In recent years, significant progress has been made in video instance
se...
Open-Domain Question Answering (ODQA) requires models to answer factoid
...
Human behavior has the nature of indeterminacy, which requires the pedes...
Image Transformer has recently achieved significant progress for natural...
Multimodal pre-training with text, layout, and image has made significan...
Trajectory prediction is confronted with the dilemma to capture the
mult...
Forecasting human trajectories in complex dynamic environments plays a
c...
Multi-turn dialogue reading comprehension aims to teach machines to read...
Pre-trained Language Models (PrLMs) have been widely used as backbones i...
Multi-choice machine reading comprehension (MRC) requires models to choo...