no code implementations • CVPR 2023 • Xiaolin Song, Binghui Chen, Pengyu Li, Jun-Yan He, Biao Wang, Yifeng Geng, Xuansong Xie, Honggang Zhang
End-to-end pedestrian detection focuses on training a pedestrian detection model via discarding the Non-Maximum Suppression (NMS) post-processing.
no code implementations • 7 Dec 2022 • Kaicheng Li, Hongyu Yang, Binghui Chen, Pengyu Li, Biao Wang, Di Huang
Along with the widespread use of face recognition systems, their vulnerability has become highlighted.
no code implementations • 6 Dec 2022 • Siyuan Zhou, Chunru Zhan, Biao Wang, Tiezheng Ge, Yuning Jiang, Li Niu
Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are relevant to the target image.
no code implementations • 4 Oct 2022 • Zixiao Wang, Yuluo Guo, Jin Zhao, Yu Zhang, Hui Yu, Xiaofei Liao, Hai Jin, Biao Wang, Ting Yu
In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model.
Ranked #1 on Link Property Prediction on ogbl-ddi
no code implementations • 29 Sep 2022 • Borun Xu, Biao Wang, Jinhong Deng, Jiale Tao, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan
Motion transfer aims to transfer the motion of a driving video to a source image.
1 code implementation • 28 Sep 2022 • Jiale Tao, Biao Wang, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan
Image animation aims to animate a source image by using motion learned from a driving video.
no code implementations • 27 Sep 2022 • Hui Lv, Zhen Cui, Biao Wang, Jian Yang
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly.
1 code implementation • 10 Aug 2022 • Wangmeng Xiang, Chao Li, Yuxuan Zhou, Biao Wang, Lei Zhang
More specifically, we employ a large-scale language model as the knowledge engine to provide text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning.
Ranked #3 on Skeleton Based Action Recognition on N-UCLA
1 code implementation • 27 Jul 2022 • Wangmeng Xiang, Chao Li, Biao Wang, Xihan Wei, Xian-Sheng Hua, Lei Zhang
For 3D video-based tasks such as action recognition, however, directly applying spatiotemporal transformers on video data will bring heavy computation and memory burdens due to the largely increased number of patches and the quadratic complexity of self-attention computation.
Ranked #5 on Action Recognition on Something-Something V1
no code implementations • 14 Jul 2022 • Rong Zhao, Jun-e Feng, Biao Wang
According to the initial state set from which both systems start, two kinds of approximate synchronization problem, local approximate synchronization and global approximate synchronization, are proposed for the first time.
1 code implementation • 15 Jun 2022 • Yuxuan Zhou, Wangmeng Xiang, Chao Li, Biao Wang, Xihan Wei, Lei Zhang, Margret Keuper, Xiansheng Hua
Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account.
Ranked #142 on Image Classification on ImageNet
1 code implementation • 25 Apr 2022 • Junshan Hu, Chaoxu Guo, Liansheng Zhuang, Biao Wang, Tiezheng Ge, Yuning Jiang, Houqiang Li
For the region perspective, we introduce Region Evaluate Module (REM) which uses a new and efficient sampling method for proposal feature representation containing more contextual information compared with point feature to refine category score and proposal boundary.
1 code implementation • CVPR 2022 • Binghui Chen, Pengyu Li, Xiang Chen, Biao Wang, Lei Zhang, Xian-Sheng Hua
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.
1 code implementation • CVPR 2022 • Jiale Tao, Biao Wang, Borun Xu, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
no code implementations • CVPR 2022 • Fanyue Wei, Biao Wang, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
no code implementations • 8 Mar 2022 • Xi Weng, Yan Yan, Genshun Dong, Chang Shu, Biao Wang, Hanzi Wang, Ji Zhang
This shows that DMA-Net provides a good tradeoff between segmentation quality and speed for semantic segmentation in street scenes.
1 code implementation • 19 Dec 2021 • Borun Xu, Biao Wang, Jiale Tao, Tiezheng Ge, Yuning Jiang, Wen Li, Lixin Duan
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
1 code implementation • ICCV 2021 • Binghui Chen, Zhaoyi Yan, Ke Li, Pengyu Li, Biao Wang, WangMeng Zuo, Lei Zhang
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
no code implementations • CVPR 2021 • Qize Yang, Xihan Wei, Biao Wang, Xian-Sheng Hua, Lei Zhang
Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.
1 code implementation • CVPR 2021 • Pengyu Li, Biao Wang, Lei Zhang
This is because the classification paradigm needs to train a fully connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities.
no code implementations • CVPR 2021 • Wenyu Li, Tianchu Guo, Pengyu Li, Binghui Chen, Biao Wang, WangMeng Zuo, Lei Zhang
In this paper, we propose a novel face recognition method, named VirFace, to effectively apply the unlabeled shallow data for face recognition.
no code implementations • 29 Apr 2021 • Biao Wang, Jun-e Feng, Daizhan Cheng
A new analytical framework consisting of two phenomena: single sample and multiple samples, is proposed to deal with the identification problem of Boolean control networks (BCNs) systematically and comprehensively.
no code implementations • 24 Jul 2020 • Baofu Zhang, Shanchao Ma, Sihua Lu, Qiurun He, Jing Guo, Zhongxing Jiao, Biao Wang
We theoretically and experimentally demonstrate a novel mode-locked ytterbium-doped fiber laser with a saturable absorber based on nonlinear Kerr beam cleanup effect.
no code implementations • 30 Apr 2020 • Fei Tang, Wanling Gao, Jianfeng Zhan, Chuanxin Lan, Xu Wen, Lei Wang, Chunjie Luo, Jiahui Dai, Zheng Cao, Xingwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
no code implementations • 17 Feb 2020 • Wanling Gao, Fei Tang, Jianfeng Zhan, Chuanxin Lan, Chunjie Luo, Lei Wang, Jiahui Dai, Zheng Cao, Xiongwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Xu Wen, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Gang Lu, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
no code implementations • 23 Jan 2020 • Canyu Le, Zhonggui Chen, Xihan Wei, Biao Wang, Lei Zhang
The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data.
no code implementations • 8 Dec 2019 • Xin Hou, Biao Wang, Wanqi Hu, Lei Yin, Haishan Wu
Renewable energy such as solar power is critical to fight the ever more serious climate change.
no code implementations • 27 Aug 2019 • Canyu Le, Xihan Wei, Biao Wang, Lei Zhang, Zhonggui Chen
To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data stream over time without forgetting the previous knowledge.
no code implementations • 13 Aug 2019 • Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng, Jiahui Dai, Zheng Cao, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Tong Wu, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.