Anjan Dutta

Dr. Anjan Dutta received PhD in Computer Science from the Autonomous University of Barcelona (UAB) in 2014, which was awarded with an Excellent Cum Laude (highest grade) qualification with international mention. He was also a recipient of the Extraordinary PhD Thesis Award for the year 2013-14 by the UAB. Before his PhD, he obtained MS in Computer Vision and Artificial Intelligence also from the UAB, MCA in Computer Applications from the West Bengal University of Technology and a BS in Mathematics (Honors) from the University of Calcutta respectively in the year of 2010, 2009 and 2006. After completing PhD, Dr. Dutta worked as a postdoctoral researcher at a few academic institutes including Télécom ParisTech, France; Indian Statistical Institute, India.

His main research interest focuses on computer vision, pattern recognition, image processing, graph-based pattern recognition, deep learning, graph neural network, deep multi-modal embedding, zero-shot and incremental learning.

More information about his research can be found at his personal webpage.

SELECTED PUBLICATIONS

• Thanh Nam Le, Muhammad Muzzamil Luqman, Anjan Dutta, Pierre Héroux, Christophe Rigaud, Clément Guérin, Pasquale Foggia, Jean-Christophe Burie, Jean-Marc Ogier, Josep Lladós and Sébastien Adam. "SSGCI: Subgraph Spotting in Graph Representations of Comic Images". In PRL, Volume 112, pp. 118-124, 2018. (JCR 2018: IF=2.810).

 

• Sangheeta Roy, Palaiahnakote Shivakumara, Namita Jain, Vijeta Khare, Anjan Dutta, Umapada Pal and Tong Lu. "Rough-Fuzzy based Video Type Categorization for Text Detection and Recognition". In PR, Volume 80, pp. 64-82, 2018 (JCR 2018: IF=5.898).

 

• Pau Riba, Josep Lladós, Alicia Fornés and Anjan Dutta. “Large-scale Graph Indexing using Binary Embeddings of Node Contexts for Information Spotting in Document Image Databases”. In PRL, Volume 87, pp. 203-211, 2017. (JCR 2017: IF=1.952).

 

• Anjan Dutta, Palaiahnakote Shivakumara, Chew Lim Tan and Umapada Pal. “Multi-oriented scene text detection in video based on wavelet and angle projection boundary growing”. In MTA, Vol. 72, No. 1, pp. 515-539, 2014. (JCR 2014: IF=1.346).

 

• Anjan Dutta, Josep Lladós and Umapada Pal. “A symbol spotting approach in graphical documents by hashing serialized graphs”. In PR, Vol. 46, No. 3, pp. 752-768, 2013. (JCR 2013: IF=2.584).

PUBLICATIONS WITHIN THE P-SPHERE PROJECT

• Anjan Dutta*, Pau Riba*, Josep Lladós, Alicia Fornés, “Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition”, arXiv, 2018.

 

• Anjan Dutta and Hichem Sahbi. “Stochastic Graphlet Embedding”. In IEEE TNNLS, 2019. (JCR 2018: IF=11.683).

 

• Anjan Dutta, Josep Lladós, Horst Bunke and Umapada Pal. "Product Graph-based Higher Order Contextual Similarities for Inexact Subgraph Matching". In PR, Volume 76, pp. 596-611, 2018. (JCR 2017: IF=5.898).

For more information see his ResearcherID.

• Pau Riba, Anjan Dutta, Lutz Goldmann, Alicia Fornés, Oriol Ramos and Josep Lladós. "Table Detection in Invoice Documents by Graph Neural Networks". In ICDAR, 2019.

 

• Anjan Dutta and Zeynep Akata. "Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval". In CVPR, 2019.

 

• Sounak Dey*, Pau Riba*, Anjan Dutta, Josep Lladós and Yi-Zhe Song. "Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval". In CVPR, 2019.

 

• Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós and Umapada Pal. "Aligning Salient Objects to Queries: A Multi-modal and Multi-object Image Retrieval Framework". In ACCV, 2018.

 

• Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós and Umapada Pal. "Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch". In ICPR, 2018.

 

• Anjan Dutta, Pau Riba, Josep Lladós and Alicia Fornés. "Pyramidal Stochastic Graphlet Embedding for Document Pattern Classification". In ICDAR, 2017.

 

• Pau Riba, Anjan Dutta, Sounak Dey, Josep Lladós and Alicia Fornés. "Improving Information Retrieval in Multiwriter Scenario by Exploiting the Similarity Graph of Document Terms". In ICDAR, 2017.