As camera and LiDAR sensors capture complementary information in autonomous driving,
great efforts have been made to conduct semantic segmentation through multi-modality data …

The performance of nighttime semantic segmentation is restricted by the poor illumination
and a lack of pixel-wise annotation, which severely limit its application in autonomous …

Abstract 3D dense captioning aims to describe individual objects by natural language in 3D
scenes, where 3D scenes are usually represented as RGB-D scans or point clouds …

Abstract Emotion Recognition in Conversations (ERC) is an increasingly popular task in the
Natural Language Processing community, which seeks to achieve accurate emotion …

Task transfer learning is a popular technique in image processing applications that uses pre-
trained models to reduce the supervision cost of related tasks. An important question is to …

Event cameras sense per-pixel intensity changes and produce asynchronous event streams
with high dynamic range and less motion blur, showing advantages over the conventional …

Inspired by the McGurk effect, studies on multimodal data fusion start with audio-visual
speech recognition tasks. Multimodal data fusion research was not popular for a period of …

Cross-modal knowledge distillation deals with transferring knowledge from a model trained
with superior modalities (Teacher) to another model trained with weak modalities (Student) …

With the emergence of multimodal electronic health records, the evidence for diseases,
events, or findings may be present across multiple modalities ranging from clinical to …

With advances in sensing technology, multi-modal data collected from different sources are
increasingly available. Multi-modal classification aims to integrate complementary …