Related papers: DCFormer: Efficient 3D Vision-Language Modeling wi…

Magnetic Resonance Imaging is a critical imaging modality in clinical diagnosis and research, yet its complexity and heterogeneity hinder scalable, generalizable machine learning. Although foundation models have revolutionized language and…

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches…

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…

Mesh deformation is a fundamental tool in 3D content manipulation. Despite extensive prior research, existing approaches often suffer from low output quality, require significant manual tuning, or depend on data-intensive training. To…

Vision Transformer shows great superiority in medical image segmentation due to the ability in learning long-range dependency. For medical image segmentation from 3D data, such as computed tomography (CT), existing methods can be broadly…

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…

Recently, deep learning methods have achieved state-of-the-art performance in many medical image segmentation tasks. Many of these are based on convolutional neural networks (CNNs). For such methods, the encoder is the key part for global…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional…

Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation in the form of reasoning and planning. Despite the progress, most still rely on pre-defined motion primitives to…

Comprehending 3D environments is vital for intelligent systems in domains like robotics and autonomous navigation. Voxel grids offer a structured representation of 3D space, but extracting high-level semantic meaning remains challenging.…

Accurate disease interpretation from radiology remains challenging due to imaging heterogeneity. Achieving expert-level diagnostic decisions requires integration of subtle image features with clinical knowledge. Yet major vision-language…

Multi-view counting (MVC) methods have shown their superiority over single-view counterparts, particularly in situations characterized by heavy occlusion and severe perspective distortions. However, hand-crafted heuristic features and…

The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This…

Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). However, this adaptation remains challenging, as it requires…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

Medical vision language pre-training (VLP) has emerged as a frontier of research, enabling zero-shot pathological recognition by comparing the query image with the textual descriptions for each disease. Due to the complex semantics of…

In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike…