Related papers: M5Product: Self-harmonized Contrastive Learning fo…
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…
We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up…
Recent advances suggest the advantage of multi-modal training in comparison with single-modal methods. In contrast to this view, in our work we find that similar gain can be obtained from training with different formats of a single…
Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…
Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient…
Multimodal learning has recently gained significant popularity, demonstrating impressive performance across various zero-shot classification tasks and a range of perceptive and generative applications. Models such as Contrastive…
The recent growth in the consumption of online media by children during early childhood necessitates data-driven tools enabling educators to filter out appropriate educational content for young learners. This paper presents an approach for…
Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text…
Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders…
Self-supervised learning has greatly facilitated medical image analysis by suppressing the training data requirement for real-world applications. Current paradigms predominantly rely on self-supervision within uni-modal image data, thereby…
Linking sheet music images to audio recordings remains a key problem for the development of efficient cross-modal music retrieval systems. One of the fundamental approaches toward this task is to learn a cross-modal embedding space via deep…
Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models, where lightweight on-device models adapt to domain-specific data and cloud-hosted models coordinate knowledge sharing. However, in…
We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide…
Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have identified modal gaps in feature spaces, a systematic…
Self-supervised learning (SSL) and diffusion models have advanced representation learning and image synthesis, but in 3D medical imaging they are still largely used separately for analysis and synthesis, respectively. Unifying them is…
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…
Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-target pairs across different modalities. Yet, despite its…
Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…
Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality…
Automatic bundle construction is a crucial prerequisite step in various bundle-aware online services. Previous approaches are mostly designed to model the bundling strategy of existing bundles. However, it is hard to acquire large-scale…