no code implementations • 13 Feb 2025 • Fei Shen, Cong Wang, Junyao Gao, Qin Guo, Jisheng Dang, Jinhui Tang, Tat-Seng Chua
Recent advances in conditional diffusion models have shown promise for generating realistic TalkingFace videos, yet challenges persist in achieving consistent head movement, synchronized facial expressions, and accurate lip synchronization over extended generations.
no code implementations • 17 Dec 2024 • Lei Xin, Caiyun Huang, Hao Li, Shihong Huang, Yuling Feng, Zhenglun Kong, Zicheng Liu, Siyuan Li, Chang Yu, Fei Shen, Hao Tang
With the rapid development of high-throughput sequencing platforms, an increasing number of omics technologies, such as genomics, metabolomics, and transcriptomics, are being applied to disease genetics research.
no code implementations • 16 Dec 2024 • Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang
Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas.
1 code implementation • 14 Aug 2024 • Xue Xia, Kun Zhan, Yuming Fang, Wenhui Jiang, Fei Shen
To this end, we propose a CNN-based DR diagnosis network with attention mechanism involved, termed lesion-aware network, to better capture lesion information from imbalanced data.
1 code implementation • 1 Aug 2024 • Qingfeng Shi, Jing Wei, Fei Shen, Zhengtao Zhang
To address these issues, we propose DefectDiffu, a novel text-guided diffusion method to model both intra-product background consistency and inter-product defect consistency across multiple products and modulate the consistency perturbation directions to control product type and defect strength, achieving diversified defect image generation.
no code implementations • 27 Jul 2024 • Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jinguo Luo, Tianlu Mao, Zhaoqi Wang
However, such methods mainly concentrate on searching for pixels without matching ambiguity (i. e., reliable pixels) when constructing deformed patches, while neglecting the deformation instability caused by unexpected edge-skipping, resulting in potential matching distortions.
1 code implementation • 17 Jul 2024 • Fei Shen, Xin Jiang, Xin He, Hu Ye, Cong Wang, Xiaoyu Du, Zechao Li, Jinhui Tang
Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting using latent diffusion models, significantly enhancing consumers' online shopping experience.
1 code implementation • 17 Jul 2024 • Zhen Qu, Xian Tao, Mukesh Prasad, Fei Shen, Zhengtao Zhang, Xinyi Gong, Guiguang Ding
In this end, we propose a visual context prompting model (VCP-CLIP) for ZSAS task based on CLIP.
Ranked #6 on
Anomaly Detection
on VisA
(Segmentation AUPRO metric, using extra
training data)
1 code implementation • 2 Jul 2024 • Fei Shen, Hu Ye, Sibo Liu, Jun Zhang, Cong Wang, Xiao Han, Wei Yang
Moreover, RCDMs can generate consistent stories with a single forward inference compared to autoregressive models.
no code implementations • 4 Jun 2024 • Cong Wang, Kuan Tian, Jun Zhang, Yonghang Guan, Feng Luo, Fei Shen, Zhiwei Jiang, Qing Gu, Xiao Han, Wei Yang
In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as facial pose and reference image.
1 code implementation • 27 May 2024 • Cong Wang, Kuan Tian, Yonghang Guan, Jun Zhang, Zhiwei Jiang, Fei Shen, Xiao Han, Qing Gu, Wei Yang
In this paper, we propose a novel ensembling method, Adaptive Feature Aggregation (AFA), which dynamically adjusts the contributions of multiple models at the feature level according to various states (i. e., prompts, initial noises, denoising steps, and spatial locations), thereby keeping the advantages of multiple diffusion models, while suppressing their disadvantages.
no code implementations • 12 May 2024 • Changpeng Cai, Guinan Guo, Jiao Li, Junhao Su, Fei Shen, Chenghao He, Jing Xiao, Yuanxu Chen, Lei Dai, Feiyu Zhu
Then we design a face editing module that modifies speech content and facial latent codes into a single latent space.
no code implementations • 2 Apr 2024 • Hanqian Li, Ruinan Zhang, Ye Pan, Junchi Ren, Fei Shen
To address this, we propose a novel location refined feature pyramid network (LR-FPN) to enhance the extraction of shallow positional information and facilitate fine-grained context interaction.
no code implementations • 27 Mar 2024 • Mengjiang Sun, Peng Chen, Zhenxin Cao, Fei Shen
Hence, a novel decomposed decoupled atomic norm minimization (DANM) method is proposed by splitting the 3D-parameter estimating matrix into multiple 2D matrices with sparsity constraints.
1 code implementation • 10 Oct 2023 • Fei Shen, Hu Ye, Jun Zhang, Cong Wang, Xiao Han, Wei Yang
Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance.
1 code implementation • 29 Sep 2023 • Zhen Qu, Xian Tao, Fei Shen, Zhengtao Zhang, Tao Li
In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consistency (also referred to equivalence) of the model is often overlooked.
no code implementations • 23 Aug 2023 • Han Gao, Huiyuan Luo, Fei Shen, Zhengtao Zhang
One-class classification (OCC) is a longstanding method for anomaly detection.
1 code implementation • 25 Jun 2023 • Xian Tao, Zhen Qu, Hengliang Luo, Jianwen Han, Yonghao He, Danfeng Liu, Chengkan Lv, Fei Shen, Zhengtao Zhang
The Vision Challenge Track 1 for Data-Effificient Defect Detection requires competitors to instance segment 14 industrial inspection datasets in a data-defificient setting.
no code implementations • 25 May 2023 • Han Gao, Huiyuan Luo, Fei Shen, Zhengtao Zhang
Although existing image anomaly detection methods yield impressive results, they are mostly an offline learning paradigm that requires excessive data pre-collection, limiting their adaptability in industrial scenarios with online streaming data.
Ranked #10 on
Anomaly Detection
on MPDD
1 code implementation • 23 Jan 2023 • Fei Shen, Xiaoyu Du, Liyan Zhang, Xiangbo Shu, Jinhui Tang
To address this problem, in this paper, we propose a simple Triplet Contrastive Representation Learning (TCRL) framework which leverages cluster features to bridge the part features and global features for unsupervised vehicle re-identification.
no code implementations • 10 Nov 2022 • Fei Shen, Mengwan Wei, Junchi Ren
Secondly, we divide the feature map along with the spatial and channel directions in each hierarchical graph.
1 code implementation • 31 May 2022 • Fei Shen, Zhe Wang, Zijun Wang, Xiaode Fu, Jiayi Chen, Xiaoyu Du, Jinhui Tang
Vision-based pattern identification (such as face, fingerprint, iris etc.)
no code implementations • 12 Jul 2021 • Fei Shen, Yi Xie, Jianqing Zhu, Xiaobin Zhu, Huanqiang Zeng
In the macro view, a list of GiT blocks are stacked to build a vehicle re-identification model, in where graphs are to extract discriminative local features within patches and transformers are to extract robust global features among patches.
Ranked #2 on
Vehicle Re-Identification
on VehicleID Small
(mAP metric)
no code implementations • 19 Apr 2021 • Fei Shen, Xin He, Mengwan Wei, Yi Xie
In this report, we introduce the technical details of our submission to the VIPriors object detection challenge.
1 code implementation • 29 May 2020 • Fei Shen, Jianqing Zhu, Xiaobin Zhu, Yi Xie, Jingchang Huang
Secondly, a novel pyramidal graph network (PGN) is designed to comprehensively explore the spatial significance of feature maps at multiple scales.
Ranked #3 on
Vehicle Re-Identification
on VehicleID Small
(mAP metric)