中科院计算所视觉信息处理与学习组
中科院计算所视觉信息处理与学习组
宋新航

职 称:博士后

研究方向:场景识别与理解

宋新航,男,2017年获中国科学院计算技术研究所博士学位。2017年中国科学院“院长特别奖”,2017年获“博士后创新人才支持计划”资助。主要研究方向包括面向计算机视觉的机器学习与模式识别算法和模型。曾在CVPRAAAIIJCAIACM MMTrans. on IPPattern Recognition等国际知名期刊和会议上以第一作者发表作论文多篇。

学术服务
刊物服务
  • IEEE Transactions on Big Data
  • IEEE Transactions on Multimedia
会议服务
  • AAAI, IJCAI, ACM MM, PCM, ChinaMM, BigMM
经历
教育经历
  • 2011.09-2017.06 中国科学院计算技术研究所 博士
  • 2007.9-2011.6 北京交通大学计算机与信息技术学院 学士
科研项目

1.   面向多模态交互的视觉场景识别与理解技术研究

项目类型:博士后创新人才支持计划
项目时间:2017.06-2019.06
项目负责人:宋新航(全国共300名,计算机科学与技术方向8名)
著论

论文

Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen, "Learning Effective RGB-D Representations for Scene Recognition," IEEE Transactions on Image Processing (TIP), doi:10.1109/TIP.2018.2872629(Accepted)

Xinhang Song, chengpeng chen, Shuqiang Jiang. RGB-D Scene Recognition with Object-to-Object RelationThe 25th ACM Multimedia Conference (ACM MM) 2017 (long paper), CCF A

Xinhang Song, Shuqiang Jiang, Luis Herranz. Combining Models from Multiple Sources for RGB-D Scene RecognitionThe 26th International Joint Conference on Artificial Intelligence (IJCAI) 2017, CCF A

Xinhang Song, Luis Herranz, Shuqiang Jiang. “Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs” Thirty-First AAAI Conference on Artificial Intelligence (AAAI)2017, CCF A

Xinhang Song, Shuqiang Jiang, Luis Herranz. “Joint Multi-feature Spatial Context for Scene Recognition in the Semantic Manifold.” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015: 1312-1320, CCF A

Xinhang Song, Shuqiang Jiang, Luis Herranz. “Multi-scale multi-feature context modeling for scene recognition in the semantic manifold.” IEEE Transactions on Image Processing (TIP), 2017, CCF A

Xinhang Song, Shuqiang Jiang, Luis Herranz, Yan Kong, Kai Zheng, “Category co-occurrence modeling for large scale scene recognition”, Pattern Recognition (PR) 59: 98-111 (2016) , CCF B

Xinhang Song, Shuqiang Jiang, Ruihan Xu, Luis Herranz, ” Semantic Features for Food Image Recognition with Geo-Constraints.” The IEEE International Conference on Data Mining series (ICDM), Workshops 2014: 1020-1025

Xinhang Song, Shuqiang Jiang, Shuhui Wang, Liang Li, Qingming Huang. “Polysemious visual representation based on feature aggregation for large scale image applications.” Multimedia Tools and Applications (MTAP), 2015


Xinhang Song, Shuqiang Jiang, Shuhui Wang, Jinhui Tang, Qingming Huang. “Cross Concept Local Fisher Discriminant Analysis for Image Classification.” The International Conference on Multimedia Modeling (MMM) 2013: 407-416

Xiaodan Zhang, Xinhang Song, Xiong Lv, Shuqiang Jiang, Jianbin Jiao, “Rich Image Description Based on Regions.” ACM Multimedia Conference (ACM MM) 2015, Short paper.

Xiangyang Li, Shuqiang Jiang, Xinhang Song, Luis Herranz, Zhiping Shi. “Multipath Convolutional-Recursive Neural Networks for Object Recognition.” International Conference on Intelligent Information Processing (IIP) 2014: 269-277


Ruihan Xu, Shuqiang Jiang, Xinhang Song, Shuang Wang, Yi Xie, Fang Wang, Xiong Lv. “MIAR ICT Participation at Robot Vision 2013.” ImageCLEF (Working Notes) 2013

Ruihan Xu, Luis Herranz, Shuqiang Jiang, Shuang Wang, Xinhang Song, Ramesh Jain, “Geolocalized Modeling for Dish Recognition”, IEEE Transactions on Multimedia (TMM) 2015.

Shuqiang Jiang, Xinhang Song, Qingming Huang. “Relative image similarity learning with contextual information for Internet cross-media retrieval.” Multimedia Systems (MMSJ). 20(6): 645-657 (2014)

视觉信息处理和学习组
  • 单位地址:北京海淀区中关村科学院南路6号
  • 邮编:100190
  • 联系电话:010-62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • 深度学习大讲堂

版权所有 @ 中科院计算所视觉信息处理与学习组 京ICP备05002829号 京公网安备1101080060