Zobrazeno 1 - 10
of 42 202
pro vyhledávání: '"An, Xiaochun"'
Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety. However, due to the rapid development of image tampering technologies, extracting more comprehensive and accurate forgery clues
Externí odkaz:
http://arxiv.org/abs/2412.09981
Autor:
Zhou, Chen, Cheng, Peng, Fang, Junfeng, Zhang, Yifan, Yan, Yibo, Jia, Xiaojun, Xu, Yanyan, Wang, Kun, Cao, Xiaochun
Multispectral object detection, utilizing RGB and TIR (thermal infrared) modalities, is widely recognized as a challenging task. It requires not only the effective extraction of features from both modalities and robust fusion strategies, but also the
Externí odkaz:
http://arxiv.org/abs/2411.18288
Autor:
Chen, Ruoyu, Liang, Siyuan, Li, Jingzhi, Liu, Shiming, Li, Maosen, Huang, Zheng, Zhang, Hua, Cao, Xiaochun
Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models\' decisions has grown increasingly chall
Externí odkaz:
http://arxiv.org/abs/2411.16198
Autor:
Sarajlic, Olesya, He, Xiaochun
Cosmic ray measurements have inspired numerous interesting applications over several decades worldwide. These applications encompass non-invasive cosmic ray muon tomography, which enables the imaging of concealed dense objects or structures, the moni
Externí odkaz:
http://arxiv.org/abs/2411.03142
Autor:
Jia, Xiaojun, Gao, Sensen, Guo, Qing, Ma, Ke, Huang, Yihao, Qin, Simeng, Liu, Yang, Fellow, Ivor Tsang, Cao, Xiaochun
Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to developin
Externí odkaz:
http://arxiv.org/abs/2411.02669
Autor:
Wu, Haibin, Li, Wenming, Yan, Kai, Fan, Zhihua, Wu, Peiyang, Liu, Yuqun, Liu, Yanhuan, Qiang, Ziqing, Wu, Meng, Liu, Kunming, Ye, Xiaochun, Fan, Dongrui
Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced to reduce
Externí odkaz:
http://arxiv.org/abs/2411.00734
Image restoration has experienced significant advancements due to the development of deep learning. Nevertheless, it encounters challenges related to ill-posed problems, resulting in deviations between single model predictions and ground-truths. Ense
Externí odkaz:
http://arxiv.org/abs/2410.22959
Autor:
Shen, Li, Tang, Anke, Yang, Enneng, Guo, Guibing, Luo, Yong, Zhang, Lefei, Cao, Xiaochun, Du, Bo, Tao, Dacheng
Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that merging the parameters of independently fine-tuned models can effectivel
Externí odkaz:
http://arxiv.org/abs/2410.21804
Design space exploration (DSE) enables architects to systematically evaluate various design options, guiding decisions on the most suitable configurations to meet specific objectives such as optimizing performance, power, and area. However, the growi
Externí odkaz:
http://arxiv.org/abs/2410.18368
Autor:
Luo, Yihong, Chen, Yuhan, Qiu, Siya, Wang, Yiwei, Zhang, Chen, Zhou, Yan, Cao, Xiaochun, Tang, Jing
Graph Neural Networks (GNNs) have shown superior performance in node classification. However, GNNs perform poorly in the Few-Shot Node Classification (FSNC) task that requires robust generalization to make accurate predictions for unseen classes with
Externí odkaz:
http://arxiv.org/abs/2410.16845