Search Results for author: Pinaki Nath Chowdhury

Found 15 papers, 6 papers with code

SceneTrilogy: On Scene Sketches and its Relationship with Text and Photo

no code implementations25 Apr 2022 Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Tao Xiang, Yi-Zhe Song

We spell out a few insights on the complementarity of each modality for scene understanding, and study for the first time a series of scene-specific applications like joint sketch- and text-based image retrieval, sketch captioning.

Image Retrieval Scene Understanding

Sketch3T: Test-Time Training for Zero-Shot SBIR

no code implementations CVPR 2022 Aneeshan Sain, Ayan Kumar Bhunia, Vaishnav Potlapalli, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

In this paper, we question to argue that this setup by definition is not compatible with the inherent abstract and subjective nature of sketches, i. e., the model might transfer well to new categories, but will not understand sketches existing in different test-time distribution as a result.

Meta-Learning Sketch-Based Image Retrieval

FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context

no code implementations4 Mar 2022 Pinaki Nath Chowdhury, Aneeshan Sain, Yulia Gryaditskaya, Ayan Kumar Bhunia, Tao Xiang, Yi-Zhe Song

In addition, we propose new solutions enabled by our dataset (i) We adopt meta-learning to show how the retrieval model can be fine-tuned to a new user style given just a small set of sketches, (ii) We extend a popular vector sketch LSTM-based encoder to handle sketches with larger complexity than was supported by previous work.

Image Captioning Image Retrieval +1

SketchLattice: Latticed Representation for Sketch Manipulation

no code implementations ICCV 2021 Yonggang Qi, Guoyao Su, Pinaki Nath Chowdhury, Mingkang Li, Yi-Zhe Song

The key challenge in designing a sketch representation lies with handling the abstract and iconic nature of sketches.

Towards the Unseen: Iterative Text Recognition by Distilling from Errors

no code implementations ICCV 2021 Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain, Yi-Zhe Song

Our framework is iterative in nature, in that it utilises predicted knowledge of character sequences from a previous iteration, to augment the main network in improving the next prediction.

Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation

no code implementations ICCV 2021 Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Yi-Zhe Song

In this paper, for the first time, we argue for their unification -- we aim for a single model that can compete favourably with two separate state-of-the-art STR and HTR models.

Handwriting Recognition Knowledge Distillation +1

MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition

1 code implementation CVPR 2021 Ayan Kumar Bhunia, Shuvozit Ghose, Amandeep Kumar, Pinaki Nath Chowdhury, Aneeshan Sain, Yi-Zhe Song

In this paper, we take a completely different perspective -- we work on the assumption that there is always a new style that is drastically different, and that we will only have very limited data during testing to perform adaptation.

Handwritten Text Recognition Meta-Learning

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval

1 code implementation CVPR 2021 Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain, Yongxin Yang, Tao Xiang, Yi-Zhe Song

A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs.

Cross-Modal Retrieval Semi-Supervised Sketch Based Image Retrieval +1

UDBNET: Unsupervised Document Binarization Network via Adversarial Game

1 code implementation14 Jul 2020 Amandeep Kumar, Shuvozit Ghose, Pinaki Nath Chowdhury, Partha Pratim Roy, Umapada Pal

In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game.

Binarization

Modeling Extent-of-Texture Information for Ground Terrain Recognition

1 code implementation17 Apr 2020 Shuvozit Ghose, Pinaki Nath Chowdhury, Partha Pratim Roy, Umapada Pal

Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.