Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion
By Parag Kumar Mital, Tim J. Smith, Robin L. Hill, J. Henderson. Cognitive Computation, 2011
464 citations recorded by the source corpus.
Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Human-Computer Interaction
View Paper: https://www.semanticscholar.org/paper/27266e3be4d9b9572e8e11f4ef34110a2a00f515
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Ming-Ming Cheng
- Jianbing Shen
- Ali Borji
- Wenguan Wang
- Haibin Ling
- Shenghua Gao
- Kristen Grauman
- Fang Guo
In Computer Vision and Pattern Recognition
- Wenguan Wang
- Jianbing Shen
- Ming-Ming Cheng
- Ling Shao
- Ming-Hsuan Yang
- Haibin Ling
- Luc Van Gool
- Ali Borji
In Human-Computer Interaction
- Jianbing Shen
- Wenguan Wang
- Ming-Ming Cheng
- Kenneth Holmqvist
- Haibin Ling
- Ali Borji
- Kristen Grauman
- Yu-Chuan Su
Citations in the corpus
- Revisiting Video Saliency Prediction in the Deep Learning Era (2021, methodology): “Previous investigations [35], [58], [86] suggested that motion is a key factor that directs attention allocation in dynamic viewing.”
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, methodology): “CRCNS [25] 2004 50 640× 480 6-94 15 task-goal Hollywood-2 [43] 2012 1,707 720× 480 2-120 19 task-goal UCF sports [43] 2012 150 720× 480 2-14 19 task-goal DIEM [44] 2011 84 1280× 720 27-217 ∼50 free-view SFU [17] 2012 12 352× 288 3-10 15 free-view DHF1K(Ours) 2017 1,000 640× 360 17-42 17 free-view”
- Detecting Engagement in Egocentric Video (2016, background): “By contrast, clips in popular third-person saliency datasets are typically 20 seconds [23] to 2 minutes [42], since the interest is in gauging instantaneous gaze reactions.”
- Differential privacy for eye-tracking data (2019, methodology): “Other similar approaches involve gaze represented as height maps [9; 30] or Gaussian Mixture Models [24].”
- Gaze Prediction in Dynamic 360° Immersive Videos (2018, background): “Some work also attempts to use low-level appearance and motion cues as inputs or extend deep learning approaches to more complex scenarios such as stereo images [9] or videos [4] [7] [11] [31] [35] [32] [16] [12] [6] [18].”
- Processing of native and foreign language subtitles in films: An eye tracking study (2012, methodology): “Saliency maps have been used to understand the deployment of visual attention in static scene perception (Itti & Koch, 2000, 2001) and more recently in the area of dynamic scene perception (Mital, Smith, Hill, & Henderson, 2010).”