中文
相关论文

相关论文: DiCo: Disentangled Concept Representation for Text…

200 篇论文

The rapid proliferation of large-scale text-to-image diffusion (T2ID) models has raised serious concerns about their potential misuse in generating harmful content. Although numerous methods have been proposed for erasing undesired concepts…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Koushik Srivatsan , Fahad Shamshad , Muzammal Naseer , Vishal M. Patel , Karthik Nandakumar

This paper proposes learning disentangled but complementary face features with minimal supervision by face identification. Specifically, we construct an identity Distilling and Dispelling Autoencoder (D2AE) framework that adversarially…

计算机视觉与模式识别 · 计算机科学 2018-04-11 Yu Liu , Fangyin Wei , Jing Shao , Lu Sheng , Junjie Yan , Xiaogang Wang

An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis. Recently, with the explosive demands of practical applications, a lot…

计算机视觉与模式识别 · 计算机科学 2020-04-28 Zheng Wang , Zhixiang Wang , Yinqiang Zheng , Yang Wu , Wenjun Zeng , Shin'ichi Satoh

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

人工智能 · 计算机科学 2026-03-20 Duc Hao Pham , Van Duy Truong , Duy Khanh Dinh , Tien Cuong Nguyen , Dien Hy Ngo , Tuan Anh Bui

Person re-identification (ReID) plays a critical role in applications such as security surveillance and criminal investigations. Most traditional image-based ReID methods face challenges including occlusions and lighting changes, while text…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Jincheng Yan , Yun Wang , Xiaoyan Luo , Yu-Wing Tai

The collection and release of street-level recordings as Open Data play a vital role in advancing autonomous driving systems and AI research. However, these datasets pose significant privacy risks, particularly for pedestrians, due to the…

计算机视觉与模式识别 · 计算机科学 2025-07-16 Robert Aufschläger , Youssef Shoeb , Azarm Nowzad , Michael Heigl , Fabian Bally , Martin Schramm

Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…

计算机视觉与模式识别 · 计算机科学 2020-10-20 Yotam Nitzan , Amit Bermano , Yangyan Li , Daniel Cohen-Or

Disentangled representation has been widely explored in many fields due to its maximal compactness, interpretability and versatility. Recommendation system also needs disentanglement to make representation more explainable and general for…

社会与信息网络 · 计算机科学 2020-10-27 Weiguang Chen , Wenjun Jiang , Xueqi Li , Kenli Li , Albert Zomaya , Guojun Wang

Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Mehmet Yigit Avci , Pedro Borges , Virginia Fernandez , Paul Wright , Mehmet Yigitsoy , Sebastien Ourselin , Jorge Cardoso

Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks. However, a persistent and long-standing limitation is the decline in facial identity (ID) consistency during realistic portrait editing.…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Yuran Dong , Hang Dai , Mang Ye

In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning. Existing classification-based methods for text-image…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Mingzhen Huang , Shan Jia , Zhou Zhou , Yan Ju , Jialing Cai , Siwei Lyu

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Chengcheng Wang , Jianyuan Guo , Hongguang Li , Yuchuan Tian , Ying Nie , Chang Xu , Kai Han

Visible-Infrared Person Re-identification (VI-ReID) is a challenging cross-modal pedestrian retrieval task, due to significant intra-class variations and cross-modal discrepancies among different cameras. Existing works mainly focus on…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Kaijie Ren , Lei Zhang

Camera-based person re-identification (ReID) systems have been widely applied in the field of public security. However, cameras often lack the perception of 3D morphological information of human and are susceptible to various limitations,…

计算机视觉与模式识别 · 计算机科学 2023-12-13 Wenxuan Guo , Zhiyu Pan , Yingping Liang , Ziheng Xi , Zhi Chen Zhong , Jianjiang Feng , Jie Zhou

The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks…

图像与视频处理 · 电气工程与系统科学 2025-08-26 Abhinau K. Venkataramanan , Cosmin Stejerean , Ioannis Katsavounidis , Hassene Tmar , Alan C. Bovik

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…

计算机视觉与模式识别 · 计算机科学 2021-06-11 Alexander H. Liu , SouYoung Jin , Cheng-I Jeff Lai , Andrew Rouditchenko , Aude Oliva , James Glass

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a…

计算机视觉与模式识别 · 计算机科学 2017-10-19 Dangwei Li , Xiaotang Chen , Zhang Zhang , Kaiqi Huang

The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique…

机器学习 · 计算机科学 2020-07-08 Graham Spinks , Marie-Francine Moens

Multi-spectral object Re-identification (ReID) aims to retrieve specific objects by leveraging complementary information from different image spectra. It delivers great advantages over traditional single-spectral ReID in complex visual…

计算机视觉与模式识别 · 计算机科学 2023-12-18 Yuhao Wang , Xuehu Liu , Pingping Zhang , Hu Lu , Zhengzheng Tu , Huchuan Lu

Multimodal data has significantly advanced recommendation systems by integrating diverse information sources to model user preferences and item characteristics. However, these systems often struggle with redundant and irrelevant…

信息检索 · 计算机科学 2025-09-25 Hui Wang , Jinghui Qin , Wushao Wen , Qingling Li , Shanshan Zhong , Zhongzhan Huang