English
Related papers

Related papers: Closing the Modality Gap for Mixed Modality Search

200 papers

State-of-the-art empirical work has shown that visual representations learned by deep neural networks are robust in nature and capable of performing classification tasks on diverse datasets. For example, CLIP demonstrated zero-shot transfer…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Chanda Grover , Indra Deep Mastan , Debayan Gupta

Recent research suggested that the embeddings produced by CLIP-like contrastive language-image training are suboptimal for image-only tasks. The main theory is that the inter-modal (language-image) alignment loss ignores intra-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jonas Herzog , Yue Wang

Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, their ability to handle complex, real-world web documents…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yiqi Lin , Alex Jinpeng Wang , Linjie Li , Zhengyuan Yang , Mike Zheng Shou

Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical datasets tend to have high cross-modal correlation but low…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Shengzhu Yang , Jiawei Du , Shuai Lu , Weihang Zhang , Ningli Wang , Huiqi Li

Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Huaishao Luo , Lei Ji , Ming Zhong , Yang Chen , Wen Lei , Nan Duan , Tianrui Li

Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Zineng Tang , Long Lian , Seun Eisape , XuDong Wang , Roei Herzig , Adam Yala , Alane Suhr , Trevor Darrell , David M. Chan

Contrastive Language-Image Pre-Training (CLIP) is a popular method for learning multimodal latent spaces with well-organized semantics. Despite its wide range of applications, CLIP's latent space is known to fail at handling complex…

Machine Learning · Computer Science 2026-03-17 Raphi Kang , Yue Song , Georgia Gkioxari , Pietro Perona

The advent of text-image models, most notably CLIP, has significantly transformed the landscape of information retrieval. These models enable the fusion of various modalities, such as text and images. One significant outcome of CLIP is its…

Information Retrieval · Computer Science 2024-06-21 Christian Lülf , Denis Mayr Lima Martins , Marcos Antonio Vaz Salles , Yongluan Zhou , Fabian Gieseke

We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…

Machine Learning · Computer Science 2025-08-07 Dahun Kim , Anelia Angelova

Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Lorenzo Bianchi , Fabio Carrara , Nicola Messina , Fabrizio Falchi

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Gangyan Zeng , Yuan Zhang , Jin Wei , Dongbao Yang , Peng Zhang , Yiwen Gao , Xugong Qin , Yu Zhou

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Fawaz Sammani , Nikos Deligiannis

CLIP and BiomedCLIP are examples of vision-language foundation models and offer strong cross-modal embeddings; however, they are not optimized for fine-grained medical retrieval tasks, such as retrieving clinically relevant radiology…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Zhaohui Liang , Sivaramakrishnan Rajaraman , Niccolo Marini , Zhiyun Xue , Sameer Antani

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Samuel Lavoie , Polina Kirichenko , Mark Ibrahim , Mahmoud Assran , Andrew Gordon Wilson , Aaron Courville , Nicolas Ballas

The multi-modal hashing method is widely used in multimedia retrieval. It can fuse multi-source data to generate binary hash code. However, the current multi-modal methods have the problem of low retrieval accuracy. The reason is that the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Jian Zhu , Mingkai Sheng , Mingda Ke , Zhangmin Huang , Jingfei Chang

Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Linhui Xiao , Xiaoshan Yang , Fang Peng , Ming Yan , Yaowei Wang , Changsheng Xu

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Junyang Wang , Yi Zhang , Ming Yan , Ji Zhang , Jitao Sang

Advances in vision-language models (VLMs) have enabled effective cross-modality retrieval. However, when both text and images exist in the database, similarity scores would differ in scale by modality. This phenomenon, known as the modality…

Computation and Language · Computer Science 2025-12-01 Shuhei Yamashita , Daiki Shirafuji , Tatsuhiko Saito

Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the success of VLMs, they still significantly lag behind human…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Honglin Lin , Siyu Li , Guoshun Nan , Chaoyue Tang , Xueting Wang , Jingxin Xu , Rong Yankai , Zhili Zhou , Yutong Gao , Qimei Cui , Xiaofeng Tao

The Visual Language Model, known for its robust cross-modal capabilities, has been extensively applied in various computer vision tasks. In this paper, we explore the use of CLIP (Contrastive Language-Image Pretraining), a vision-language…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Huazhong Zhao , Lei Qi , Xin Geng