相关论文: Connect, Collapse, Corrupt: Learning Cross-Modal T…

Modern Review Helpfulness Prediction systems are dependent upon multiple modalities, typically texts and images. Unfortunately, those contemporary approaches pay scarce attention to polish representations of cross-modal relations and tend…

Pre-trained multi-modal models, such as CLIP, provide transferable embeddings and show promising results in diverse applications. However, the analysis of learned multi-modal embeddings is relatively unexplored, and the embedding…

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies discovered that CLIP can only encode one aspect of the feature space, leading to substantial information loss and…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Contrastive learning is a powerful way of learning multimodal representations across various domains such as image-caption retrieval and audio-visual representation learning. In this work, we investigate if these findings generalize to the…

While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a measure-theoretic framework in which representation measures…

In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging problem for self-supervised 3D action representation learning.…

Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed…

Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention. However, most of these methods are designed by jointly learning feature representation from multi-modalities that…

Recent research has demonstrated that Large Language Models (LLMs) are not limited to text-only tasks but can also function as multimodal models across various modalities, including audio, images, and videos. In particular, research on 3D…

Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have…

We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers. While contrastive models are usually trained from scratch, LiT (Zhai et al.,…

Multimodal Large Language Models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval,…

The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize…

Learning from tabular data is of paramount importance, as it complements the conventional analysis of image and video data by providing a rich source of structured information that is often critical for comprehensive understanding and…

In multimedia applications, the text and image components in a web document form a pairwise constraint that potentially indicates the same semantic concept. This paper studies cross-modal learning via the pairwise constraint, and aims to…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under the food-computing…

Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching…

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…