Automatic Notification of Dangerous Situations in Blind Spots via Image-based Pedestrian Detection using Deep Learning

SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

Multispectral Pedestrian Detection with Sparsely Annotated Label

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

Enabling Visual Object Detection with Object Sounds via Visual Modality Recalling Memory

Spatial Mask-based Adaptive Robust Training for Video Object Segmentation with Noisy Labels

Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

Towards Model-Agnostic Dataset Condensation by Heterogeneous Models