Search Results for author: Han Zou

Found 16 papers, 4 papers with code

Mind the Discriminability: Asymmetric Adversarial Domain Adaptation

no code implementations ECCV 2020 Jianfei Yang, Han Zou, Yuxun Zhou, Zhaoyang Zeng, Lihua Xie ()

Adversarial domain adaptation has made tremendous success by learning domain-invariant feature representations.

Domain Adaptation

TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition

no code implementations14 Nov 2023 Yunjiao Zhou, Jianfei Yang, Han Zou, Lihua Xie

Through the IoT-language contrastive learning, we derive a unified semantic feature space that aligns multi-modal features with language embeddings, so that the IoT data corresponds to specific words that describe the IoT data.

Contrastive Learning Human Activity Recognition

RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution

no code implementations6 Jul 2023 Han Zou, Masanori Suganuma, Takayuki Okatani

Then, we propose an improved method, RefVSR++, which can aggregate two features in parallel in the temporal direction, one for aggregating the fused LR and Ref inputs and the other for Ref inputs over time.

Reference-based Video Super-Resolution Video Super-Resolution

Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image

no code implementations6 Jul 2023 Han Zou, Masanori Suganuma, Takayuki Okatani

We can utilize an alternative shot of the identical scene, just like in video deblurring, or we can even employ a distinct image from another scene.

Deblurring Image Deblurring

GaitFi: Robust Device-Free Human Identification via WiFi and Vision Multimodal Learning

1 code implementation30 Aug 2022 Lang Deng, Jianfei Yang, Shenghai Yuan, Han Zou, Chris Xiaoxuan Lu, Lihua Xie

As an important biomarker for human identification, human gait can be collected at a distance by passive sensors without subject cooperation, which plays an essential role in crime prevention, security detection and other human identification applications.

Gait Recognition Retrieval

MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation

no code implementations22 Aug 2022 Jianfei Yang, Yunjiao Zhou, He Huang, Han Zou, Lihua Xie

Avatar refers to a representative of a physical user in the virtual world that can engage in different activities and interact with other objects in metaverse.

Pose Estimation

AutoFi: Towards Automatic WiFi Human Sensing via Geometric Self-Supervised Learning

1 code implementation12 Apr 2022 Jianfei Yang, Xinyan Chen, Han Zou, Dazhuo Wang, Lihua Xie

The AutoFi transfers knowledge from randomly collected CSI samples into human gait recognition and achieves state-of-the-art performance.

Activity Recognition Domain Adaptation +4

EfficientFi: Towards Large-Scale Lightweight WiFi Sensing via CSI Compression

no code implementations8 Apr 2022 Jianfei Yang, Xinyan Chen, Han Zou, Dazhuo Wang, Qianwen Xu, Lihua Xie

WiFi technology has been applied to various places due to the increasing requirement of high-speed Internet access.

Cloud Computing Edge-computing +2

SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition

no code implementations4 Apr 2022 Jianfei Yang, Han Zou, Lihua Xie

The results validate that our method works well on wireless human activity recognition and person identification systems.

Adversarial Attack Human Activity Recognition +1

Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation

no code implementations28 Jan 2022 Changwei Xu, Jianfei Yang, Haoran Tang, Han Zou, Cheng Lu, Tianshuo Zhang

Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with the help of adversarially trained models.

Transfer Learning Unsupervised Domain Adaptation

Pushing the Envelope of Thin Crack Detection

no code implementations9 Jan 2021 Liang Xu, Taro Hatsutani, Xing Liu, Engkarat Techapanurak, Han Zou, Takayuki Okatani

We experimentally show that this makes it possible to detect cracks from an image of one-third the resolution of images used for annotation with about the same accuracy.

Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training

no code implementations ICLR 2020 Jianfei Yang, Han Zou, Yuxun Zhou, Lihua Xie

The proposed MDAT stabilizes the gradient reversing in ARN by replacing the domain classifier with a reconstruction network, and in this manner ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures.

Domain Adaptation Model Selection

Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation

no code implementations22 Jun 2014 Ming Jin, Han Zou, Kevin Weekly, Ruoxi Jia, Alexandre M. Bayen, Costas J. Spanos

We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant carried multi-purpose sensors.

energy management Management +1

Cannot find the paper you are looking for? You can Submit a new open access paper.