Zobrazeno 1 - 10
of 363
pro vyhledávání: '"Cui, Qimei"'
Autor:
Lin, Honglin, Li, Siyu, Nan, Guoshun, Tang, Chaoyue, Wang, Xueting, Xu, Jingxin, Yankai, Rong, Zhou, Zhili, Gao, Yutong, Cui, Qimei, Tao, Xiaofeng
Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the success of VLMs, they still significantly lag behind human performance in
Externí odkaz:
http://arxiv.org/abs/2405.19226
Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
Autor:
Du, Hang, Zhang, Sicheng, Xie, Binzhu, Nan, Guoshun, Zhang, Jiayang, Xu, Junrui, Liu, Hangyu, Leng, Sicong, Liu, Jiangming, Fan, Hehe, Huang, Dajiu, Feng, Jing, Chen, Linli, Zhang, Can, Li, Xuhuan, Zhang, Hao, Chen, Jianhang, Cui, Qimei, Tao, Xiaofeng
Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on
Externí odkaz:
http://arxiv.org/abs/2405.00181
Autor:
Rong, Yankai, Nan, Guoshun, Zhang, Minwei, Chen, Sihan, Wang, Songtao, Zhang, Xuefei, Ma, Nan, Gong, Shixun, Yang, Zhaohui, Cui, Qimei, Tao, Xiaofeng, Quek, Tony Q. S.
Recently proliferated deep learning-based semantic communications (DLSC) focus on how transmitted symbols efficiently convey a desired meaning to the destination. However, the sensitivity of neural models and the openness of wireless channels cause t
Externí odkaz:
http://arxiv.org/abs/2402.02950
Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks
Autor:
Qiu, Chenyang, Nan, Guoshun, Xiong, Tianyu, Deng, Wendi, Wang, Di, Teng, Zhiyang, Sun, Lijuan, Cui, Qimei, Tao, Xiaofeng
Graph convolution networks (GCNs) are extensively utilized in various graph tasks to mine knowledge from spatial data. Our study marks the pioneering attempt to quantitatively investigate the GCN robustness over omnipresent heterophilic graphs for no
Externí odkaz:
http://arxiv.org/abs/2312.16418
Autor:
Du, Hang, Nan, Guoshun, Zhang, Sicheng, Xie, Binzhu, Xu, Junrui, Fan, Hehe, Cui, Qimei, Tao, Xiaofeng, Jiang, Xudong
Multimodal Sarcasm Understanding (MSU) has a wide range of applications in the news field such as public opinion analysis and forgery detection. However, existing MSU benchmarks and approaches usually focus on sentence-level MSU. In document-level ne
Externí odkaz:
http://arxiv.org/abs/2312.16023
Autor:
Gong, Zhenzhen, Hashash, Omar, Wang, Yingze, Cui, Qimei, Ni, Wei, Saad, Walid, Sakaguchi, Kei
In this paper, a novel joint energy and age of information (AoI) optimization framework for IoT devices in a non-stationary environment is presented. In particular, IoT devices that are distributed in the real-world are required to efficiently utiliz
Externí odkaz:
http://arxiv.org/abs/2312.00334
Autor:
Liu, Xinghan, Nan, Guoshun, Cui, Qimei, Li, Zeju, Liu, Peiyuan, Xing, Zebin, Mu, Hanqing, Tao, Xiaofeng, Quek, Tony Q. S.
Recently proliferated semantic communications (SC) aim at effectively transmitting the semantics conveyed by the source and accurately interpreting the meaning at the destination. While such a paradigm holds the promise of making wireless communicati
Externí odkaz:
http://arxiv.org/abs/2309.01386
Autor:
Qiu, Chenyang, Geng, Yingsheng, Lu, Junrui, Chen, Kaida, Zhu, Shitong, Su, Ya, Nan, Guoshun, Zhang, Can, Fu, Junsong, Cui, Qimei, Tao, Xiaofeng
Network-based intrusion detection system (NIDS) monitors network traffic for malicious activities, forming the frontline defense against increasing attacks over information infrastructures. Although promising, our quantitative analysis shows that exi
Externí odkaz:
http://arxiv.org/abs/2307.11079
Autor:
Nan, Guoshun, Li, Zhichun, Zhai, Jinli, Cui, Qimei, Chen, Gong, Du, Xin, Zhang, Xuefei, Tao, Xiaofeng, Han, Zhu, Quek, Tony Q. S.
End-to-end semantic communications (ESC) rely on deep neural networks (DNN) to boost communication efficiency by only transmitting the semantics of data, showing great potential for high-demand mobile applications. We argue that central to the succes
Externí odkaz:
http://arxiv.org/abs/2305.07220
Deep learning based semantic communication(DLSC) systems have shown great potential of making wireless networks significantly more efficient by only transmitting the semantics of the data. However, the open nature of wireless channel and fragileness
Externí odkaz:
http://arxiv.org/abs/2304.10147