arXiv subjects

Jinhong Yang

Publications and source records attributed to Jinhong Yang.

5 recordsLinked to original sources

arXiv2026

AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose

Existing face-swapping methods often deliver competitive results in constrained settings but exhibit substantial quality degradation when handling extreme facial poses. To improve facial pose robustness, explicit geometric features are applied, but this approach remains problematic since it introduces additional dependencies and increases computational cost. Diffusion-based methods have achieved remarkable results; however, they are impractical for real-time processing. We introduce AlphaFace, which leverages an open-source vision-language model and CLIP image and text embeddings to apply novel visual and textual semantic contrastive losses. AlphaFace enables stronger identity representation and more precise attribute preservation, all while maintaining real-time performance. Comprehensive experiments across FF++, MPIE, and LPFF demonstrate that AlphaFace surpasses state-of-the-art methods in pose-challenging cases. The project is publicly available on `https://github.com/andrewyu90/Alphaface_Official.git'.

cs.CV↗

arXiv2025

Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation

Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or weakly labelled target domains. One of the most efficient strategies involves using synthetic datasets generated within controlled virtual environments, such as video games or traffic simulators, which can automatically generate pixel-level annotations. However, even when such datasets are available, learning a well-generalised representation that captures both domains remains challenging, owing to probabilistic and geometric discrepancies between the virtual world and real-world imagery. This work introduces a semantic segmentation method based on latent diffusion models, termed Inter-Coder Connected Latent Diffusion (ICCLD), alongside an unsupervised domain adaptation approach. The model employs an inter-coder connection to enhance contextual understanding and preserve fine details, while adversarial learning aligns latent feature distributions across domains during the latent diffusion process. Experiments on GTA5, Synthia, and Cityscapes demonstrate that ICCLD outperforms state-of-the-art UDA methods, achieving mIoU scores of 74.4 (GTA5$\rightarrow$Cityscapes) and 67.2 (Synthia$\rightarrow$Cityscapes).

cs.CV↗

arXiv2023

Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection

In this paper, we propose the Adversarial Denoising Diffusion Model (ADDM). The ADDM is based on the Denoising Diffusion Probabilistic Model (DDPM) but complementarily trained by adversarial learning. The proposed adversarial learning is achieved by classifying model-based denoised samples and samples to which random Gaussian noise is added to a specific sampling step. With the addition of explicit adversarial learning on data samples, ADDM can learn the semantic characteristics of the data more robustly during training, which achieves a similar data sampling performance with much fewer sampling steps than DDPM. We apply ADDM to anomaly detection in unsupervised MRI images. Experimental results show that the proposed ADDM outperformed existing generative model-based unsupervised anomaly detection methods. In particular, compared to other DDPM-based anomaly detection methods, the proposed ADDM shows better performance with the same number of sampling steps and similar performance with 50% fewer sampling steps.

eess.IV↗

arXiv2020

The pagoda instability (PI) on soluble fibers

This paper presents a new kind of instability when inserting a soluble fiber into liquid. After wetting and dissolving the fiber by the liquid, the moving contact line (MCL) spontaneously loses stability. Because the sculpted shape from fiber looks like a Chinese pagoda, we name this instability as pagoda instability (PI). Coupling of dissolution and wetting leads to other special phenomena, i.e. dissolving-induced jet flow, and optimizes the fiber shape, etc. We propose a criterion of PI and show the competition between interface energy and chemical potential deduce the MCL motion and PI. A phase diagram is used to summary the final shapes of fibers. By conducting atomic force microscope (AFM) measurement, we find the fiber with optimized-shape has the characteristics of low adhesion force. Using the optimized-fiber can decrease the 70% influence of capillary force for AFM measurement in humid environment.

physics.chem-ph↗

arXiv2019

Communication Interface Identifier Protocol (CIIP): An Energy Efficient Protocol for smaller IoT Sensor

Today we can use technologies like switched Ethernet, TCP/IP, high-speed wide area networks, and high-performance low-cost computers very easily. However, protocols designed for those communication are inefficient or not energy efficient. Smart home, smart grid, blockchain, Internet of Things (IoT) all these technologies are coming very rapidly with higher communication facilities demands an energy efficient Ethernet. Due to controller and network equipment use a huge quantity of energy. Layer to layer communication making our communication method more complex and costly. In this work, we propose an architecture, which will make the communication of sensor devices to outside world easier. Our proposed system removes certain layer from TCP-IP communication. We used a communication interface identifier protocol (CIIP) which can be used for smaller IoT sensors.

cs.NI↗