Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Recent VQA models may tend to rely on language bias as a shortcut and thus fail to
sufficiently learn the multi-modal knowledge from both vision and language. In this paper, we …

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of
human. Despite tremendous success in the AI research, most of existing methods have only …

3D object detection from a single image without LiDAR is a challenging task due to the lack
of accurate depth information. Conventional 2D convolutions are unsuitable for this task …

A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation
model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the …

The goal of few-shot learning (FSL) is to recognize a set of novel classes with only few
labeled samples by exploiting a large set of abundant base class samples. Adopting a meta-…

Multi-modal pre-training models have been intensively explored to bridge vision and
language in recent years. However, most of them explicitly model the cross-modal interaction …

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval.
Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-…

Recently, large-scale few-shot learning (FSL) becomes topical. It is discovered that, for a
large-scale FSL problem with 1,000 classes in the source domain, a strong baseline emerges, …

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers
in diffusion-based video generation. It features transformer blocks with modularized …