1 citations · 1 across the 7 of their papers we have counts for
7 papers
Moving by Looking: Towards Vision-Driven Avatar Motion Generation
Markos Diomataris, Berat Mert Albaba, Giorgio Becherini +3
The way we perceive the world fundamentally shapes how we move, whether it is how we navigate in a room or how we interact with other humans. Current human motion generation method…
NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models
Mert Albaba, Chenhao Li, Markos Diomataris +3
Acquiring physically plausible motor skills across diverse and unconventional morphologies-including humanoid robots, quadrupeds, and animals-is essential for advancing character s…
MotionFix: Text-Driven 3D Human Motion Editing
Nikos Athanasiou, Alpár Cseke, Markos Diomataris +2
The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as describe…
WANDR: Intention-guided Human Motion Generation
Markos Diomataris, Nikos Athanasiou, Omid Taheri +3
Synthesizing natural human motions that enable a 3D human avatar to walk and reach for arbitrary goals in 3D space remains an unsolved problem with many applications. Existing meth…
RelVAE: Generative Pretraining for few-shot Visual Relationship Detection
Sotiris Karapiperis, Markos Diomataris, Vassilis Pitsikalis
Visual relations are complex, multimodal concepts that play an important role in the way humans perceive the world. As a result of their complexity, high-quality, diverse and large…
Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction
Zacharias Anastasakis, Dimitrios Mallis, Markos Diomataris +3
We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD). Motivated by the effectiveness of Masked…
Interpretable Visual Question Answering via Reasoning Supervision
Maria Parelli, Dimitrios Mallis, Markos Diomataris +1
Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task. However, such models are likely to disregard crucial…