Ionut Cosmin Duta :: Department of Information Engineering and Computer Science :: University of Trento

Research

My major research interests are in computer vision, deep/machine learning, image and video content processing and analysis, multimedia.

2017

"Spatio-Temporal Vector of Locally Max Pooled Features for Action Recognition in Videos" - I. C. Duta, B. Ionescu, K. Aizawa, and N. Sebe. In Computer Vision and Pattern Recognition (CVPR), 2017. [pdf] [code] [doi]
"Efficient Human Action Recognition using Histograms of Motion Gradients and VLAD with Descriptor Shape Information" - I. C. Duta, J. R. R. Uijlings, K. Aizawa, A. Hauptmann, B. Ionescu and N. Sebe. In Journal of Multimedia Tools and Applications (MTAP), 2017. [pdf] [code] [doi]
"Simple, Efficient and Effective Encodings of Local Deep Features for Video Action Recognition" - I. C. Duta, B. Ionescu, K. Aizawa, and N. Sebe. In International Conference on Multimedia Retrieval (ICMR), 2017 (accepted as oral presentation). [pdf] [doi]
"Spatio-temporal VLAD Encoding for Human Action Recognition in Videos" - I. C. Duta, B. Ionescu, K. Aizawa, and N. Sebe. In International Conference on Multimedia Modeling (MMM), Best paper candidate, 2017 (accepted as oral presentation). [pdf] [code] [doi]

2016

"Boosting VLAD with Double Assignment using Deep Features for Action Recognition in Videos" - I. C. Duta, T. A. Nguyen, K. Aizawa, B. Ionescu and N. Sebe. In International Conference on Pattern Recognition (ICPR), 2016 (accepted as oral presentation). [pdf] [doi]
"Histograms of Motion Gradients for Real-time Video Classification" - I. C. Duta, J. R. R. Uijlings, T. A. Nguyen, K. Aizawa, A. Hauptmann, B. Ionescu and N. Sebe. In International Workshop on Content-based Multimedia Indexing (CBMI), 2016 (accepted as oral presentation). [pdf] [code] [doi]
"Evaluation of Deep Features with PCA for Fine-grained Image Retrieval" - T. A. Nguyen, I. C. Duta, T. Yamasaki, K. Aizawa. In the 19th Meeting on Image Recognition and Understanding (MIRU), 2016. [pdf] [doi]

2015

"A Modified Vector of Locally Aggregated Descriptors Approach for Fast Video Classification" - I. Mironica, I. C. Duta, B. Ionescu and N. Sebe. In Multimedia Tools and Applications (MTAP), 2015. [pdf] [doi]
"Beyond Bag-of-Words: Fast Video Classification with Fisher Kernel Vector of Locally Aggregated Descriptors" - I. Mironica, I. C. Duta, B. Ionescu and N. Sebe. In International Conference on Multimedia and Expo (ICME), 2015. [pdf] [doi]

2014

"Video classification with Densely extracted HOG/HOF/MBH features: an evaluation of the accuracy/computational efficiency trade-off" - J. R. R. Uijlings, I. C. Duta, E. Sangineto and N. Sebe. In International Journal of Multimedia Information Retrieval (IJMIR), 2014. [pdf] [code] [doi]
“Realtime Video Classification using Dense HOF/HOG” - J. R. R. Uijlings, I. C. Duta, N. Rostamzadeh and N. Sebe, ACM ICMR, Glasgow (UK), 2014 (accepted as oral presentation). [pdf] [code] [doi]