English
Related papers

Related papers: Improving Visual-Semantic Embeddings by Learning S…

200 papers

Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Xiangyang Wu , Liu Liu , Baosheng Yu , Jiayan Qiu , Zhenwei Shi

Medical vision-language pre-training (VLP) offers significant potential for advancing medical image understanding by leveraging paired image-report data. However, existing methods are limited by Fa}lse Negatives (FaNe) induced by…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Peng Zhang , Zhihui Lai , Wenting Chen , Xu Wu , Heng Kong

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Kai Yao , Alberto Ortiz , Francisco Bonnin-Pascual

We propose a semantic similarity metric for image registration. Existing metrics like Euclidean Distance or Normalized Cross-Correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our…

Machine Learning · Computer Science 2021-04-21 Steffen Czolbe , Oswin Krause , Aasa Feragen

Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the samples where the associated text does not correlate with the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-08 Yash Patel , Yusheng Xie , Yi Zhu , Srikar Appalaraju , R. Manmatha

The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of hard negative samples in contrastive learning. This study…

Computation and Language · Computer Science 2023-10-24 Pengyue Hou , Xingyu Li

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Machine Learning · Computer Science 2023-06-05 Christopher Liao , Theodoros Tsiligkaridis , Brian Kulis

Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment due to domain gaps between pre-training and downstream tasks. Existing approaches primarily…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Xiaojie Yin , Qilong Wang , Qinghua Hu

Visual commonsense understanding requires Vision Language (VL) models to not only understand image and text but also cross-reference in-between to fully integrate and achieve comprehension of the visual scene described. Recently, various…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Zhecan Wang , Haoxuan You , Yicheng He , Wenhao Li , Kai-Wei Chang , Shih-Fu Chang

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are…

Information Retrieval · Computer Science 2020-02-28 Hadi Abdi Khojasteh , Ebrahim Ansari , Parvin Razzaghi , Akbar Karimi

Few-shot learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Bin Xiao , Chien-Liang Liu , Wen-Hoar Hsaio

Evaluation is essential in image fusion research, yet most existing metrics are directly borrowed from other vision tasks without proper adaptation. These traditional metrics, often based on complex image transformations, not only fail to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Chunyang Cheng , Tianyang Xu , Xiao-Jun Wu , Tao Zhou , Hui Li , Zhangyong Tang , Josef Kittler

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network…

Computer Vision and Pattern Recognition · Computer Science 2018-01-17 Chao-Yuan Wu , R. Manmatha , Alexander J. Smola , Philipp Krähenbühl

Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Wentao Chen , Chenyang Si , Zhang Zhang , Liang Wang , Zilei Wang , Tieniu Tan

Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…

Computer Vision and Pattern Recognition · Computer Science 2020-03-04 Weihao Xia , Zhanglin Cheng , Yujiu Yang , Jing-Hao Xue

The goal of this work is to bring semantics into the tasks of text recognition and retrieval in natural images. Although text recognition and retrieval have received a lot of attention in recent years, previous works have focused on…

Computer Vision and Pattern Recognition · Computer Science 2015-09-22 Albert Gordo , Jon Almazan , Naila Murray , Florent Perronnin

The cross-modal retrieval model leverages the potential of triple loss optimization to learn robust embedding spaces. However, existing methods often train these models in a singular pass, overlooking the distinction between semi-hard and…

Sound · Computer Science 2023-10-23 Donghuo Zeng , Kazushi Ikeda

The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while randomly mismatched…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Arda Senocak , Hyeonggon Ryu , Junsik Kim , In So Kweon

Multi-modal word semantics aims to enhance embeddings with perceptual input, assuming that human meaning representation is grounded in sensory experience. Most research focuses on evaluation involving direct visual input, however, visual…

Computation and Language · Computer Science 2021-10-07 Anita L. Verő , Ann Copestake

Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence. The goal is to predict whether the image semantically entails…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Zhiyuan Chang , Mingyang Li , Junjie Wang , Cheng Li , Qing Wang