相关论文: T-MARS: Improving Visual Representations by Circum…

Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and…

We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods limited to specific image types (e.g., natural images or…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated…

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic…

In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In…

Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems. Most existing FAS methods are formulated as binary classification tasks, providing confidence scores without interpretation. They…

Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While several datasets exist for natural images and high-resolution optical remote sensing…

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…

Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. Such models often achieve excellent performance, but lack flexibility. LLMs and VLMs offer…

Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights…

The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We…

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by…

Multiple clustering has gained significant attention in recent years due to its potential to reveal multiple hidden structures of data from different perspectives. The advent of deep multiple clustering techniques has notably advanced the…

Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current methods often depend on large replay buffers or heavily…

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…

Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and few-shot transfer to novel tasks where task-specific annotation is scarce. We address…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…