activity
20212024
collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2024

BehAVE: Behaviour Alignment of Video Game Encodings

Nemanja Rašajski, Chintan Trivedi, Konstantinos Makantasis +2

Domain randomisation enhances the transferability of vision models across visually distinct domains with similar content. However, current methods heavily depend on intricate simul…

cs.CV2023

Towards General Game Representations: Decomposing Games Pixels into Content and Style

Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis +1

On-screen game footage contains rich contextual information that players process when playing and experiencing a game. Learning pixel representations of games can benefit artificia…

cs.CV2022

Game State Learning via Game Scene Augmentation

Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis +1

Having access to accurate game state information is of utmost importance for any artificial intelligence task including game-playing, testing, player modeling, and procedural conte…

cs.CV2022

Learning Task-Independent Game State Representations from Unlabeled Images

Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis +1

Self-supervised learning (SSL) techniques have been widely used to learn compact and informative representations from high-dimensional complex data. In many computer vision tasks,…

cs.CV2021

Contrastive Learning of Generalized Game Representations

Chintan Trivedi, Antonios Liapis, Georgios N. Yannakakis

Representing games through their pixels offers a promising approach for building general-purpose and versatile game models. While games are not merely images, neural network models…