1 code implementation • 12 Apr 2024 • Iuliia Kotseruba, John K. Tsotsos
The crux of the problem is lack of public data with annotations that could be used to train top-down models and evaluate how well models of any kind capture effects of task on attention.
1 code implementation • 12 Apr 2024 • Iuliia Kotseruba, John K. Tsotsos
In this paper, we address the challenge of effective modeling of task and context with common sources of data for use in practical systems.
1 code implementation • 13 Oct 2023 • Iuliia Kotseruba, John K. Tsotsos
Therefore, to enable analysis and modeling of these factors for drivers' gaze prediction, we propose the following: 1) we correct the data processing pipeline used in DR(eye)VE to reduce noise in the recorded gaze data; 2) we then add per-frame labels for driving task and context; 3) we benchmark a number of baseline and SOTA models for saliency and driver gaze prediction and use new annotations to analyze how their performance changes in scenarios involving different tasks; and, lastly, 4) we develop a novel model that modulates drivers' gaze prediction with explicit action and context information.
no code implementations • 8 Feb 2023 • Iuliia Kotseruba, Amir Rasouli
Current research on pedestrian behavior understanding focuses on the dynamics of pedestrians and makes strong assumptions about their perceptual abilities.
no code implementations • 14 Nov 2022 • Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
no code implementations • 14 Oct 2022 • Amir Rasouli, Iuliia Kotseruba
To address this challenge, we propose a novel framework that relies on different data modalities to predict future trajectories and crossing actions of pedestrians from an ego-centric perspective.
no code implementations • 10 Jul 2021 • Iuliia Kotseruba, Manos Papagelis, John K. Tsotsos
The results indicate that the distribution of the research topics is similar in industry and academic papers.
1 code implementation • 12 Apr 2021 • Iuliia Kotseruba, John K. Tsotsos
Drivers deal with multiple concurrent tasks, such as keeping the vehicle in the lane, observing and anticipating the actions of other road users, reacting to hazards, and dealing with distractions inside and outside the vehicle.
no code implementations • 5 Jan 2021 • John K. Tsotsos, Omar Abid, Iuliia Kotseruba, Markus D. Solbach
The key conclusions of this paper are that an executive controller is necessary for human attentional function in vision, and that there is a 'first principles' computational approach to its understanding that is complementary to the previous approaches that focus on modelling or learning from experimental observations directly.
2 code implementations • 13 May 2020 • Iuliia Kotseruba, Calden Wloka, Amir Rasouli, John K. Tsotsos
Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets.
1 code implementation • 13 May 2020 • Amir Rasouli, Iuliia Kotseruba, John K. Tsotsos
To this end, we propose a solution for the problem of pedestrian action anticipation at the point of crossing.
no code implementations • 28 Aug 2019 • John K. Tsotsos, Iuliia Kotseruba, Alexander Andreopoulos, Yulong Wu
This reveals a strong mismatch between optimal performance ranges of classical theory-driven algorithms and sensor setting distributions in the common vision datasets, while data-driven models were trained for those datasets.
no code implementations • 15 Jan 2019 • John K. Tsotsos, Iuliia Kotseruba, Calden Wloka
The current dominant visual processing paradigm in both human and machine research is the feedforward, layered hierarchy of neural-like processing elements.
1 code implementation • 20 Dec 2018 • Calden Wloka, Toni Kunić, Iuliia Kotseruba, Ramin Fahimi, Nicholas Frosst, Neil D. B. Bruce, John K. Tsotsos
The Saliency Model Implementation Library for Experimental Research (SMILER) is a new software package which provides an open, standardized, and extensible framework for maintaining and executing computational saliency models.
no code implementations • 29 Jun 2018 • John K. Tsotsos, Iuliia Kotseruba, Amir Rasouli, Markus D. Solbach
It is almost universal to regard attention as the facility that permits an agent, human or machine, to give priority processing resources to relevant stimuli while ignoring the irrelevant.
2 code implementations • CVPR 2018 • Calden Wloka, Iuliia Kotseruba, John K. Tsotsos
However, on static images the emphasis of these models has largely been based on non-ordered prediction of fixations through a saliency map.
no code implementations • 29 Nov 2017 • Calden Wloka, Iuliia Kotseruba, John K. Tsotsos
The accuracy of such models has dramatically increased recently due to deep learning.
no code implementations • 26 Nov 2017 • Iuliia Kotseruba, John K. Tsotsos
In this paper we present STAR-RT - the first working prototype of Selective Tuning Attention Reference (STAR) model and Cognitive Programs (CPs).
no code implementations • 27 Oct 2016 • Iuliia Kotseruba, John K. Tsotsos
Thus, in this survey we wanted to shift the focus towards a more inclusive and high-level overview of the research on cognitive architectures.
no code implementations • 15 Sep 2016 • Iuliia Kotseruba, Amir Rasouli, John K. Tsotsos
In this paper we present a novel dataset for a critical aspect of autonomous driving, the joint attention that must occur between drivers and of pedestrians, cyclists or other drivers.
Robotics