no code implementations • 10 Mar 2024 • Chenxing Gao, Hang Zhou, Junqing Yu, Yuteng Ye, Jiale Cai, Junle Wang, Wei Yang
Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications.
no code implementations • 20 Dec 2023 • Beibei Jing, Youjia Zhang, Zikai Song, Junqing Yu, Wei Yang
Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion. Recent advances in diffusion models have enabled significant progress in human motion synthesis. However, existing methods struggle to handle text inputs that describe complex or long motions. In this paper, we propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion. This process exploits the LLM's ability to provide anatomical guidance for complex motion synthesis. We then devise a two-branch fusion scheme that balances the influence of the input text and the anatomical scripts on the inverse diffusion process, which adaptively ensures the semantic fidelity and diversity of the synthesized motion. Our method can effectively handle texts with complex or long motion descriptions, where existing methods often fail.
no code implementations • 11 Dec 2023 • Youjia Zhang, Zikai Song, Junqing Yu, Yawei Luo, Wei Yang
We leverage the rendered views from the optimized radiance field as the basis and develop a two-step specialization process of a 2D diffusion model, which is adept at conducting object-specific denoising and generating high-quality multi-view images.
1 code implementation • 27 Nov 2023 • Yuteng Ye, Guanwen Li, Hang Zhou, Cai Jiale, Junqing Yu, Yawei Luo, Zikai Song, Qilong Xing, Youjia Zhang, Wei Yang
A pivotal aspect of our approach is the strategic use of the predicted $x_0$ space by diffusion models within the latent space of diffusion processes.
1 code implementation • 18 Sep 2023 • Yuteng Ye, Jiale Cai, Hang Zhou, Guanwen Li, Youjia Zhang, Zikai Song, Chenxing Gao, Junqing Yu, Wei Yang
In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges.
no code implementations • ICCV 2023 • Youjia Zhang, Teng Xu, Junqing Yu, Yuteng Ye, Junle Wang, Yanqing Jing, Jingyi Yu, Wei Yang
Recovering the physical attributes of an object's appearance from its images captured under an unknown illumination is challenging yet essential for photo-realistic rendering.
1 code implementation • 10 Feb 2023 • Hang Zhou, Junqing Yu, Wei Yang
To address this issue, we propose an Uncertainty Regulated Dual Memory Units (UR-DMU) model to learn both the representations of normal data and discriminative features of abnormal data.
1 code implementation • 26 Jan 2023 • Zikai Song, Run Luo, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang
Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism.
1 code implementation • 27 Nov 2022 • Yuteng Ye, Hang Zhou, Jiale Cai, Chenxing Gao, Youjia Zhang, Junle Wang, Qiang Hu, Junqing Yu, Wei Yang
The framework mainly consists of a sparse encoder, a multi-view feature mathcing module, and a feature consolidation decoder.
1 code implementation • CVPR 2022 • Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism.
no code implementations • 8 Mar 2022 • Ziyu Wang, Wei Yang, Junming Cao, Lan Xu, Junqing Yu, Jingyi Yu
We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.
1 code implementation • NeurIPS 2020 • Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, Yi Yang
We aim at the problem named One-Shot Unsupervised Domain Adaptation.
domain classification One-shot Unsupervised Domain Adaptation +2
no code implementations • ICCV 2019 • Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, Yi Yang
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks in which the latent representations are overcomplex.
1 code implementation • 26 Sep 2018 • Yawei Luo, Tao Guan, Junqing Yu, Ping Liu, Yi Yang
To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning.
Ranked #4 on Node Classification on Cora: fixed 20 node per class
1 code implementation • CVPR 2019 • Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
We consider the problem of unsupervised domain adaptation in semantic segmentation.
Ranked #8 on Semantic Segmentation on DADA-seg
1 code implementation • ECCV 2018 • Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN).
Ranked #12 on Semantic Segmentation on LIP val