1 citations · 1 across the 3 of their papers we have counts for
3 papers · 1 filter
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…
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…