Tianxiao Han

ORCID: 0000-0003-1307-2575
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Speech and Audio Processing
  • Remote Sensing and LiDAR Applications
  • Speech Recognition and Synthesis
  • 3D Surveying and Cultural Heritage
  • Wireless Signal Modulation Classification
  • Digital Media Forensic Detection
  • Advanced Optical Sensing Technologies
  • Generative Adversarial Networks and Image Synthesis
  • Advanced Steganography and Watermarking Techniques
  • Gait Recognition and Analysis
  • Video Coding and Compression Technologies
  • 3D Shape Modeling and Analysis
  • Video Surveillance and Tracking Methods
  • Advanced Data Compression Techniques
  • Music and Audio Processing
  • Advanced Vision and Imaging
  • Advanced Image Processing Techniques

Zhejiang University
2022-2024

Xi'an Jiaotong University
2021

Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless that focus on abstract symbols, approaches attempt achieve better efficiency by only sending semantic-related information source data. this paper, we consider semantic-oriented which transmits semantic-relevant over channel recognition task, a compact additional set semantic-irrelevant reconstruction task....

10.1109/jsac.2022.3221952 article EN IEEE Journal on Selected Areas in Communications 2022-11-16

Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model further improve the efficiency of image transmission and protect private information. particular, transmitter extracts interpretable latent representation from original by exploiting GAN inversion method. We also employ privacy filter knowledge base erase information replace it with natural features base. The simulation...

10.1109/icassp49357.2023.10096372 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023-05-05

Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless that focus on abstract symbols, approaches attempt achieve better efficiency by only sending semantic-related information source data. this paper, we consider semantic-oriented text transmission. We propose a novel end-to-end DL-based transceiver, which includes an attention-based soft alignment module...

10.1109/iccworkshops53468.2022.9814492 article EN 2022 IEEE International Conference on Communications Workshops (ICC Workshops) 2022-05-16

10.1109/globecom52923.2024.10901573 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2024-12-08

As three-dimensional (3D) data acquisition devices become increasingly prevalent, the demand for 3D point cloud transmission is growing. In this study, we introduce a semanticaware communication system robust classification that capitalizes on advantages of pre-trained Point-BERT models. Our proposed method comprises four main components: semantic encoder, channel decoder, and decoder. By employing two-stage training strategy, our facilitates efficient adaptable learning tailored to specific...

10.1109/globecom54140.2023.10437861 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2023-12-04

As three-dimensional acquisition technologies like LiDAR cameras advance, the need for efficient transmission of 3D point clouds is becoming increasingly important. In this paper, we present a novel semantic communication (SemCom) approach cloud transmission. Different from existing methods that rely on downsampling and feature extraction compression, our utilizes parallel structure to separately extract both global local information clouds. This system composed five key components: encoder,...

10.48550/arxiv.2409.03319 preprint EN arXiv (Cornell University) 2024-09-05

As three-dimensional (3D) data acquisition devices become increasingly prevalent, the demand for 3D point cloud transmission is growing. In this study, we introduce a semantic-aware communication system robust classification that capitalizes on advantages of pre-trained Point-BERT models. Our proposed method comprises four main components: semantic encoder, channel decoder, and decoder. By employing two-stage training strategy, our facilitates efficient adaptable learning tailored to...

10.48550/arxiv.2306.13296 preprint EN other-oa arXiv (Cornell University) 2023-01-01

Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless that focus on abstract symbols, approaches attempt achieve better efficiency by only sending semantic-related information source data. this paper, we consider semantic-oriented which transmits semantic-relevant over channel recognition task, a compact additional set semantic-irrelevant reconstruction task....

10.48550/arxiv.2205.12727 preprint EN other-oa arXiv (Cornell University) 2022-01-01

Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years. In contrast to traditional wireless that focus on abstract symbols, approaches attempt achieve better efficiency by only sending semantic-related information source data. this paper, we consider semantic-oriented text transmission. We propose a novel end-to-end DL-based transceiver, which includes an attention-based soft alignment module...

10.48550/arxiv.2202.03211 preprint EN other-oa arXiv (Cornell University) 2022-01-01

Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model further improve the efficiency of image transmission and protect private information. particular, transmitter extracts interpretable latent representation from original by exploiting GAN inversion method. We also employ privacy filter knowledge base erase information replace it with natural features base. The simulation...

10.48550/arxiv.2211.10287 preprint EN cc-by arXiv (Cornell University) 2022-01-01

With the more and common use of infrared video in life, people have higher requirements for imaging frame rates. Better quality images provide a better basis subsequent target recognition, compression decompression operations. Therefore, it is great significance to effectively obtain high rate improve images. As an effective means conversion, enhancement technology has become research hotspot direction computer vision. However, existing interpolation methods based on are all implemented...

10.1145/3474963.3475843 article EN 2021-06-25
Coming Soon ...