English
Related papers

Related papers: Cross the Gap: Exposing the Intra-modal Misalignme…

200 papers

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

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Haonan Xu , Dian Chao , Xiangyu Wu , Zhonghua Wan , Yang Yang

Multi-modal models, such as CLIP, have demonstrated strong performance in aligning visual and textual representations, excelling in tasks like image retrieval and zero-shot classification. Despite this success, the mechanisms by which these…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Wenhao Wang , Adam Dziedzic , Grace C. Kim , Michael Backes , Franziska Boenisch

Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. However, there is limited research on learning video-text representations for general…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Xingjian He , Sihan Chen , Fan Ma , Zhicheng Huang , Xiaojie Jin , Zikang Liu , Dongmei Fu , Yi Yang , Jing Liu , Jiashi Feng

Multimodal learning leverages complementary information derived from different modalities, thereby enhancing performance in medical image segmentation. However, prevailing multimodal learning methods heavily rely on extensive well-annotated…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Xiaogen Zhou , Yiyou Sun , Min Deng , Winnie Chiu Wing Chu , Qi Dou

The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to reliably evaluate their semantic alignment. Contrastive Language-Image Pre-training (CLIP)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Hai Wang , Xiaochen Yang , Mingzhi Dong , Jing-Hao Xue

While large language-image pre-trained models like CLIP offer powerful generic features for image clustering, existing methods typically freeze the encoder. This creates a fundamental mismatch between the model's task-agnostic…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zihan Li , Wei Sun , Jing Hu , Jianhua Yin , Jianlong Wu , Liqiang Nie

Pretrained cross-modal models, for instance, the most representative CLIP, have recently led to a boom in using pre-trained models for cross-modal zero-shot tasks, considering the generalization properties. However, we analytically discover…

Multimedia · Computer Science 2024-06-28 Hanyao Wang , Yibing Zhan , Liu Liu , Liang Ding , Yan Yang , Jun Yu

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Ximeng Tao , Dimitar Filev , Gaurav Pandey

Multi-modal embeddings form the foundation for vision-language models, such as CLIP embeddings, the most widely used text-image embeddings. However, these embeddings are vulnerable to subtle misalignment of cross-modal features, resulting…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Yilin Ye , Shishi Xiao , Xingchen Zeng , Wei Zeng

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Lijie Zhou

Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Cilin Yan , Haochen Wang , Xiaolong Jiang , Yao Hu , Xu Tang , Guoliang Kang , Efstratios Gavves

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 Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Haonan Jia , Shichao Dong , Xin Dong , Zenghui Sun , Jin Wang , Jinsong Lan , Xiaoyong Zhu , Bo Zheng , Kaifu Zhang

As a challenging vision-language task, Zero-Shot Composed Image Retrieval (ZS-CIR) is designed to retrieve target images using bi-modal (image+text) queries. Typical ZS-CIR methods employ an inversion network to generate pseudo-word tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Haiwen Li , Fei Su , Zhicheng Zhao

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Xiang An , Kaicheng Yang , Xiangzi Dai , Ziyong Feng , Jiankang Deng

Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization…

Large-scale joint training of multimodal models, e.g., CLIP, have demonstrated great performance in many vision-language tasks. However, image-text pairs for pre-training are restricted to the intersection of images and texts, limiting…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Yanan Sun , Zihan Zhong , Qi Fan , Chi-Keung Tang , Yu-Wing Tai

Vision-Language Pretraining (VLP) has achieved remarkable success across various downstream tasks, but such gains are largely driven by scaling up on training data. Yet, literature methods treat image-text pairs as isolated training…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Wenbo Lu
‹ Prev 1 8 9 10 Next ›