English
Related papers

Related papers: CapRecover: A Cross-Modality Feature Inversion Att…

200 papers

In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yi Zhang , Ke Yu , Siqi Wu , Zhihai He

We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Zeyuan Yin , Eric Xing , Zhiqiang Shen

Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…

Computation and Language · Computer Science 2025-07-29 George Ibrahim , Rita Ramos , Yova Kementchedjhieva

The rapid evolution of deepfake technology, particularly in instruction-guided image editing, threatens the integrity of digital images by enabling subtle, context-aware manipulations. Generated conditionally from real images and textual…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Tuan Nguyen , Naseem Khan , Issa Khalil

Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics)…

Computer Vision and Pattern Recognition · Computer Science 2023-05-01 Xu Zhang , Xinzheng Niu , Philippe Fournier-Viger , Xudong Dai

Video semantic communication, praised for its transmission efficiency, still faces critical challenges related to privacy leakage. Traditional security techniques like steganography and encryption are challenging to apply since they are not…

Image and Video Processing · Electrical Eng. & Systems 2025-12-30 Zhihan Cao , Xiao Yang , Gaolei Li , Jun Wu , Jianhua Li , Yuchen Liu

Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we…

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Renyi Qu , Mark Yatskar

Large repositories of image-caption pairs are essential for the development of vision-language models. However, these datasets are often extracted from noisy data scraped from the web, and contain many mislabeled instances. In order to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Haoran Zhang , Aparna Balagopalan , Nassim Oufattole , Hyewon Jeong , Yan Wu , Jiacheng Zhu , Marzyeh Ghassemi

Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Tzu-Heng Huang , Sirajul Salekin , Javier Movellan , Frederic Sala , Manjot Bilkhu

Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Chuhao Liu , Ke Wang , Jieqi Shi , Zhijian Qiao , Shaojie Shen

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Stephanie Fu , Mark Hamilton , Laura Brandt , Axel Feldman , Zhoutong Zhang , William T. Freeman

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Tianshuo Peng , Zuchao Li , Lefei Zhang , Hai Zhao , Ping Wang , Bo Du

Partial multi-label learning aims to extract knowledge from incompletely annotated data, which includes known correct labels, known incorrect labels, and unknown labels. The core challenge lies in accurately identifying the ambiguous…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Xin Wu , Fei Teng , Yue Feng , Kaibo Shi , Zhuosheng Lin , Ji Zhang , James Wang

Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Mert Bulent Sariyildiz , Julien Perez , Diane Larlus

Understanding the memorization and privacy leakage risks in Contrastive Language--Image Pretraining (CLIP) is critical for ensuring the security of multimodal models. Recent studies have demonstrated the feasibility of extracting sensitive…

Cryptography and Security · Computer Science 2026-05-22 Yunhao Chen , Shujie Wang , Xin Wang , Ran He , Xingjun Ma , Yu-Gang Jiang

Recently, masked video modeling has been widely explored and significantly improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Han Fang , Zhifei Yang , Xianghao Zang , Chao Ban , Hao Sun

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Artificial Intelligence · Computer Science 2026-05-05 Yuanyuan Jia , Shunpu Tang , Qianqian Yang

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Machine Learning · Computer Science 2025-01-29 Qing Li , Jiahui Geng , Zongxiong Chen , Kun Song , Lei Ma , Fakhri Karray

Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Linli Yao , Weijing Chen , Qin Jin