especially in video.”
• Human Gaze Assisted Artificial Intelligence: A Review (2020, background): “Alterna-tively, a related line of research named gaze following models the gaze of people inside images or videos [Recasens et al. , 2015; Recasens et al. , 2017].”
• It Takes Two to Tango: Towards Theory of AI's Mind (2017, methodology): “We instantiate these ideas in the domain of Visual Question Answering (VQA).”
• Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze (2020, background): “(Recasens et al. 2015) proposed a two-stream CNN to find the position where people in the image are looking at.”
• Detecting Attended Visual Targets in Video (2020, methodology): “[46] adapt the method of [42] to a human-robot interaction task.”
• LAEO-Net: Revisiting People Looking at Each Other in Videos (2019, background): “Gaze [23] and head pose [6] are powerful tools to deal with the problem of determining the visual focus of attention (VFoA) in a scene, i.”
• Eye Tracking for Everyone (2016, methodology): “The recent success of deep learning has been apparent in a variety of domains in computer vision [20, 7, 36, 28, 19], but its impact on improving the performance of eye tracking has been rather limited [43].”