Adil Kaan Akan

I am a PhD candidate at Koc University, where I work on computer vision and machine learning.

At KUIS AI Lab, I am working on weakly-supervised temporal action detection and video understanding, under the supervision of Prof. Yücel Yemez.

Previously, I recevied my Master's degree (Thesis) from KUIS AI Lab, Koc University, my Bachelor's from Department of Computer Engineering, Middle East Technical University. I have received "Academic Excellence Award" at Koc University for my contributions to the research and academic standing.

Email  /  CV  /  Bio  /  Google Scholar  /  Twitter  /  Github

I'm interested in computer vision, machine learning, with a special interest in temporal problems and generative models such as temporal action detection, future prediction, video understanding and generative models.

We propose a novel method for trajectory prediction that can adapt itself into every agent in the shared scene. We exploit dynamic weight learning to adapt each agent's state separately to predict their future trajectories simultaneously without rotating and normalizing the scene frame. Our results achieve state-of-the-art performance on Argoverse and INTERACTION datasets with impressive runtime performance..

We propose a novel method for future instance segmentation in Bird's-eye view space. We exploit state-space models for the future state prediction for encoding 3D scene structure and decoding future instance segmentations. Our results achieve state-of-the-art performance on NuScnes dataset with a great margin.

We propose a novel method for trajectory prediction. We propose to use Temporal Graph Networks for learning dynamically evolving agent features. Our results reaches the state-of-the-art performance on Argoverse Forecasting dataset.

We decompose the scene into static and dynamic parts by encoding it into ego-motion and optical flow. We first factorize scene structure, the ego-motion, then conditioned on this, we predict the residual flow in the scene specifically for independently moving objects.

We propose a novel way for stochastic video prediction by decomposing static and dynamic parts of the scene. We reason about appearance and motion in the video stochastically by predicting the future based on the motion history.

We propose theoretical understanding of JND concept for machine perception and conduct further analyses and comparisons with other state-of-the-art methods.

This paper extends our ICIP 2020 paper.

We propose a new concept for adversarial example generation. Inspired by the experimental psychology, we use the concept of Just Noticeable Difference to generate natural looking adverarial images.

We proposed a new method for classifying cognitive states using Artificial Brain Networks. The proposed model generates state-of-the-art results for Tower of London, complex problem solving dataset.

• COMP302: Software Engineering, Koc University
• COMP100: Introduction to Computer Science and Programming, Koc University
• CENG223: Discrete Computational Structures, Middle East Technical University
• CENG230: C Programming, Middle East Technical University

Website format from Jon Barron.