1 code implementation • 31 Mar 2024 • Jiading Li, Zhiyu Zhu, Jinhui Hou, Junhui Hou, Jinjian Wu
Technically, we propose a two-stage learning-based gaze estimation framework to divide the whole gaze estimation process into a coarse-to-fine process of anchor state selection and final gaze location.
1 code implementation • 1 Feb 2024 • Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Huaming Chen
The robustness of deep learning models against adversarial attacks remains a pivotal concern.
no code implementations • 25 Jan 2024 • Zhiyu Zhu, Yang Yang, Mingzhe Chen, Caili Guo, Julian Cheng, Shuguang Cui
This paper provides a comprehensive survey of VLP systems.
1 code implementation • 11 Jan 2024 • Zhiyu Zhu, Huaming Chen, Xinyi Wang, Jiayu Zhang, Zhibo Jin, Kim-Kwang Raymond Choo, Jun Shen, Dong Yuan
With the functional and characteristic similarity analysis, we introduce a novel gradient editing (GE) mechanism and verify its feasibility in generating transferable samples on various models.
1 code implementation • 24 Dec 2023 • Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu
One pivotal issue at the heart of this endeavor is the precise alignment and calibration of embeddings derived from event-centric data such that they harmoniously coincide with those originating from RGB imagery.
Ranked #1 on Event-based Object Segmentation on DSEC-SEG
1 code implementation • 21 Dec 2023 • Zhiyu Zhu, Huaming Chen, Jiayu Zhang, Xinyi Wang, Zhibo Jin, Minhui Xue, Dongxiao Zhu, Kim-Kwang Raymond Choo
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome.
1 code implementation • NeurIPS 2023 • Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Hui Yuan
To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.
Ranked #2 on Low-Light Image Enhancement on LOL
1 code implementation • 16 Oct 2023 • Zhibo Jin, Zhiyu Zhu, Xinyi Wang, Jiayu Zhang, Jun Shen, Huaming Chen
While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments.
1 code implementation • ICCV 2023 • Zhiyu Zhu, Junhui Hou, Dapeng Oliver Wu
This paper addresses the problem of cross-modal object tracking from RGB videos and event data.
Ranked #1 on Object Tracking on COESOT
1 code implementation • 1 Jul 2023 • Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Wu
Specifically, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context.
1 code implementation • 15 Jan 2023 • Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Deyu Meng
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity.
no code implementations • 9 Jul 2022 • Jinhui Hou, Zhiyu Zhu, Hui Liu, Junhui Hou
This paper tackles the challenging problem of hyperspectral (HS) image denoising.
1 code implementation • 6 Jul 2022 • Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan
The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors to build probabilistic detectors and supervise the learning of the localization uncertainty.
Ranked #1 on 3D Object Detection on KITTI Cars Easy
1 code implementation • 30 May 2022 • Jinhui Hou, Zhiyu Zhu, Junhui Hou, Huanqiang Zeng, Jinjian Wu, Jiantao Zhou
Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing lightweight PDE-Net, in which high-resolution (HR) HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR-HS images via probability-inspired HS embedding.
no code implementations • 18 Apr 2022 • Zhiyu Zhu, Caili Guo, Rongzhen Bao, Mingzhe Chen, Walid Saad, Yang Yang
In this paper, the arc feature of the circular luminaire and the coordinate information obtained via visible light communication (VLC) are jointly used for VLC-enabled indoor positioning, and a novel perspective arcs approach is proposed.
1 code implementation • ICCV 2021 • Zhiyu Zhu, Hui Liu, Junhui Hou, Huanqiang Zeng, Qingfu Zhang
Specifically, on the basis of the intrinsic imaging degradation model of RGB images from HS images, we progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective unsupervised camera spectral response function estimation.
1 code implementation • 12 Aug 2021 • Zhiyu Zhu, Hui Liu, Junhui Hou, Sen Jia, Qingfu Zhang
Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.
1 code implementation • CVPR 2021 • Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan, Ying He
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
Ranked #6 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)
no code implementations • 26 Sep 2020 • Jing Jin, Junhui Hou, Zhiyu Zhu, Jie Chen, Sam Kwong
To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation.
1 code implementation • 18 Jun 2020 • Zhiyu Zhu, Junhui Hou, Jie Chen, Huanqiang Zeng, Jiantao Zhou
Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension.
Hyperspectral Image Super-Resolution Hyperspectral Unmixing +1
no code implementations • 17 Jun 2020 • Yang Yang, Zhiyu Zhu, Caili Guo, Chunyan Feng
Due to the interactions among LEDs and the illumination uniformity constraint, the formulated problem is complex and non-convex.
no code implementations • 19 Apr 2020 • Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou, Yi Wang, Lap-Pui Chau
However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.