相关论文: Dictionary-based Framework for Interpretable and C…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…

The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar…

Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, their ability to handle complex, real-world web documents…

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

Predicting socioeconomic indicators within urban regions is crucial for fostering inclusivity, resilience, and sustainability in cities and human settlements. While pioneering studies have attempted to leverage multi-modal data for…

Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existing works focus on pixel grouping and cross-modal semantic…

Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this…

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…

Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning…

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…

Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained…

We describe a new approach to data modeling, called the concept-oriented model (COM), and a novel concept-oriented query language (COQL). The model is based on three principles: duality principle postulates that any element is a couple…

Fine-grained Vision-Language Pre-training (FVLP) demonstrates significant potential in 3D medical image understanding by aligning anatomy-level visual representations with corresponding textual descriptions. However, existing FVLP paradigms…

Recent advances in Large Vision-Language Models (LVLMs) have enabled general-purpose vision tasks through visual instruction tuning. While existing LVLMs can generate segmentation masks from text prompts for single images, they struggle…

Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation.…

Complementary recommendations, which aim at providing users product suggestions that are supplementary and compatible with their obtained items, have become a hot topic in both academia and industry in recent years. %However, it is…

Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is particularly acute in highly homogeneous scenarios that…

Medical Visual Question Answering (Medical-VQA) aims to to answer clinical questions regarding radiology images, assisting doctors with decision-making options. Nevertheless, current Medical-VQA models learn cross-modal representations…

Medical image segmentation is a critical yet challenging task, primarily due to the difficulty of obtaining extensive datasets of high-quality, expert-annotated images. Contrastive learning presents a potential but still problematic…