Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by John K. Tsotsos
Convergent binocular stereo: Depth perception for humanoid robot vision
Abstract Supplementary Materials REFERENCES AND NOTES Information & Authors Metrics & Citations Check Access References Figures Tables Media Share This article has 0 eLetter . Abstract The design of robotic binocular camera systems has been inspired by human vision, as has their use in humanoid robots. One aspect of this inspiration has yet to play a major role, namely, that humans determine depth using a convergent binocular imaging geometry with both eyes pointing at the same location.
[2511.17595] Boosting Reinforcement Learning in 3D Visuospatial Tasks Through Human-Informed Curriculum Design
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Learning a Model of Shape Selectivity in V4 Cells Reveals Shape Encoding Mechanisms in the Brain
Discussion Our goal was to understand the shape signal transformation in the ventral stream up to V4. The present work used findings of the various visual areas involved in shape processing in this stream along with geometry and machine learning to propose a step-by-step explanation for this transformation. We refrained from using end-to-end deep neural networks because explaining what is learned in each layer of these deep architectures is still an open problem.
Learning a model of shape selectivity in V4 cells reveals shape encoding mechanisms in the brain
Thank you for sharing this Journal of Neuroscience article. NOTE: We request your email address only to inform the recipient that it was you who recommended this article, and that it is not junk mail. We do not retain these email addresses. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas.
When We Study the Ability to Attend, What Exactly Are We Trying to Understand?
Open AccessFeature PaperOpinion by John K.
Correction: Rapid visual categorization is not guided by early salience-based selection
Figs 4, 6 and 7 are incorrect. The authors have provided the corrected versions here. Fig 4. Sensitivity analysis of performance thresholds. The plots show how percentage of points of interest P within the ground truth masks and parafovea gradually decreases depending on how much of the GTM (by area) is inside the parafovea. On each plot the point (0,0) corresponds to measure B (i.e. P is within the GTM and parafovea regardless of the amount of GTM within the parafovea).
Feed-forward visual processing suffices for coarse localization but fine-grained localization in an attention-demanding context needs feedback processing
Loading metrics Open Access Peer-reviewed Research Article Sang-Ah Yoo , John K. Tsotsos, Mazyar Fallah Sang-Ah Yoo, John K. Tsotsos, Mazyar Fallah Published: September 26, 2019 https://doi.org/10.1371/journal.pone.0223166 Figures Abstract It is well known that simple visual tasks, such as object detection or categorization, can be performed within a short period of time, suggesting the sufficiency of feed-forward visual processing.
Why vision is not both hierarchical and feedforward
In classical models of object recognition, first, basic features (e.g., edges and lines) are analyzed by independent filters that mimic the receptive field profiles of V1 neurons. In a feedforward fashion, the outputs of these filters are fed to filters at the next processing stage, pooling information across several filters from the previous level, and so forth at subsequent processing stages. Low-level processing determines high-level processing.
[1808.03305] The Elephant in the Room
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with John K.
Contact John K., search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack