Profile

Dr Anjan Dutta

Lecturer in Computer Vision and Machine Learning (E&R)

Email:

Visit personal website »

I have moved as a Senior Lecturer to the University of Surrey in April 2022.

Short Bio

Dr. Anjan Dutta is a Lecturer (Assistant Professor) of Computer Science of Education & Research family at the University of Exeter in United Kingdom. He received a 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. Moreover, he is 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. His main research interests revolve around computer vision and machine learning. Specifically, I work on deep multi-modal embedding, zero-shot learning, graph neural network for various computer vision tasks.

Experience

• 2019 - Now: Lecturer of Computer Vision & Machine Learning at University of Exeter.
• 2017 - 2019: Marie Curie Fellow at Computer Vision Centre.
• 2016 - 2017: Postdoctoral Researcher at Computer Vision Centre.
• 2014 - 2015: Postdoctoral Researcher at Télécom ParisTech.

Education

• PhD: Autonomous University of Barcelona, Spain, 2014.
• MS: Autonomous University of Barcelona, Spain, 2010.
• MCA: Maulana Abul Kalam Azad University of Technology, India, 2009.
• BSc: University of Calcutta, India, 2006.

Awards

• Extraordinary PhD Thesis Award, UAB, Barcelona, 2013 - 2014.

Research Grants and Competitive Fellowships

• (PI) Alan Turing Institute - Dstl "LOREN", Turing/D028/1.0, 2020, £100K.
• (CI) MINECO Retos "SDME" (PI: Dr. Luis Herranz) RTI2018-102285-A-I00, 2019 - 2021, €27.6K.
• Marie Sklodowska-Curie Fellowship within the P-SPHERE project 665919, 2017 - 2019, €171.3K.
• Marie Sklodowska-Curie Fellowship (desisted for P-SPHERE) within the TECNIOSpring PLUS project 712949, 2017 - 2019, €107.9K.
• NVIDIA GPU Grants, 3 TITAN GPUs (one each of X, Xp & V) (approx €6K).
• PhD Fellowship, AGAUR, Govt. of Catalonia, 2011FIB 01022, 2012FIB1 00174 and 2013FIB2 00074, €50K.
• PhD Mobility Fellowship, AGAUR, Govt. of Catalonia, 2011 BE1 00169, €3K.

Other Professional Activities

• Area Chair for Conferences:
  • BMVC 2021 
• Reviewer for Conferences:
  • BMVC 2015, 2016, 2021; CVPR 2020 - ; ECCV 2020 - ; ICCV 2021 - .
  • ICLR 2020 - ; NeurIPS 2020 - ; ICML 2021 - .
  • ICPR 2016, 2018; ACPR 2015, 2017, 2019; ICDAR 2017, 2019.
• Associate Editors for Journals:
  • SNCS (2021 - ).
• Reviewer for Journals:
  • PR (2015 - ), TNNLS (2015 - ), IJCV (2017 - ), TCYB (2017 - ), TPAMI (2019 - ).
• Tutorial on Graph-based Methods in Pattern Recognition & Document Image Analysis, ICDAR 2017, 2019, Organizing Committee.

Selected Publications

2021

• Implicit and Explicit Attention for Zero-Shot Learning
  Faisal Alamri and Anjan Dutta
  German Conference on Pattern Recognition (GCPR), 2021
• Concurrent Discrimination and Alignment for Self-Supervised Feature Learning
  Anjan Dutta, Massimiliano Mancini and Zeynep Akata
  International Conference on Computer Vision (ICCV), 2021
• Multi-Headed Self-Attention via Vision Transformer for Zero-Shot Learning
  Faisal Alamri and Anjan Dutta
  Irish Machine Vision and Image Processing Conference (IMVIP), 2021

2020

• Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrieval
  Anjan Dutta and Zeynep Akata
  International Journal of Computer Vision (IJCV), 2020
• Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition
  Anjan Dutta*, Pau Riba*, Josep Lladós and Alicia Fornés
  Neural Computing and Applications (NCAA), 2020
• Learning Robust Representations via Multi-View Information Bottleneck
  Marco Federici, Anjan Dutta, Patrick Forré, Nate Kushman, Zeynep Akata
  International Conference on Learning Representation (ICLR), 2020
• Bookworm continual learning: beyond zero-shot learning and continual learning
  Kai Wang, Luis Herranz, Anjan Dutta, Joost van de Weijer
  Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), 2020

2019

• Stochastic Graphlet Embedding
  Anjan Dutta and Hichem Sahbi
  IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2019
• Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval
  Anjan Dutta and Zeynep Akata
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
• Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval
  Sounak Dey, Pau Riba, Anjan Dutta, Josep Lladós and Yi-Zhe Song
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral Presentation)
• Table Detection in Invoice Documents by Graph Neural Networks
  Pau Riba, Anjan Dutta, Lutz Goldmann, Alicia Fornés, Oriol Ramos and Josep Lladós
  International Conference on Document Analysis and Recognition (ICDAR), 2019 (Oral Presentation)

2018

• Rough-Fuzzy based Scene Categorization for Text Detection and Recognition in Video
  Sangheeta Roy, Palaiahnakote Shivakumara, Namita Jain, Vijeta Khare, Anjan Dutta, Umapada Pal and Tong Lu
  Pattern Recognition (PR), 2018.
• Product Graph-based Higher Order Contextual Similarities for Inexact Subgraph Matching
  Anjan Dutta, Josep Lladós, Horst Bunke and Umapada Pal
  Pattern Recognition (PR), 2018.
• Aligning Salient Objects to Queries: A Multi-modal and Multi-object Image Retrieval Framework
  Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós and Umapada Pal
  Asian Conference on Computer Vision (ACCV), 2018
• Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch
  Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós and Umapada Pal
  International Conference on Pattern Recognition (ICPR), 2018

2017

• Large-scale Graph Indexing using Binary Embeddings of Node Contexts for Information Spotting in Document Image Databases
  Pau Riba, Josep Lladós, Alicia Fornés and Anjan Dutta
  Pattern Recognition Letters (PRL), 2017.
• Pyramidal Stochastic Graphlet Embedding for Document Pattern Classification
  Anjan Dutta, Pau Riba, Josep Lladós and Alicia Fornés
  International Conference on Document Analysis and Recognition (ICDAR), 2017 (Oral Presentation)
• Improving Information Retrieval in Multiwriter Scenario by Exploiting the Similarity Graph of Document Terms
  Pau Riba, Anjan Dutta, Sounak Dey, Josep Lladós and Alicia Fornés
  International Conference on Document Analysis and Recognition (ICDAR), 2017 (Oral Presentation)

2016 and Earlier

• Multi-oriented scene text detection in video based on wavelet and angle projection boundary growing
  Palaiahnakote Shivakumara, Anjan Dutta, Chew Lim Tan and Umapada Pal
  Multimedia Tools and Applications (MTA), 2014
• A symbol spotting approach in graphical documents by hashing serialized graphs
  Anjan Dutta, Josep Lladós and Umapada Pal
  Pattern Recognition (PR), 2013
• A Novel Mutual Nearest Neighbor based Symmetry for Text Frame Classification in Video
  Palaiahnakote Shivakumara, Anjan Dutta, Trung Quy Phan, Chew Lim Tan and Umapada Pal
  Pattern Recognition (PR), 2011
• Compact Correlated Features for Writer Independent Signature Verification
  Anjan Dutta, Umapada Pal and Josep Lladós
  International Conference on Pattern Recognition (ICPR), 2016 (Oral Presentation)
• High Order Graphlets for Pattern Classification
  Anjan Dutta and Hichem Sahbi
  Asian Conference on Pattern Recognition (ACPR), 2015
• Combination of Product Graph and Random Walk Kernel for Symbol Spotting in Graphical Documents
  Anjan Dutta, Jaume Gibert, Josep Lladós, Horst Bunke and Umapada Pal
  International Conference on Pattern Recognition (ICPR), 2012.
• Symbol Spotting in Line Drawings Through Graph Paths Hashing
  Anjan Dutta, Josep Lladós and Umapada Pal
  International Conference on Document Analysis and Recognition (ICDAR), 2011 (Oral Presentation)
• The ICDAR 2011 Music Scores Competition: Staff Removal and Writer Identification
  Alicia Fornés, Anjan Dutta, Albert Gordo and Josep Lladós
  International Conference on Document Analysis and Recognition (ICDAR), 2011 (Oral Presentation)