Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Benchmarking (2)
- Fixations (2)
- Free-viewing (2)
- Saliency (2)
- Aperture problem (1)
-
- Bayesian Utility Theory (1)
- Bayesian model (1)
- Binocular vision (1)
- Compositional approach (1)
- Deep learning (1)
- Feature selection (1)
- Human activity recognition (1)
- Information theory (1)
- Liquids (1)
- Material perception (1)
- Metrics (1)
- Model comparison (1)
- Model-Comparison (1)
- Motion perception (1)
- Pattern theory (1)
- Scanpaths (1)
- Video event understanding (1)
Articles 1 - 6 of 6
Full-Text Articles in Physical Sciences and Mathematics
Evaluating Models Of Scanpath Prediction, Matthias Kümmerer, Matthias Bethge
Evaluating Models Of Scanpath Prediction, Matthias Kümmerer, Matthias Bethge
MODVIS Workshop
No abstract provided.
Selecting Maximally-Predictive Deep Features To Explain What Drives Fixations In Free-Viewing, Matthias Kümmerer, Thomas S.A. Wallis, Matthias Bethge
Selecting Maximally-Predictive Deep Features To Explain What Drives Fixations In Free-Viewing, Matthias Kümmerer, Thomas S.A. Wallis, Matthias Bethge
MODVIS Workshop
No abstract provided.
Consistent Saliency Benchmarking: How One Model Can Win On All Metrics, Matthias Kümmerer, Thomas S.A. Wallis, Matthias Bethge
Consistent Saliency Benchmarking: How One Model Can Win On All Metrics, Matthias Kümmerer, Thomas S.A. Wallis, Matthias Bethge
MODVIS Workshop
No abstract provided.
Shape Features Underlying The Perception Of Liquids, Jan Jaap R. Van Assen, Pascal Barla, Roland W. Fleming
Shape Features Underlying The Perception Of Liquids, Jan Jaap R. Van Assen, Pascal Barla, Roland W. Fleming
MODVIS Workshop
No abstract provided.
Video Event Understanding With Pattern Theory, Fillipe Souza, Sudeep Sarkar, Anuj Srivastava, Jingyong Su
Video Event Understanding With Pattern Theory, Fillipe Souza, Sudeep Sarkar, Anuj Srivastava, Jingyong Su
MODVIS Workshop
We propose a combinatorial approach built on Grenander’s pattern theory to generate semantic interpretations of video events of human activities. The basic units of representations, termed generators, are linked with each other using pairwise connections, termed bonds, that satisfy predefined relations. Different generators are specified for different levels, from (image) features at the bottom level to (human) actions at the highest, providing a rich representation of items in a scene. The resulting configurations of connected generators provide scene interpretations; the inference goal is to parse given video data and generate high-probability configurations. The probabilistic structures are imposed using energies that …
Binocular 3d Motion Perception As Bayesian Inference, Martin Lages, Suzanne Heron
Binocular 3d Motion Perception As Bayesian Inference, Martin Lages, Suzanne Heron
MODVIS Workshop
The human visual system encodes monocular motion and binocular disparity input before it is integrated into a single 3D percept. Here we propose a geometric-statistical model of human 3D motion perception that solves the aperture problem in 3D by assuming that (i) velocity constraints arise from inverse projection of local 2D velocity constraints in a binocular viewing geometry, (ii) noise from monocular motion and binocular disparity processing is independent, and (iii) slower motions are more likely to occur than faster ones. In two experiments we found that instantiation of this Bayesian model can explain perceived 3D line motion direction under …