Publications
Webpage template modified from here
Iuliia (Yulia) Kotseruba
Postdoctoral Visitor, York University
I am a Postdoctoral Visitor at the Lab for Active and Attentive Vision at York University.
I am interested in building AI systems inspired by knowledge about human vision and cognition for various applications, such as intelligent transportation, saliency prediction, and video game playing. My work focuses on applying domain knowledge, data analysis, and benchmarking to develop better models and identify open problems.
Projects
-
Attention and Driving
- A curated list of papers (with code links) on how drivers observe the traffic scene
Top-down models of drivers' attention and extended annotations for DR(eye)VE, BDD-A, and LBW (code and data) -
Cognitive Architectures
- A survey of 84 cognitive architectures developed in the past 40 years
-
Pedestrian Behavior Understanding
- Two datasets (JAAD and PIE) for studying pedestrian crossing behavior
Models for predicting trajectory (PIEtraj) and crossing action (SF-GRU,PCPA) -
Odd-One-Out Benchmark
- A collection of synthetic and natural images with odd-one-out (singleton) objects and metrics for evaluating saliency algorithms
-
Saccade Generator for Static Images
- A model for generating sequences of fixations for any image -- STAR-FC(C++) and pySTAR-FC (Python)