English
Related papers

Related papers: Unified Multi-modal Unsupervised Representation Le…

200 papers

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Yuncheng Guo , Xiaodong Gu

Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance. While existing methods address training-inference modality gaps via specialized per-combination models, they…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Xiaoqi Zhao , Youwei Pang , Chenyang Yu , Lihe Zhang , Huchuan Lu , Shijian Lu , Georges El Fakhri , Xiaofeng Liu

Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex…

Multimedia · Computer Science 2024-05-22 Hanlei Zhang , Hua Xu , Fei Long , Xin Wang , Kai Gao

Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect. On the other hand, we see a recent paradigm shift from supervised learning to…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Muhammad Abdullah Jamal , Omid Mohareri

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Machine Learning · Computer Science 2025-03-27 Yuncheng Guo , Xiaodong Gu

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…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Yunhua Zhang , Hazel Doughty , Cees G. M. Snoek

Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Aiham Taleb , Christoph Lippert , Tassilo Klein , Moin Nabi

Multimodal learning typically utilizes multimodal joint loss to integrate different modalities and enhance model performance. However, this joint learning strategy can induce modality imbalance, where strong modalities overwhelm weaker ones…

Machine Learning · Computer Science 2025-09-08 Shijie Wang , Li Zhang , Xinyan Liang , Yuhua Qian , Shen Hu

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Md Kaykobad Reza , Ashley Prater-Bennette , M. Salman Asif

Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can be broadly divided into two categories: early-fusion…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Juan Li , Chuanghao Ding , Xujie Zhang , Cam-Tu Nguyen

Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Jiajun Qin , Yuan Pu , Zhuolun He , Seunggeun Kim , David Z. Pan , Bei Yu

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning~(MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of model learning.…

Machine Learning · Computer Science 2025-03-07 Qingyuan Jiang , Zhouyang Chi , Xiao Ma , Qirong Mao , Yang Yang , Jinhui Tang

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Chenzhuang Du , Yue Zhao , Chonghua Liao , Jiacheng You , Jie Fu , Hang Zhao

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Ching-Yi Lai , Chih-Yu Jian , Pei-Cheng Chuang , Chia-Ming Lee , Chih-Chung Hsu , Chiou-Ting Hsu , Chia-Wen Lin

Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are…

Machine Learning · Computer Science 2021-06-22 Chenzhuang Du , Tingle Li , Yichen Liu , Zixin Wen , Tianyu Hua , Yue Wang , Hang Zhao

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Wanjiang Weng , Hongsong Wang , Junbo Wang , Lei He , Guosen Xie

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

Machine Learning · Computer Science 2024-10-10 Niki Nezakati , Md Kaykobad Reza , Ameya Patil , Mashhour Solh , M. Salman Asif

Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Xiantao Hu , Bineng Zhong , Qihua Liang , Zhiyi Mo , Liangtao Shi , Ying Tai , Jian Yang

Multimodal learning has demonstrated remarkable performance improvements over unimodal architectures. However, multimodal learning methods often exhibit deteriorated performances if one or more modalities are missing. This may be attributed…

Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion recognition. Existing approaches use directional pairwise attention or a message hub to fuse…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Ziwang Fu , Feng Liu , Hanyang Wang , Siyuan Shen , Jiahao Zhang , Jiayin Qi , Xiangling Fu , Aimin Zhou