Publications

Full list at Google Scholar

Journal papers

  1. Guosheng Hu, Xiaojiang Peng, etc. Frankenstein: Learning Deep Face Representations using Small Data. IEEE Transactions on Image Processing, 2017. [PDF]

  2. Xiaojiang Peng, Limin Wang, Yu Qiao, etc. Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice. Computer Vision and Image Understanding (CVIU), 2016. [PDF, Bibtex, Code]

  3. Xiaojiang Peng, Yu Qiao, etc. Large Margin Dimensionality Reduction for Action Similarity Labeling. IEEE Signal Processing Letter (SPL), 2014. [PDF, Bibtex, Code]

  4. Xiaojiang Peng, Yu Qiao, etc. Motion Boundary Based Sampling and 3D Co-occurrence Descriptors for Action Recognition. Image and Vision Computing (IVC), 2014. [PDF, Bibtex, Code]

Conference papers

  1. Lianzhi Tan, Xiaojiang Peng, Yu Qiao, etc. Group Emotion Recognition with Individual Facial Emotion CNNs and Global Image Based CNNs. International Conference on Multimodal Interaction (ICMI’17), ACM. [PDF, Poster, Code]

  2. Xiaojiang Peng and Cordelia Schmid. Multi-region two-stream R-CNN for action detection. European Conference on Computer Vision (ECCV), 2016. [PDF, Bibtex, Poster, Code]

  3. Xiaojiang Peng and Cordelia Schmid. Encoding Feature Maps of CNNs for Action Recognition. THUMOS Challenge 2015 Workshop, CVPR, 2015. [PDF, Bibtex, Slides]

  4. Xiaojiang Peng, Yu Qiao, etc. Action Recognition with Stacked Fisher Vectors. European Conference on Computer Vision (ECCV), 2014. [PDF, Bibtex, Poster, Code-googledrive, Code-baidu(pwd:5480)]

  5. Xiaojiang Peng, Yu Qiao, etc. Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics. European Conference on Computer Vision (ECCV), 2014. [PDF, Bibtex, Poster]

  6. Xiaojiang Peng, Limin Wang, etc. Action and Gesture Temporal Spotting with Super Vector Representation. ChaLearn Looking at People (LAP) workshop, ECCV, 2014. [PDF, Bibtex]. Winner of both track 1 and track2, and rank 4th for track3.

  7. Zuowei Cai, Limin Wang, Xiaojiang Peng, Yu Qiao. Multi-View Super Vector for Action Recognition. CVPR, 2014. ( oral )

  8. Xiaojiang Peng, Limin Wang, etc. A Joint Evaluation of Dictionary Learning and Feature Encoding for Action Recognition. International Conference on Pattern Recognition (ICPR), 2014.

  9. Xiaojiang Peng, Yu Qiao, etc. Exploring Motion Boundary Based Sampling and Spatial-temporal Context Descriptors for Action Recognition. British Machine Vision Conference (BMVC), 2013.

  10. Xiaojiang Peng, Yu Qiao, etc. Hybrid Super Vector with Improved Dense Trajectories for Action Recognition. THUMOS’13 Action Recognition Challenge Workshop, ICCV, 2013.