相关论文: Is the Modality Gap a Bug or a Feature? A Robustne…

Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images. MLLMs are heavily influenced by modality bias, often relying on language while…

Sub-population shift is a specific type of domain shift that highlights changes in data distribution within specific sub-groups or populations between training and testing. Sub-population shift accounts for a significant source of…

The advent of Vision-Language Models (VLMs) in medical image analysis has the potential to help process multimodal inputs and increase performance over traditional inference methods. However, when considering the domain in which these…

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

One of the latest trends in generative Artificial Intelligence is tools that generate and analyze content in different modalities, such as text and images, and convert information from one to the other. From a conceptual point of view, it…

Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…

The rapid evolution of machine learning has propelled neural networks to unprecedented success across diverse domains. In particular, multimodal learning has emerged as a transformative paradigm, leveraging complementary information from…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images…

During multimodal model training and testing, certain data modalities may be absent due to sensor limitations, cost constraints, privacy concerns, or data loss, negatively affecting performance. Multimodal learning techniques designed to…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text)…

Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit…

Vision-Language Models (VLMs) have demonstrated strong capabilities across a wide range of multimodal tasks. However, recent studies have shown that VLMs, such as CLIP, perform poorly in understanding negation expressions, which are common…

Video paragraph captioning (VPC) involves generating detailed narratives for long videos, utilizing supportive modalities such as speech and event boundaries. However, the existing models are constrained by the assumption of constant…

Measurement outliers are unavoidable when solving real-world robot state estimation problems. A large family of robust loss functions (RLFs) exists to mitigate the effects of outliers, including newly developed adaptive methods that do not…

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional learning models, implicit networks offer competitive…

Cross-modal retrieval aims to bridge the semantic gap between different modalities, such as visual and textual data, enabling accurate retrieval across them. Despite significant advancements with models like CLIP that align cross-modal…