English
Related papers

Related papers: Towards Bridging the Cross-modal Semantic Gap for …

200 papers

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While…

Artificial Intelligence · Computer Science 2025-09-04 Zhiyuan Wang , Bokui Chen

Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…

Computation and Language · Computer Science 2017-11-10 Éloi Zablocki , Benjamin Piwowarski , Laure Soulier , Patrick Gallinari

Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Chau Truong , Hieu Ta Quang , Dung D. Le

Automated radiology report generation aims to expedite the tedious and error-prone reporting process for radiologists. While recent works have made progress, learning to align medical images and textual findings remains challenging due to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Yaxiong Chen , Chuang Du , Chunlei Li , Jingliang Hu , Yilei Shi , Shengwu Xiong , Xiao Xiang Zhu , Lichao Mou

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

Information Retrieval · Computer Science 2025-01-22 Chao Zhang , Haoxin Zhang , Shiwei Wu , Di Wu , Tong Xu , Xiangyu Zhao , Yan Gao , Yao Hu , Enhong Chen

Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art performance at aligning visual and textual representations…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Shaoan Xie , Lingjing Kong , Yujia Zheng , Yu Yao , Zeyu Tang , Eric P. Xing , Guangyi Chen , Kun Zhang

The study of decoding visual neural information faces challenges in generalizing single-subject decoding models to multiple subjects, due to individual differences. Moreover, the limited availability of data from a single subject has a…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Qiongyi Zhou , Changde Du , Shengpei Wang , Huiguang He

Multi-modal Contrastive Representation learning aims to encode different modalities into a semantically aligned shared space. This paradigm shows remarkable generalization ability on numerous downstream tasks across various modalities.…

Machine Learning · Computer Science 2023-10-20 Zehan Wang , Yang Zhao , Xize Cheng , Haifeng Huang , Jiageng Liu , Li Tang , Linjun Li , Yongqi Wang , Aoxiong Yin , Ziang Zhang , Zhou Zhao

Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Zhixiong Zeng , Wenji Mao

Multimedia content is of predominance in the modern Web era. Investigating how users interact with multimodal items is a continuing concern within the rapid development of recommender systems. The majority of previous work focuses on…

Information Retrieval · Computer Science 2021-07-22 Jinghao Zhang , Yanqiao Zhu , Qiang Liu , Shu Wu , Shuhui Wang , Liang Wang

Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Hao Zheng , Shunzhi Yang , Zhuoxin He , Jinfeng Yang , Zhenhua Huang

Multimodal recommendation systems integrate diverse multimodal information into the feature representations of both items and users, thereby enabling a more comprehensive modeling of user preferences. However, existing methods are hindered…

Multimedia · Computer Science 2025-01-03 Qiya Song , Jiajun Hu , Lin Xiao , Bin Sun , Xieping Gao , Shutao Li

Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression. Recent methods leverage large-scale pretrained unimodal models as backbones along with fusion techniques…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Seoyeon Kim , Minguk Kang , Dongwon Kim , Jaesik Park , Suha Kwak

We introduce Web-Scale Multimodal Summarization, a lightweight framework for generating summaries by combining retrieved text and image data from web sources. Given a user-defined topic, the system performs parallel web, news, and image…

Machine Learning · Computer Science 2026-02-17 Mounvik K , N Harshit

Multimodal learning has shown promise in medical imaging, combining complementary modalities like images and text. Vision-language models (VLMs) capture rich diagnostic cues but often require large paired datasets and prompt- or text-based…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Banafsheh Karimian , Giulia Avanzato , Soufian Belharbi , Alexis Guichemerre , Luke McCaffrey , Mohammadhadi Shateri , Eric Granger

TIReID aims to retrieve the image corresponding to the given text query from a pool of candidate images. Existing methods employ prior knowledge from single-modality pre-training to facilitate learning, but lack multi-modal correspondences.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Shuanglin Yan , Neng Dong , Liyan Zhang , Jinhui Tang

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Computer Vision and Pattern Recognition · Computer Science 2025-02-24 Zhiyu Zhu , Zhibo Jin , Jiayu Zhang , Nan Yang , Jiahao Huang , Jianlong Zhou , Fang Chen

The common multimodal recommendation pipeline involves (i) extracting multimodal features, (ii) refining their high-level representations to suit the recommendation task, (iii) optionally fusing all multimodal features, and (iv) predicting…

Information Retrieval · Computer Science 2026-02-24 Matteo Attimonelli , Danilo Danese , Angela Di Fazio , Daniele Malitesta , Claudio Pomo , Tommaso Di Noia

Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Mengxiao Tian , Xinxiao Wu , Shuo Yang

Visible-infrared person re-identification (VIReID) primarily deals with matching identities across person images from different modalities. Due to the modality gap between visible and infrared images, cross-modality identity matching poses…

Computer Vision and Pattern Recognition · Computer Science 2024-01-15 Xiaoyan Yu , Neng Dong , Liehuang Zhu , Hao Peng , Dapeng Tao