5 citations · 7 across the 8 of their papers we have counts for
8 papers
Compositional Video Synthesis by Temporal Object-Centric Learning
Adil Kaan Akan, Yucel Yemez
We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from ima…
Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning
Can Küçüksözen, Yücel Yemez
We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solv…
Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
Adil Kaan Akan, Yucel Yemez
We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our metho…
Dynamical phases of short-term memory mechanisms in RNNs
Bariscan Kurtkaya, Fatih Dinc, Mert Yuksekgonul +7
Short-term memory is essential for cognitive processing, yet our understanding of its neural mechanisms remains unclear. Neuroscience has long focused on how sequential activity pa…
AffectON: Incorporating Affect Into Dialog Generation
Zana Bucinca, Yucel Yemez, Engin Erzin +1
Due to its expressivity, natural language is paramount for explicit and implicit affective state communication among humans. The same linguistic inquiry (e.g., How are you?) might…
Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents
Nusrah Hussain, Engin Erzin, T. Metin Sezgin +1
The ability to generate appropriate verbal and non-verbal backchannels by an agent during human-robot interaction greatly enhances the interaction experience. Backchannels are part…
Speech Driven Backchannel Generation using Deep Q-Network for Enhancing Engagement in Human-Robot Interaction
Nusrah Hussain, Engin Erzin, T. Metin Sezgin +1
We present a novel method for training a social robot to generate backchannels during human-robot interaction. We address the problem within an off-policy reinforcement learning fr…
View subspaces for indexing and retrieval of 3D models
Helin Dutagaci, Afzal Godil, Bulent Sankur +1
View-based indexing schemes for 3D object retrieval are gaining popularity since they provide good retrieval results. These schemes are coherent with the theory that humans recogni…