相关论文: Mind the Gap: Understanding the Modality Gap in Mu…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success in cross-modal tasks such as zero-shot image classification and text-image retrieval by effectively aligning visual and textual representations. However, the…

Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs…

Multimodal knowledge graph completion (MKGC) aims to predict missing entities in MKGs. Previous works usually share relation representation across modalities. This results in mutual interference between modalities during training, since for…

Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest. In this paper, we investigate two challenging problems: 1) when…

Human beings have rich ways of emotional expressions, including facial action, voice, and natural languages. Due to the diversity and complexity of different individuals, the emotions expressed by various modalities may be semantically…

While humans excel at continual learning (CL), deep neural networks (DNNs) exhibit catastrophic forgetting. A salient feature of the brain that allows effective CL is that it utilizes multiple modalities for learning and inference, which is…

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…

While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot classification is hindered by a critical limitation: intra-modal misalignment. This issue,…

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

Multi-modal learning has achieved remarkable success by integrating information from various modalities, achieving superior performance in tasks like recognition and retrieval compared to uni-modal approaches. However, real-world scenarios…

Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and from the standpoint of effective knowledge acquisition for…

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…

The social media landscape of conflict dynamics has grown increasingly multi-modal. Recent advancements in model architectures such as CLIP have enabled researchers to begin studying the interplay between the modalities of text and images…

Multimodal recommendation focuses primarily on effectively exploiting both behavioral and multimodal information for the recommendation task. However, most existing models suffer from the following issues when fusing information from two…

In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…

Representation learning constitutes a pivotal cornerstone in contemporary deep learning paradigms, offering a conduit to elucidate distinctive features within the latent space and interpret the deep models. Nevertheless, the inherent…

Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…

The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates offers a unique opportunity for multimodal representation learning. We introduce…

Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomplete or redundant modality data in real-world scenarios. This paper presents a…