- Data Access
CVIE provides image and video access, encoding, transcoding as well as sharding services. It supports real-time registration and unloading of cameras. It has been adapted to various data transportation protocols like GB/T 28181, GA/T 1400, etc.
- Visual Search
Powered by advanced indexing technologies like feature quantization and heterogeneous acceleration, CVIE provides effective and efficient search engines for retrieving objects and complex events from videos. It enables indexing of both structured and semi-structured data like attributes and high dimensional feature vectors.
- Data Computing
CVIE is equipped with self-developed world-leading compute vision algorithms such as object detection, recognition and segmentation. It supports real-time analysis of thousands of online video streams and can accelerate offline video analysis by hundreds of times. Besides, it provides computing engines for heterogeneous data sources, including streaming data, sequence data, graph data, and graphics data.
- Engine of Industry
CVIE energizes various industry scenarios to promote the quality of urban life, including but not limited to public safety, transportation, municipal construction, urban planning, electricity scheduling, etc.
- Flexible, Open and Secure Platforms
As one of the first national open innovation platforms of artificial intelligence, CVIE supports open integration of algorithms, flexible work flow customization, as well as secure model encryption and dynamic authorization.
- Advanced and Abundant Self-developed Algorithms
CVIE is equipped with abundant and self-developed world-leading compute vision as well as artificial intelligence algorithms.
- Intelligent and Complete Industrial Solution
CVIE provides customized intelligent analyzing services and complete large-scale visual computing solution to solve the pain points of customers across various industries.
- Global and Intuitive Digital City Perception
CVIE can project the real world into a digital world, realizing the whole spatial and temporal perception, whole elements linkage and full cycle iteration of smart cities through global mock negotiation and real-time commanding systems.
As one of the first national open innovation platforms of artificial intelligence, CVIE provides an open and flexible AI development and servicing platform for both academia and industry. It has served many world-famous research institutions, universities and AI companies. It has also been deployed and widely used in more than 60 city brain projects. We sincerely welcome more partners to contact us and explore cooperation in scientific research and industry.
- Smart Transportation
- Public Safety
- Urban Management
- Emergency Management
- Housing and Construction
- In 2019, Ali AI defeated 10 teams including Microsoft and Seoul University and got the first position in the CVPR Visual Dialogue Challenge.
- In 2019, Ali AI won the champion of weakly supervised semantic segmentation task in the first Learning from Imperfect Data competition of CVPR.
- In 2018, the “Large-scale visual parallel heterogeneous computing platform and key technologies for city brain” won the first prize of Zhejiang Science and Technology Progress Award.
- On August 27, 2018, the 11th meeting of the 7th People’s Congress Standing Committee of Quzhou City awarded Xianshen Hua the “Celebrity Honorary Citizen”.
- In 2018, the “Alibaba Cloud City Visual Intelligence Engine Software” won the first place in the pedestrian detection track of KITTI.
- In 2018, the “Alibaba Cloud City Visual Intelligence Engine Software” breaks the world record of person reidentification algorithms, achieving the top-1 accuracy of 97.3%.
- In 2017, the “Alibaba Cloud City Visual Intelligence Engine Software” won the first place in the vehicle detection track of KITTI.
- On November 15, 2017, Alibaba “City Visual Intelligence Engine” was selected as one of the first national artificial intelligence open innovation platforms.
- Hongwei Yong, Jianqiang Huang, Wangmeng Xiang, Xiansheng Hua, Lei Zhang. Panoramic Background Image Generation for PTZ Cameras. IEEE Transactions on Image Processing, 2019(99):1-1.
- Yiru Zhao, Xu Shen, Zhongming Jin, Hongtao Lu, Xiansheng Hua. Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification. CVPR 2019.
- Jiwei Yang, Xu Shen, Jun Xing, Xinmei Tian, Houqiang Li, Bing Deng, Jianqiang Huang, Xiansheng Hua. Quantization Networks. CVPR 2019.
- Jiaxin Shi, Hanwang Zhang, Juanzi Li. Explainable and Explicit Visual Reasoning over Scene Graphs. CVPR, 2019.
- Yulei Niu, Hanwang Zhang, et al. Recursive Visual Attention in Visual Dialog. CVPR, 2019.
- Xu Yang, Kaihua Tang, Hanwang Zhang, Jianfei Cai. Auto-Encoding Scene Graphs for Image Captioning. CVPR, 2019.
- Yunke Zhang, Lixue Gong, Weiwei Xu, Lubin Fan, Peiran Ren. A Late Fusion CNN for Digital Matting. CVPR, 2019.
- Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu，Jun Wang. Attention-aware Multi-stroke Style Transfer. CVPR, 2019.
- Hui Zeng, Lida Li, Zisheng Cao, Lei Zhang. Reliable and Efficient Image Cropping: A Grid Anchor based Approachs. CVPR, 2019.
- Xixi Jia, Sanyang Liu, Xiagnchu Feng, Lei Zhang. FOCNet: A Fractional Optimal Control Network for Image Denoising. CVPR, 2019.
- Kai Zhang, Wangmeng Zuo, Lei Zhang. Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels. CVPR, 2019.
- Shi Guo, Wangmeng Zuo, Zifei Yan, Kai Zhang, Lei Zhang. Toward Convolutional Blind Denoising of Real-world Noisy Photographs. CVPR, 2019.
- Tao Dai, Jianrui Cai, Yongbing Zhang, Shutao Xia, Lei Zhang. Second-order Attention Network for Single Image Super-resolution. CVPR, 2019.
- Wenqing Chu, Yao Liu, Chen Shen, Deng Cai, and Xian-Sheng Hua. "Multi-task vehicle detection with region-of-interest voting." IEEE Transactions on Image Processing (TIP). 27, no. 1 (2018): 432-441.
- YunFu Liu, DaWei Jaw, ShihChia Huang, and JenqNeng Hwang. "DesnowNet: Context-Aware Deep Network for Snow Removal." IEEE Transaction on Image Processing (TIP). 27(2018): 3064-3073.
- Chen Shen, Guo-Jun Qi, Rongxin Jiang, Zhongming Jin, Hongwei Yong, Yaowu Chen, and Xian-Sheng Hua. Sharp Attention Network via Adaptive Sampling for Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT). 2018. Early Access.
- Xu Shen, Xinmei Tian, Jun Xing, Yong Rui, Dacheng Tao. Sequence-to-Sequence Learning via Shared Latent Representation. AAAI, 2018.
- Kai Zhang, Wangmeng Zuo, Lei Zhang. Learning a single convolutional super-resolution network for multiple degradations. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 6, 2018.
- Guotian Xie, Jingdong Wang, Ting Zhang, Jianhuang Lai, Richang Hong, Guo-Jun Qi. Interleaved Structured Sparse Convolutional Neural Networks. CVPR, 2018: 8847-8856.
- Guojun Qi, Liheng Zhang, Hao Hu, Marzieh Edraki, Jingdong Wang, Xiansheng Hua. Global versus localized generative adversarial nets. CVPR, 2018.
- Sijia Cai, Wangmeng Zuo, Davis S. Larry, Lei Zhang. Weakly-supervised Video Summarization using Variational Inference and Web Prior. European Conference on Computer Vision (ECCV). 2018:184-2
- Yare Zhao, Zhongming Jin, Guojun Qi, Hongtao Lu, Xiansheng Hua. An Adversarial Approach to Hard Triplet Generation. ECCV, 2018.
- Yiru Zhao, Zhongming Jin, Guojun Qi, Hongtao Lu, Xiansheng Hua. An Adversarial Approach to Hard Triplet Generation. 2018 European Conference on Computer Vision (ECCV). 2018: 501-517.
- Zhihang Fu, Zhongming Jin, Guo-Jun Qi, Chen Shen, Rongxin Jiang, Yaowu Chen, Xian-Sheng Hua. Previewer for Multi-Scale Object Detector. 2018 ACM Multimedia Conference. 2018: 265-273.
- Yang J, Shen X, Tian X, et al. Local Convolutional Neural Networks for Person Re-Identification. Accepted by ACM MM 2018.
- Zhihang Fu, Chang Zhou, Hongwei Yong, Rongxin Jiang, Xiang Tian, Yaowu Chen, Xian-Sheng Hua. Foreground Gated Network for Surveillance Object Detection. 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). 2018: 1-7.