Xinhang Song

According to our database1, Xinhang Song authored at least 25 papers between 2013 and 2020.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.



In proceedings 
PhD thesis 




Image Representations With Spatial Object-to-Object Relations for RGB-D Scene Recognition.
IEEE Trans. Image Processing, 2020

Deep Patch Representations with Shared Codebook for Scene Classification.
TOMM, 2019

Learning Effective RGB-D Representations for Scene Recognition.
IEEE Trans. Image Processing, 2019

Scene Recognition with Prototype-agnostic Scene Layout.
CoRR, 2019

Aberrance-aware Gradient-sensitive Attentions for Scene Recognition with RGB-D Videos.
Proceedings of the 27th ACM International Conference on Multimedia, 2019

MUCH: Mutual Coupling Enhancement of Scene Recognition and Dense Captioning.
Proceedings of the 27th ACM International Conference on Multimedia, 2019

A Real-Time Scene Recognition System Based on RGB-D Video Streams.
Proceedings of the International Conference on Multimodal Interaction, 2019

Focal Loss for Region Proposal Network.
Proceedings of the Pattern Recognition and Computer Vision - First Chinese Conference, 2018

Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold.
IEEE Trans. Image Processing, 2017

RGB-D Scene Recognition with Object-to-Object Relation.
Proceedings of the 2017 ACM on Multimedia Conference, 2017

Combining Models from Multiple Sources for RGB-D Scene Recognition.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Keyword-driven image captioning via Context-dependent Bilateral LSTM.
Proceedings of the 2017 IEEE International Conference on Multimedia and Expo, 2017

Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs.
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

Category co-occurrence modeling for large scale scene recognition.
Pattern Recognition, 2016

Image Captioning with both Object and Scene Information.
Proceedings of the 2016 ACM Conference on Multimedia Conference, 2016

Joint Learning of CNN and LSTM for Image Captioning.
Proceedings of the Working Notes of CLEF 2016, 2016

Geolocalized Modeling for Dish Recognition.
IEEE Trans. Multimedia, 2015

Polysemious visual representation based on feature aggregation for large scale image applications.
Multimedia Tools Appl., 2015

Rich Image Description Based on Regions.
Proceedings of the 23rd Annual ACM Conference on Multimedia Conference, MM '15, Brisbane, Australia, October 26, 2015

Joint multi-feature spatial context for scene recognition in the semantic manifold.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015

Relative image similarity learning with contextual information for Internet cross-media retrieval.
Multimedia Syst., 2014

Multipath Convolutional-Recursive Neural Networks for Object Recognition.
Proceedings of the Intelligent Information Processing VII, 2014

Semantic Features for Food Image Recognition with Geo-Constraints.
Proceedings of the 2014 IEEE International Conference on Data Mining Workshops, 2014

Cross Concept Local Fisher Discriminant Analysis for Image Classification.
Proceedings of the Advances in Multimedia Modeling, 19th International Conference, 2013

MIAR ICT Participation at Robot Vision 2013.
Proceedings of the Working Notes for CLEF 2013 Conference , 2013