English
Related papers

Related papers: MCE: Towards a General Framework for Handling Miss…

200 papers

In this work, we undertake the challenge of augmenting the existing generative capabilities of pre-trained text-only large language models (LLMs) with multi-modal generation capability while satisfying two core constraints: C1 preserving…

Computation and Language · Computer Science 2025-04-02 Raman Dutt , Harleen Hanspal , Guoxuan Xia , Petru-Daniel Tudosiu , Alexander Black , Yongxin Yang , Steven McDonagh , Sarah Parisot

Multimodal Entity Linking (MEL) aims to link ambiguous mentions within multimodal contexts to associated entities in a multimodal knowledge base. Existing approaches to MEL introduce multimodal interaction and fusion mechanisms to bridge…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Zhiwei Hu , Víctor Gutiérrez-Basulto , Zhiliang Xiang , Ru Li , Jeff Z. Pan

Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other…

Machine Learning · Computer Science 2024-11-05 Zirun Guo , Tao Jin , Jingyuan Chen , Zhou Zhao

Healthcare relies on multiple types of data, such as medical images, genetic information, and clinical records, to improve diagnosis and treatment. However, missing data is a common challenge due to privacy restrictions, cost, and technical…

Machine Learning · Computer Science 2025-03-13 Nazanin Moradinasab , Saurav Sengupta , Jiebei Liu , Sana Syed , Donald E. Brown

Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Lincan Cai , Shuang Li , Wenxuan Ma , Jingxuan Kang , Binhui Xie , Zixun Sun , Chengwei Zhu

Current e-commerce multimodal retrieval systems face two key limitations: they optimize for specific tasks with fixed modality pairings, and lack comprehensive benchmarks for evaluating unified retrieval approaches. To address these…

Information Retrieval · Computer Science 2025-08-20 Zihan Liang , Yufei Ma , ZhiPeng Qian , Huangyu Dai , Zihan Wang , Ben Chen , Chenyi Lei , Yuqing Ding , Han Li

Multimodal Emotion Recognition in Conversations (ERC) is a typical multimodal learning task in exploiting various data modalities concurrently. Prior studies on effective multimodal ERC encounter challenges in addressing modality imbalances…

Multimedia · Computer Science 2024-08-26 Cam-Van Thi Nguyen , The-Son Le , Anh-Tuan Mai , Duc-Trong Le

Multimodal AI has demonstrated superior performance over unimodal approaches by leveraging diverse data sources for more comprehensive analysis. However, applying this effectiveness in healthcare is challenging due to the limited…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Pranav Poudel , Prashant Shrestha , Sanskar Amgain , Yash Raj Shrestha , Prashnna Gyawali , Binod Bhattarai

Multi-Modal Entity Alignment (MMEA) aims to retrieve equivalent entities from different Multi-Modal Knowledge Graphs (MMKGs), a critical information retrieval task. Existing studies have explored various fusion paradigms and consistency…

Multimedia · Computer Science 2025-05-16 Taoyu Su , Jiawei Sheng , Duohe Ma , Xiaodong Li , Juwei Yue , Mengxiao Song , Yingkai Tang , Tingwen Liu

Recent advances in instruction-based image editing have shown remarkable progress. However, existing methods remain limited to relatively simple editing operations, hindering real-world applications that require complex and compositional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Xuehai Bai , Xiaoling Gu , Akide Liu , Hangjie Yuan , YiFan Zhang , Jack Ma

Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…

Computation and Language · Computer Science 2024-07-09 Ting-Yu Yen , Yun-Da Tsai , Keng-Te Liao , Shou-De Lin

The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and…

Computation and Language · Computer Science 2025-09-09 Junxi Wu , Jinpeng Wang , Zheng Liu , Bin Chen , Dongjian Hu , Hao Wu , Shu-Tao Xia

Multimodal learning is of continued interest in artificial intelligence-based applications, motivated by the potential information gain from combining different data modalities. However, modalities observed in the source environment may…

Machine Learning · Computer Science 2026-03-03 Young Sang Choi , Vincent Jeanselme , Pierre Elias , Shalmali Joshi

Pre-trained large multi-modal models (LMMs) exploit fine-tuning to adapt diverse user applications. Nevertheless, fine-tuning may face challenges due to deactivated sensors (e.g., cameras turned off for privacy or technical issues),…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Shu Zhao , Xiaohan Zou , Tan Yu , Huijuan Xu

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Hyundong Jin , Eunwoo Kim

When training classification models, it expects that the learned features are compact within classes, and can well separate different classes. As the dominant loss function for training classification models, minimizing cross-entropy (CE)…

Machine Learning · Computer Science 2025-05-12 Qiufu Li , Huibin Xiao , Linlin Shen

The multimodal relevance metric is usually borrowed from the embedding ability of pretrained contrastive learning models for bimodal data, which is used to evaluate the correlation between cross-modal data (e.g., CLIP). However, the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Zhicheng Du , Qingyang Shi , Jiasheng Lu , Yingshan Liang , Xinyu Zhang , Yiran Wang , Peiwu Qin

Effectively managing missing modalities is a fundamental challenge in real-world multimodal learning scenarios, where data incompleteness often results from systematic collection errors or sensor failures. Sparse Mixture-of-Experts (SMoE)…

Machine Learning · Computer Science 2026-05-12 Liangwei Nathan Zheng , Wei Emma Zhang , Mingyu Guo , Olaf Maennel , Weitong Chen

Missing data is a common problem in machine learning and in retrospective imaging research it is often encountered in the form of missing imaging modalities. We propose to take into account missing modalities in the design and training of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Karin van Garderen , Marion Smits , Stefan Klein

Reliable channel estimation (CE) is fundamental for robust communication in dynamic wireless environments, where models must generalize across varying conditions such as signal-to-noise ratios (SNRs), the number of resource blocks (RBs),…

Signal Processing · Electrical Eng. & Systems 2025-09-22 Tianyu Li , Yan Xin , Jianzhong , Zhang