Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
Yuchi Ishikawa, Shota Nakada, Hokuto Munakata +3
In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrai…
cs.CV2024
Data Collection-free Masked Video Modeling
Yuchi Ishikawa, Masayoshi Kondo, Yoshimitsu Aoki
Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, lice…