Previous works have shown that increasing the window size for Transformer-based image
super-resolution models (eg, SwinIR) can significantly improve the model performance but …

Recent state-of-the-art methods for HOI detection typically build on transformer architectures
with two decoder branches, one for human-object pair detection and the other for interaction …

Image captioning, like many tasks involving vision and language, currently relies on
Transformer-based architectures for extracting the semantics in an image and translating it …

Recent progress in the text-driven 3D stylization of a single object has been considerably
promoted by CLIP-based methods. However the stylization of multi-object 3D scenes is still …

We present DFormer, a novel RGB-D pretraining framework to learn transferable
representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) …

We consider the problem of referring camouflaged object detection (Ref-COD), a new task
that aims to segment specified camouflaged objects based on a small set of referring images …

Numerous studies have shown that in-depth mining of correlations between multi-modal
features can help improve the accuracy of cross-modal data analysis tasks. However, the …

In this work, we propose a training-free method to inject visual referring into Multimodal
Large Language Models (MLLMs) through learnable visual token optimization. We observe …

The issue of hallucinations is a prevalent concern in existing Large Vision-Language
Models (LVLMs). Previous efforts have primarily focused on investigating object …

It is well believed that the higher uncertainty in a word of the caption, the more inter-
correlated context information is required to determine it. However, current image captioning …