Maja Pantic
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition
arXiv 2026
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution
arXiv 2025
Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models
arXiv 2025
Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS
arXiv 2025
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
arXiv 2024
Large Language Models are Strong Audio-Visual Speech Recognition Learners
arXiv 2024
Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels
arXiv 2023
Laughing Matters: Introducing Laughing-Face Generation using Diffusion Models
arXiv 2023
Visual Speech Recognition for Multiple Languages in the Wild
arXiv 2022
RoI Tanh-polar Transformer Network for Face Parsing in the Wild
arXiv 2021
FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild
arXiv 2021
Affiliations
Frequent co-authors
10from 11 papers