您当前的位置:
宋新航
宋新航 副研究员 (Associate Professor)
电子邮箱: xinhang [dot] song@vipl [dot] ict [dot] ac [dot] cn
通讯地址: NO.6 KEXUEYUAN SOUTH ROAD ZHONGGUANCUN
研究方向: 场景识别与理解
个人简介

宋新航,男,2017年获中国科学院计算技术研究所博士学位,现任副研究员,硕士生导师。主要研究方向包括场景图像/视频识别、分割、目标检测与机器人导航等。曾在CVPR,AAAI,IJCAI,ACM MM,Trans. on IP,Pattern Recognition等国际知名期刊和会议上以第一作者发表作论文十余篇。


主要获奖情况:

2019获中国图象图形学学会(CSIG)优博;

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;

CVPR 2021 Embodied AI目标导航竞赛冠军;

ACM MM2016 Yahoo-Flickr语言描述生成冠军;

ImageCLEF 2013机器人视觉竞赛冠军。


研究生招生:通常每年秋季招收1名硕士生,同时也欢迎对场景图像/视频识别、分割、目标检测与机器人导航等方向感兴趣的同学来实习研究。


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


学术服务

刊物服务

Information Fusion

IEEE Transactions on Industrial Informatics

IEEE Transactions on Systems, Man, and Cybernetics: Systems

IEEE Transactions on Big Data

IEEE Transactions on Multimedia

会议服务

CVPR, ICCV, NeuralPS, AAAI, IJCAI, ACM MM, PCM, ChinaMM, BigMM


研究内容

1.   智能体视觉导航

在仿真环境研究基于强化学习的智能体视觉导航算法,通过研究先验知识图编码、元学习、生成式模型等技术,大幅度提升在位置环境的导航准确率。

2.   多粒度场景理解

以多分辨率图像为输入,探索场景图像局部区域与全局关联,研究局部上下文关联建模,局部内容与空间关系结构化表达,局部图题概括与场景信息关联建模等技术,不仅实现了场景识别与理解准确率的有效提升,还实现了未知类别的准确识别。

3.   RGB-D多模态场景识别

以RGB-D图像或视频为输入,通过研究多步式弱监督学习,多源多模态融合,时序空间自适应融合等技术,最终搭建实时RGB-D识别系统,并部署到机器人平台。


著论

论文

代表性论文(完整列表参见 https://dblp.uni-trier.de/pid/125/2281.html):


Sixian Zhang, Xinhang Song, Yubing Bai, Weijie Li, Yakui Chu,  Shuqiang Jiang. Hierarchical Object-to-Zone Graph for Object Navigation. ICCV 2021, CCF A

Weijie Li, Xinhang Song, Yubing Bai, Sixian Zhang, Shuqiang Jiang. ION: Instance-level Object Navigation. In 29th ACM International Conference on Multimedia (MM ’21), CCF A

Xinhang Song, Haitao Zeng, Sixian Zhang, Luis Herranz, Shuqiang Jiang. 2020. Generalized Zero-shot Learning with Multi-source Semantic Embeddings for Scene Recognition. In 28th ACM International Conference on Multimedia (MM ’20), CCF A

Xinhang Song, Shuqiang Jiang, Bohan Wang, Chengpeng Chen, Gongwei Chen. “Image Representations with Spatial Object-to-Object Relations for RGB-D Scene Recognition.” IEEE Transactions on Image Processing (TIP) 2020, CCF A

 Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen, "Learning Effective RGB-D Representations for Scene Recognition," IEEE Transactions on Image Processing (TIP), 2019, CCF A

Xinhang Song, Sixian Zhang, Yuyun Hua and Shuqiang Jiang. “Aberrance-aware gradient-sensitive attentions for scene recognition with RGB-D videos.” (ACM Multimedia 2019), 21-25 October 2019, Nice, France , CCF A

Xinhang Song, Bohan Wang, Gongwei Chen and Shuqiang Jiang. “MUCH: MUtual Coupling enHancement of scene recognition and dense captioning.” (ACM Multimedia 2019), 21-25 October 2019, Nice, France , CCF A

Xinhang Song, chengpeng chen, Shuqiang Jiang. “RGB-D Scene Recognition with Object-to-Object Relation” The 25th ACM Multimedia Conference (ACM MM) 2017, CCF A

Xinhang Song, Shuqiang Jiang, Luis Herranz. “Combining Models from Multiple Sources for RGB-D Scene Recognition” The 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

 Gongwei Chen, Xinhang Song, Haitao Zeng and Shuqiang Jiang. "Scene Recognition with Prototype-agnostic Scene Layout." IEEE Transactions on Image Processing (TIP) 2020, CCF A

unzhong Ji, Cheng Xu, Xiaodan Zhang, Boyue Wang, Xinhang Song: Spatio-Temporal Memory Attention for Image Captioning. IEEE Trans. Image Process. (TIP) 29: 7615-7628 (2020), CCF A

Haitao Zeng, Xinhang Song, Gongwei Chen and Shuqiang Jiang. "Learning Scene Attribute for Scene Recognition". IEEE Transactions on Multimedia (TMM) 2019, CCF B

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