no code implementations • 11 Jul 2023 • Sikai Bai, Shuaicheng Li, Weiming Zhuang, Jie Zhang, Song Guo, Kunlin Yang, Jun Hou, Shuai Zhang, Junyu Gao, Shuai Yi
Theoretically, we show the convergence guarantee of the dual regulators.
no code implementations • 18 Apr 2023 • Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi, Ziwei Liu
Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details.
1 code implementation • Conference 2022 • Wei Lin, Kunlin Yang, Xinzhu Ma, Junyu Gao, Lingbo Liu, Shinan Liu, Jun Hou, Shuai Yi, Antoni B. Chan
Here we propose a scale-sensitive generalized loss to tackle this problem.
Ranked #5 on Object Counting on FSC147
no code implementations • 15 Aug 2022 • Xinzhu Ma, Yuan Meng, Yinmin Zhang, Lei Bai, Jun Hou, Shuai Yi, Wanli Ouyang
We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.
1 code implementation • 5 Jul 2022 • Weichen Fan, Jinghuan Chen, Jiabin Ma, Jun Hou, Shuai Yi
We evaluate our model in several I2I translation benchmarks, and the results show that the proposed model has advantages over previous methods in both strongly constrained and normally constrained tasks.
Ranked #1 on Style Transfer on WikiArt
no code implementations • 21 Jun 2022 • Shuaicheng Li, Feng Zhang, Kunlin Yang, Lingbo Liu, Shinan Liu, Jun Hou, Shuai Yi
Our proposed method mainly leverages the intra-modality encoding and cross-modality co-occurrence encoding for fully representation modeling.
1 code implementation • 13 Jun 2022 • Zengyu Qiu, Xinzhu Ma, Kunlin Yang, Chunya Liu, Jun Hou, Shuai Yi, Wanli Ouyang
Besides, our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers.
no code implementations • 9 Apr 2022 • Weiming Zhuang, Xin Gan, Yonggang Wen, Xuesen Zhang, Shuai Zhang, Shuai Yi
To address this problem, we propose federated unsupervised domain adaptation for face recognition, FedFR.
no code implementations • 11 Jan 2022 • Zipeng Qin, Jianbo Liu, Xiaolin Zhang, Maoqing Tian, Aojun Zhou, Shuai Yi, Hongsheng Li
The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level classification method.
1 code implementation • ICCV 2021 • Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li
To this end, we propose Multi-level Attention Encoder-Decoder Network (MAED), including a Spatial-Temporal Encoder (STE) and a Kinematic Topology Decoder (KTD) to model multi-level attentions in a unified framework.
Ranked #39 on 3D Human Pose Estimation on MPI-INF-3DHP
1 code implementation • ICCV 2021 • Shuaicheng Li, Qianggang Cao, Lingbo Liu, Kunlin Yang, Shinan Liu, Jun Hou, Shuai Yi
It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-temporal transformer.
1 code implementation • ICCV 2021 • Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, Shuai Yi
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem.
1 code implementation • ICCV 2021 • Weiming Zhuang, Xin Gan, Yonggang Wen, Shuai Zhang, Shuai Yi
In this framework, each party trains models from unlabeled data independently using contrastive learning with an online network and a target network.
1 code implementation • 29 Jul 2021 • Yinmin Zhang, Xinzhu Ma, Shuai Yi, Jun Hou, Zhihui Wang, Wanli Ouyang, Dan Xu
In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection.
Ranked #10 on Monocular 3D Object Detection on KITTI Cars Moderate
1 code implementation • ICCV 2021 • Zhipeng Luo, Zhongang Cai, Changqing Zhou, Gongjie Zhang, Haiyu Zhao, Shuai Yi, Shijian Lu, Hongsheng Li, Shanghang Zhang, Ziwei Liu
In addition, existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world.
no code implementations • 16 Jun 2021 • Zhipeng Luo, Xiaobing Zhang, Shijian Lu, Shuai Yi
Compared with single-source unsupervised domain adaptation (SUDA), domain shift in MUDA exists not only between the source and target domains but also among multiple source domains.
Classification Multi-Source Unsupervised Domain Adaptation +2
no code implementations • 17 May 2021 • Weiming Zhuang, Xin Gan, Yonggang Wen, Xuesen Zhang, Shuai Zhang, Shuai Yi
To this end, FedFR forms an end-to-end training pipeline: (1) pre-train in the source domain; (2) predict pseudo labels by clustering in the target domain; (3) conduct domain-constrained federated learning across two domains.
no code implementations • CVPR 2021 • Junzhe Zhang, Xinyi Chen, Zhongang Cai, Liang Pan, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Bo Dai, Chen Change Loy
In contrast to previous fully supervised approaches, in this paper we present ShapeInversion, which introduces Generative Adversarial Network (GAN) inversion to shape completion for the first time.
1 code implementation • CVPR 2021 • Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi, Ziwei Liu
In particular, we propose a dual-path architecture to enable principled probabilistic modeling across partial and complete clouds.
Ranked #2 on Point Cloud Completion on Completion3D
1 code implementation • CVPR 2021 • Xinzhu Ma, Yinmin Zhang, Dan Xu, Dongzhan Zhou, Shuai Yi, Haojie Li, Wanli Ouyang
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging.
Ranked #8 on 3D Object Detection on Rope3D
no code implementations • 6 Jan 2021 • Jiawei Ren, Xiao Ma, Chen Xu, Haiyu Zhao, Shuai Yi
Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems.
no code implementations • 23 Dec 2020 • Daisheng Jin, Xiao Ma, Chongzhi Zhang, Yizhuo Zhou, Jiashu Tao, Mingyuan Zhang, Haiyu Zhao, Shuai Yi, Zhoujun Li, Xianglong Liu, Hongsheng Li
We observe that during training, the relationship proposal distribution is highly imbalanced: most of the negative relationship proposals are easy to identify, e. g., the inaccurate object detection, which leads to the under-fitting of low-frequency difficult proposals.
no code implementations • 15 Dec 2020 • Jiawei Ren, Cunjun Yu, Zhongang Cai, Mingyuan Zhang, Chongsong Chen, Haiyu Zhao, Shuai Yi, Hongsheng Li
Panoptic segmentation aims at generating pixel-wise class and instance predictions for each pixel in the input image, which is a challenging task and far more complicated than naively fusing the semantic and instance segmentation results.
Ranked #11 on Panoptic Segmentation on COCO test-dev
1 code implementation • ICLR 2021 • Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, Hao Su
To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for efficient deep learning on point clouds.
2 code implementations • 26 Aug 2020 • Weiming Zhuang, Yonggang Wen, Xuesen Zhang, Xin Gan, Daiying Yin, Dongzhan Zhou, Shuai Zhang, Shuai Yi
Then we propose two optimization methods: (1) To address the unbalanced weight problem, we propose a new method to dynamically change the weights according to the scale of model changes in clients in each training round; (2) To facilitate convergence, we adopt knowledge distillation to refine the server model with knowledge generated from client models on a public dataset.
1 code implementation • 14 Aug 2020 • Xianghui Yang, Bairun Wang, Kaige Chen, Xinchi Zhou, Shuai Yi, Wanli Ouyang, Luping Zhou
(2) The object categories at the training and inference stages have no overlap, leaving the inter-class gap.
no code implementations • ECCV 2020 • Zhongang Cai, Junzhe Zhang, Daxuan Ren, Cunjun Yu, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Chen Change Loy
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views.
1 code implementation • NeurIPS 2020 • Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, Hongsheng Li
In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.
Ranked #7 on Long-tail Learning on CIFAR-10-LT (ρ=10)
1 code implementation • ECCV 2020 • Cunjun Yu, Xiao Ma, Jiawei Ren, Haiyu Zhao, Shuai Yi
In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.
no code implementations • ECCV 2020 • Dongzhan Zhou, Xinchi Zhou, Hongwen Zhang, Shuai Yi, Wanli Ouyang
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection.
1 code implementation • 25 Feb 2020 • Yushi Lan, Yu-An Liu, Maoqing Tian, Xinchi Zhou, Xuesen Zhang, Shuai Yi, Hongsheng Li
Meanwhile, we introduce "Semantic Fusion Branch" to filter out irrelevant noises by selectively fusing semantic region information sequentially.
no code implementations • 4 Feb 2020 • Wenyang Hu, Xiaocong Cai, Jun Hou, Shuai Yi, Zhiping Lin
Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attentionbased methods.
no code implementations • CVPR 2020 • Dongzhan Zhou, Xinchi Zhou, Wenwei Zhang, Chen Change Loy, Shuai Yi, Xuesen Zhang, Wanli Ouyang
While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming.
6 code implementations • NeurIPS 2018 • Shuyang Sun, Jiangmiao Pang, Jianping Shi, Shuai Yi, Wanli Ouyang
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e. g., image-level, region-level, and pixel-level are diverging.
12 code implementations • 4 Dec 2018 • Zhuoran Shen, Mingyuan Zhang, Haiyu Zhao, Shuai Yi, Hongsheng Li
Dot-product attention has wide applications in computer vision and natural language processing.
Ranked #2 on Extractive Text Summarization on GovReport
2 code implementations • NeurIPS 2018 • Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li
Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.
Ranked #3 on Person Re-Identification on CUHK03
no code implementations • 27 Aug 2018 • Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li
Dense depth cues are important and have wide applications in various computer vision tasks.
Ranked #10 on Depth Completion on KITTI Depth Completion
1 code implementation • ECCV 2018 • Xiaoyang Guo, Hongsheng Li, Shuai Yi, Jimmy Ren, Xiaogang Wang
Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving.
1 code implementation • CVPR 2018 • Yantao Shen, Hongsheng Li, Tong Xiao, Shuai Yi, Dapeng Chen, Xiaogang Wang
Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images.
1 code implementation • CVPR 2018 • Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang
Person re-identification aims to robustly measure similarities between person images.
no code implementations • ECCV 2018 • Yantao Shen, Hongsheng Li, Shuai Yi, Dapeng Chen, Xiaogang Wang
However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery images independently while ignores the relationship information between different probe-gallery pairs.
Ranked #2 on Person Re-Identification on CUHK03
no code implementations • CVPR 2018 • Dapeng Chen, Hongsheng Li, Tong Xiao, Shuai Yi, Xiaogang Wang
The attention weights are obtained based on a query feature, which is learned from the whole probe snippet by an LSTM network, making the resulting embeddings less affected by noisy frames.
Ranked #4 on Person Re-Identification on PRID2011
no code implementations • CVPR 2018 • Maoqing Tian, Shuai Yi, Hongsheng Li, Shihua Li, Xuesen Zhang, Jianping Shi, Junjie Yan, Xiaogang Wang
State-of-the-art methods mainly utilize deep learning based approaches for learning visual features for describing person appearances.
no code implementations • ICCV 2017 • Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang
In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed.
2 code implementations • ICCV 2017 • Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems.
Ranked #2 on Pedestrian Attribute Recognition on RAP
no code implementations • ICCV 2017 • Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang
Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation.
1 code implementation • 11 Jul 2017 • Luming Tang, Boyang Deng, Haiyu Zhao, Shuai Yi
The proposed framework contains hierarchical deep architecture, including the frame-level sequence modeling part and the video-level classification part.
1 code implementation • CVPR 2017 • Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, Xiaoou Tang
Person re-identification (ReID) is an important task in video surveillance and has various applications.
no code implementations • ICCV 2015 • Shuai Yi, Hongsheng Li, Xiaogang Wang
In this paper, we target on the problem of estimating the statistic of pedestrian travel time within a period from an entrance to a destination in a crowded scene.
no code implementations • CVPR 2015 • Shuai Yi, Hongsheng Li, Xiaogang Wang
Pedestrian behavior modeling and analysis is important for crowd scene understanding and has various applications in video surveillance.
no code implementations • CVPR 2014 • Shuai Yi, Xiaogang Wang, Cewu Lu, Jiaya Jia
We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance.