Researcher:
Akan, Adil Kaan

Profile Picture
ORCID

Job Title

PhD Student

First Name

Adil Kaan

Last Name

Akan

Name

Name Variants

Akan, Adil Kaan

Email Address

Birth Date

Filters

2021 - 20222

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.acec35c0-66b6-47fd-8c7f-031458dec8db

Search Results

Now showing 1 - 2 of 2
  • Placeholder
    PublicationMetadata only
    Stretchbev: stretching future instance prediction spatially and temporally
    (Springer International Publishing Ag, 2022) N/A; Department of Computer Engineering; Akan, Adil Kaan; Güney, Fatma; PhD Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; 187939
    In self-driving, predicting future in terms of location and motion of all the agents around the vehicle is a crucial requirement for planning. Recently, a new joint formulation of perception and prediction has emerged by fusing rich sensory information perceived from multiple cameras into a compact bird's-eye view representation to perform prediction. However, the quality of future predictions degrades over time while extending to longer time horizons due to multiple plausible predictions. In this work, we address this inherent uncertainty in future predictions with a stochastic temporal model. Our model learns temporal dynamics in a latent space through stochastic residual updates at each time step. By sampling from a learned distribution at each time step, we obtain more diverse future predictions that are also more accurate compared to previous work, especially stretching both spatially further regions in the scene and temporally over longer time horizons. Despite separate processing of each time step, our model is still efficient through decoupling of the learning of dynamics and the generation of future predictions.
  • Thumbnail Image
    PublicationOpen Access
    SLAMP: stochastic latent appearance and motion prediction
    (Institute of Electrical and Electronics Engineers (IEEE), 2021) Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Güney, Fatma; Akan, Adil Kaan; Faculty Member; Department of Computer Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of Engineering; Graduate School of Sciences and Engineering; 20331; 187939; N/A
    Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components. Most of the previous work utilizing motion is deterministic but there are stochastic methods that can model the inherent uncertainty of the future. Existing stochastic models either do not reason about motion explicitly or make limiting assumptions about the static part. In this paper, we reason about appearance and motion in the video stochastically by predicting the future based on the motion history. Explicit reasoning about motion without history already reaches the performance of current stochastic models. The motion history further improves the results by allowing to predict consistent dynamics several frames into the future. Our model performs comparably to the state-of-the-art models on the generic video prediction datasets, however, significantly outperforms them on two challenging real-world autonomous driving datasets with complex motion and dynamic background.