Publications

Equal contribution denoted by *

2024

  1. losa.png
    Time-Memory-and Parameter-Efficient Visual Adaptation
    Otniel-Bogdan Mercea, Alexey Gritsenko, Cordelia Schmid, and 1 more author
    SPOTLIGHT @ CVPR, 2024
    Seattle, USA
  2. clip_clap.png
    Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models
    David Kurzendörfer*Otniel-Bogdan Mercea*, A Koepke, and 1 more author
    CVPRW, 2024
    Seattle, USA
  3. towards.png
    Towards Optimal Adapter Placement for Efficient Transfer Learning
    Aleksandra I Nowak, Otniel-Bogdan Mercea, Anurag Arnab, and 3 more authors
    arXiv preprint arXiv:2410.15858, 2024

2023

  1. regada.png
    Video-adverb retrieval with compositional adverb-action embeddings
    Thomas Hummel, Otniel-Bogdan Mercea, A. Sophia Koepke, and 1 more author
    ORAL @ BMVC, 2023
    Aberdeen, UK
  2. avdiff.jpeg
    Text-to-feature diffusion for audio-visual few-shot learning
    Otniel-Bogdan Mercea, Thomas Hummel, A Sophia Koepke, and 1 more author
    DAGM GCPR, 2023
    Heidelberg, Germany

2022

  1. plant.png
    PlanT: Explainable Planning Transformers via Object-Level Representations
    Katrin Renz, Kashyap Chitta, Otniel-Bogdan Mercea, and 3 more authors
    CoRL, 2022
    Auckland, New Zealand
  2. tcaf.png
    Temporal and cross-modal attention for audio-visual zero-shot learning
    Otniel-Bogdan Mercea*, Thomas Hummel*, A Sophia Koepke, and 1 more author
    ECCV, 2022
    Tel Aviv, Israel
  3. avca.png
    Audio-visual generalised zero-shot learning with cross-modal attention and language
    Otniel-Bogdan Mercea, Lukas Riesch, A Koepke, and 1 more author
    CVPR, 2022
    New Orleans, USA