English
Related papers

Related papers: M5Product: Self-harmonized Contrastive Learning fo…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Wouter Van Gansbeke , Simon Vandenhende , Stamatios Georgoulis , Luc Van Gool

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…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Yiyuan Zhang , Handong Li , Jing Liu , Xiangyu Yue

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…

Sound · Computer Science 2021-03-25 Luyu Wang , Aaron van den Oord

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…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuanhuiyi Lyu , Xu Zheng , Dahun Kim , Lin Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Fangzhou Hong , Liang Pan , Zhongang Cai , Ziwei Liu

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…

Machine Learning · Computer Science 2026-02-16 Can Yaras , Siyi Chen , Peng Wang , Qing Qu

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…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Rohit Gupta , Anirban Roy , Claire Christensen , Sujeong Kim , Sarah Gerard , Madeline Cincebeaux , Ajay Divakaran , Todd Grindal , Mubarak Shah

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…

Computation and Language · Computer Science 2022-03-15 Wei Li , Can Gao , Guocheng Niu , Xinyan Xiao , Hao Liu , Jiachen Liu , Hua Wu , Haifeng Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Haonan Chen , Liang Wang , Nan Yang , Yutao Zhu , Ziliang Zhao , Furu Wei , Zhicheng Dou

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Shaohao Rui , Lingzhi Chen , Zhenyu Tang , Lilong Wang , Mianxin Liu , Shaoting Zhang , Xiaosong Wang

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…

Sound · Computer Science 2023-09-22 Luis Carvalho , Tobias Washüttl , Gerhard Widmer

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-17 Yuze Liu , Shibo Chu , Tiehua Zhang , Hao Zhou , Zhishu Shen , Jinze Wang , Jianzhong Qi , Feng Xia

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…

Computer Vision and Pattern Recognition · Computer Science 2022-02-16 Licheng Yu , Jun Chen , Animesh Sinha , Mengjiao MJ Wang , Hugo Chen , Tamara L. Berg , Ning Zhang

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…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Fanheng Kong , Jingyuan Zhang , Yahui Liu , Hongzhi Zhang , Shi Feng , Xiaocui Yang , Daling Wang , Yu Tian , Victoria W. , Fuzheng Zhang , Guorui Zhou

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…

Image and Video Processing · Electrical Eng. & Systems 2026-04-07 Junkai Liu , Ling Shao , Le Zhang

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…

Information Retrieval · Computer Science 2023-08-15 Andres Ferraro , Jaehun Kim , Sergio Oramas , Andreas Ehmann , Fabien Gouyon

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…

Information Retrieval · Computer Science 2026-04-03 Geonmo Gu , Byeongho Heo , Jaemyung Yu , Jaehui Hwang , Taekyung Kim , Sangmin Lee , HeeJae Jun , Yoohoon Kang , Sangdoo Yun , Dongyoon Han

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…

Machine Learning · Computer Science 2024-05-29 Hangyu Lin , Chen Liu , Chengming Xu , Zhengqi Gao , Yanwei Fu , Yuan Yao

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…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Heqing Zou , Meng Shen , Chen Chen , Yuchen Hu , Deepu Rajan , Eng Siong Chng

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…

Information Retrieval · Computer Science 2023-10-31 Yunshan Ma , Xiaohao Liu , Yinwei Wei , Zhulin Tao , Xiang Wang , Tat-Seng Chua