no code implementations • 1 May 2024 • Jincheng Zhang, Qijun Zhao, Tie Liu
To facilitate the re-identification (Re-ID) of individual animals, existing methods primarily focus on maximizing feature similarity within the same individual and enhancing distinctiveness between different individuals.
no code implementations • 17 Mar 2024 • Zuyuan He, Zongyong Deng, Qiaoyun He, Qijun Zhao
To address the above issues, we propose a novel morphing attack method to improve the quality of morphed images and better preserve the contributing identities.
no code implementations • 4 Mar 2024 • Xin Zhang, Tao Xiao, GePeng Ji, Xuan Wu, Keren Fu, Qijun Zhao
The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner.
no code implementations • 16 Feb 2024 • Xin Zhang, Keren Fu, Qijun Zhao
To facilitate the seamless integration of global classification features with the finely detailed local features selected by DPSM, we introduce a novel feature blending module (FBM).
no code implementations • 30 Jan 2024 • Qiaoyun He, Zongyong Deng, Zuyuan He, Qijun Zhao
Our proposed method overcomes the limitations of previous approaches by optimizing the morphing landmarks and using Graph Convolutional Networks (GCNs) to combine landmark and appearance features.
no code implementations • 30 Dec 2023 • Xianjie Liu, Keren Fu, Qijun Zhao
We have high expectations regarding whether SAM, as a foundation model, can be improved towards highly accurate object segmentation, which is known as dichotomous image segmentation (DIS).
2 code implementations • 24 Oct 2023 • Ao Mou, Yukang Lu, Jiahao He, Dingyao Min, Keren Fu, Qijun Zhao
Ablation experiments were performed on both pseudo and realistic RGB-D video datasets to demonstrate the advantages of individual modules as well as the necessity of introducing realistic depth.
1 code implementation • ICCV 2023 • Ruowei Wang, Yu Liu, Pei Su, Jianwei Zhang, Qijun Zhao
Our method utilizes implicit functions as the 3D shape representation and combines a novel latent-space GAN with a linear subspace model to discover semantic dimensions in the local latent space of 3D shapes.
no code implementations • 9 May 2023 • Bo Yuan, Yao Jiang, Keren Fu, Qijun Zhao
To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features.
no code implementations • 19 Nov 2022 • Yaxuan Wang, Zhixin Zeng, Qijun Zhao
Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function.
1 code implementation • 8 Aug 2022 • Wenbo Zhang, Keren Fu, Zhuo Wang, Ge-Peng Ji, Qijun Zhao
Inspired by the fact that depth quality is a key factor influencing the accuracy, we propose an efficient depth quality-inspired feature manipulation (DQFM) process, which can dynamically filter depth features according to depth quality.
no code implementations • 5 Jul 2022 • Xucheng Wang, Dan Zeng, Qijun Zhao, Shuiwang Li
Model compression is a promising way to narrow the gap (i. e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking.
1 code implementation • CVPR 2022 • Mingbo Hong, Yuhang Lu, Nianjin Ye, Chunyu Lin, Qijun Zhao, Shuaicheng Liu
Estimating homography from an image pair is a fundamental problem in image alignment.
2 code implementations • 12 Feb 2022 • Yukang Lu, Dingyao Min, Keren Fu, Qijun Zhao
However, existing video salient object detection (VSOD) methods only utilize spatiotemporal information and seldom exploit depth information for detection.
1 code implementation • 5 Jul 2021 • Wenbo Zhang, Ge-Peng Ji, Zhuo Wang, Keren Fu, Qijun Zhao
To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy.
2 code implementations • 4 Jul 2021 • Mingbo Hong, Shuiwang Li, Yuchao Yang, Feiyu Zhu, Qijun Zhao, Li Lu
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.
no code implementations • 1 May 2021 • Shuiwang Li, Qijun Zhao, Ziliang Feng, Li Lu
On the surface, correlation filter and convolution filter are usually used for different purposes.
1 code implementation • 7 Apr 2021 • Shuiwang Li, YuTing Liu, Qijun Zhao, Ziliang Feng
Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and public security.
1 code implementation • 5 Apr 2021 • Wenbo Zhang, Yao Jiang, Keren Fu, Qijun Zhao
Depth information has been proved beneficial in RGB-D salient object detection (SOD).
Ranked #2 on RGB-D Salient Object Detection on DES
1 code implementation • 23 Mar 2021 • Ruowei Wang, Chenguo Lin, Qijun Zhao, Feiyu Zhu
Digital watermarking has been widely used to protect the copyright and integrity of multimedia data.
1 code implementation • 25 Jan 2021 • Qian Chen, Ze Liu, Yi Zhang, Keren Fu, Qijun Zhao, Hongwei Du
The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams.
1 code implementation • 10 Oct 2020 • Keren Fu, Yao Jiang, Ge-Peng Ji, Tao Zhou, Qijun Zhao, Deng-Ping Fan
Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, from which insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models, are achieved.
1 code implementation • 16 Sep 2020 • Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
2 code implementations • 26 Aug 2020 • Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao, Jianbing Shen, Ce Zhu
Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.
Ranked #3 on RGB-D Salient Object Detection on STERE
no code implementations • 12 Aug 2020 • Yuting Liu, Zheng Wang, Miaojing Shi, Shin'ichi Satoh, Qijun Zhao, Hongyu Yang
We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.
1 code implementation • CVPR 2020 • Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao
This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection.
Ranked #6 on RGB-D Salient Object Detection on NLPR
no code implementations • 24 Dec 2019 • WeiRan Yan, MaoLin Tang, Qijun Zhao, Peng Chen, Dunwu Qi, Rong Hou, Zhihe Zhang
Giant pandas, stereotyped as silent animals, make significantly more vocal sounds during breeding season, suggesting that sounds are essential for coordinating their reproduction and expression of mating preference.
no code implementations • 9 Aug 2019 • Qi He, Qijun Zhao, Ning Liu, Peng Chen, Zhihe Zhang, Rong Hou
We are going to release our database and model in the public domain to promote the research on automatic animal identification and particularly on the technique for protecting red pandas.
no code implementations • CVPR 2019 • Yuting Liu, Miaojing Shi, Qijun Zhao, Xiaofang Wang
In the end, we propose a curriculum learning strategy to train the network from images of relatively accurate and easy pseudo ground truth first.
no code implementations • 1 May 2018 • Ziqing Feng, Qijun Zhao
The PEN depth image is finally passed to $Net_{F}$, which extracts a robust feature representation via another DCNN for face recognition.
no code implementations • CVPR 2018 • Feng Liu, Ronghang Zhu, Dan Zeng, Qijun Zhao, Xiaoming Liu
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously.
no code implementations • 14 Mar 2018 • Zhen-Hua Feng, Patrik Huber, Josef Kittler, Peter JB Hancock, Xiao-Jun Wu, Qijun Zhao, Paul Koppen, Matthias Rätsch
To this end, we organise a competition that provides a new benchmark dataset that contains 2000 2D facial images of 135 subjects as well as their 3D ground truth face scans.
no code implementations • 9 Aug 2017 • Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng
Extensive experiments show that the proposed method can achieve the state-of-the-art accuracy in both face alignment and 3D face reconstruction, and benefit face recognition owing to its reconstructed PEN 3D face.
no code implementations • 9 Feb 2017 • Zongping Deng, Ke Li, Qijun Zhao, Yi Zhang, Hu Chen
In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data.
no code implementations • Conference paper 2016 • Li Shao, Ronghang Zhu, Qijun Zhao
Glasses detection plays an important role in face recognition and soft biometrices for person identification.
no code implementations • 21 Sep 2015 • Feng Liu, Dan Zeng, Jing Li, Qijun Zhao
Cascaded regression has been recently applied to reconstructing 3D faces from single 2D images directly in shape space, and achieved state-of-the-art performance.