2 papers
cs.CV2025
VeS: Teaching Pixels to Listen Without Supervision
Sajay Raj
Recent dense audio-visual (AV) models achieve impressive retrieval and emergent localization, but almost all evidence comes from English-centric, caption-rich web video. It is uncl…
cs.CV2025
ICPR 2024 Competition on Rider Intention Prediction
Shankar Gangisetty, Abdul Wasi, Shyam Nandan Rai +8
The recent surge in the vehicle market has led to an alarming increase in road accidents. This underscores the critical importance of enhancing road safety measures, particularly f…