相关论文: DCFormer: Efficient 3D Vision-Language Modeling wi…

Transformer models have demonstrated remarkable success in many domains such as natural language processing (NLP) and computer vision. With the growing interest in transformer-based architectures, they are now utilized for gesture…

Vision Transformers (ViTs) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too such as voxels or…

We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to…

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use…

The visual projector, which bridges the vision and language modalities and facilitates cross-modal alignment, serves as a crucial component in MLLMs. However, measuring the effectiveness of projectors in vision-language alignment remains…

Background:Convolutional Neural Networks(CNN) and Vision Transformers(ViT) are the main techniques used in Medical image segmentation. However, CNN is limited to local contextual information, and ViT's quadratic complexity results in…

The challenge of Multimodal Deformable Image Registration (MDIR) lies in the conversion and alignment of features between images of different modalities. Generative models (GMs) cannot retain the necessary information enough from the source…

3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA). 3DMMs were used as statistical priors for…

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}'…

Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves…

Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. However, the prevailing approaches primarily regard the visual…

Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality…

We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language…

The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First,…

The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge…

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models…

3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited…

Decades of cognitive science establish that humans navigate environments by forming cognitive maps, defined as allocentric and topology-preserving representations of 3D space. While modern Vision-Language Models (VLMs) demonstrate emergent…

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…