1 code implementation • 18 Aug 2023 • Ke Yang, Sixian Wang, Jincheng Dai, Xiaoqi Qin, Kai Niu, Ping Zhang
As one of the key techniques to realize semantic communications, end-to-end optimized neural joint source-channel coding (JSCC) has made great progress over the past few years.
no code implementations • 26 Mar 2023 • Sixian Wang, Jincheng Dai, Xiaoqi Qin, Kai Niu, Ping Zhang
We first focus on those two paradigms of NeurJSCC by identifying their common and different components in building end-to-end communication systems.
no code implementations • 26 Mar 2023 • Sixian Wang, Jincheng Dai, Xiaoqi Qin, Zhongwei Si, Kai Niu, Ping Zhang
First, we introduce a contextual entropy model to better capture the spatial correlations among the semantic latent features, thereby more accurate rate allocation and contextual joint source-channel coding are developed accordingly to enable higher coding gain.
no code implementations • 8 Nov 2022 • Jincheng Dai, Sixian Wang, Ke Yang, Kailin Tan, Xiaoqi Qin, Zhongwei Si, Kai Niu, Ping Zhang
Specifically, we update the off-the-shelf pre-trained models after deployment in a lightweight online fashion to adapt to the distribution shifts in source data and environment domain.
1 code implementation • ECCV 2022 2022 • Wei Suo, Mengyang Sun, Kai Niu, Yiqi Gao, Peng Wang, Yanning Zhang, Qi Wu
Text-based person search aims to associate pedestrian images with natural language descriptions.
Ranked #8 on Text based Person Retrieval on ICFG-PEDES
2 code implementations • 2 Nov 2022 • Ke Yang, Sixian Wang, Jincheng Dai, Kailin Tan, Kai Niu, Ping Zhang
In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT).
no code implementations • 4 Aug 2022 • Jincheng Dai, Ping Zhang, Kai Niu, Sixian Wang, Zhongwei Si, Xiaoqi Qin
Classical communication paradigms focus on accurately transmitting bits over a noisy channel, and Shannon theory provides a fundamental theoretical limit on the rate of reliable communications.
no code implementations • 26 May 2022 • Jun Wang, Sixian Wang, Jincheng Dai, Zhongwei Si, Dekun Zhou, Kai Niu
However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM).
no code implementations • 26 May 2022 • Sixian Wang, Jincheng Dai, Zijian Liang, Kai Niu, Zhongwei Si, Chao Dong, Xiaoqi Qin, Ping Zhang
In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels.
no code implementations • 7 May 2022 • Zhipeng Zhang, Xinglin Hou, Kai Niu, Zhongzhen Huang, Tiezheng Ge, Yuning Jiang, Qi Wu, Peng Wang
Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation.
no code implementations • 25 Jan 2022 • Sixian Wang, Ke Yang, Jincheng Dai, Kai Niu
In particular, we consider a pair of images captured by two cameras with probably overlapping fields of view transmitted over wireless channels and reconstructed in the center node.
1 code implementation • 21 Dec 2021 • Jincheng Dai, Sixian Wang, Kailin Tan, Zhongwei Si, Xiaoqi Qin, Kai Niu, Ping Zhang
In the considered model, the transmitter first learns a nonlinear analysis transform to map the source data into latent space, then transmits the latent representation to the receiver via deep joint source-channel coding.
1 code implementation • 27 Sep 2021 • Shizhou Zhang, De Cheng, Wenlong Luo, Yinghui Xing, Duo Long, Hao Li, Kai Niu, Guoqiang Liang, Yanning Zhang
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance. However, different from the real-world scenarios where the bounding boxes are not available, existing text-based person retrieval methods mainly focus on the cross modal matching between the query text descriptions and the gallery of cropped pedestrian images.
no code implementations • 2 Nov 2020 • Jianhua Yang, Yan Huang, Kai Niu, Linjiang Huang, Zhanyu Ma, Liang Wang
Previous methods fail to explicitly align the video content with the textual query in a fine-grained manner according to the actor and its action, due to the problem of \emph{semantic asymmetry}.
Ranked #9 on Referring Expression Segmentation on J-HMDB
no code implementations • 23 Jun 2019 • Kai Niu, Yan Huang, Wanli Ouyang, Liang Wang
Firstly, the global-global alignment in the Global Contrast (GC) module is for matching the global contexts of images and descriptions.
Ranked #19 on Text based Person Retrieval on CUHK-PEDES
1 code implementation • 17 Aug 2012 • Kai Chen, Kai Niu, Jia-Ru Lin
As improved versions of successive cancellation (SC) decoding algorithm, successive cancellation list (SCL) decoding and successive cancellation stack (SCS) decoding are used to improve the finite-length performance of polar codes.
Information Theory Information Theory