Search Results - "Bhunia, Ayan Kumar"

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification by Chang, Dongliang, Ding, Yifeng, Xie, Jiyang, Bhunia, Ayan Kumar, Li, Xiaoxu, Ma, Zhanyu, Wu, Ming, Guo, Jun, Song, Yi-Zhe

“…The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been…”
Get full text

Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network by Bhunia, Ankan Kumar, Konwer, Aishik, Bhunia, Ayan Kumar, Bhowmick, Abir, Roy, Partha P., Pal, Umapada

“…•A new attention based CNN-LSTM network is proposed for script identification.•It is based on local and global feature extraction and dynamically weighting…”
Get full text

Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning by Bhunia, Ayan Kumar, Das, Abhirup, Bhunia, Ankan Kumar, Kishore, Perla Sai Raj, Roy, Partha Pratim

“…Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. The design of deep…”
Get full text

Handwriting Trajectory Recovery using End-to-End Deep Encoder-Decoder Network by Kumar Bhunia, Ayan, Bhowmick, Abir, Kumar Bhunia, Ankan, Konwer, Aishik, Banerjee, Prithaj, Pratim Roy, Partha, Pal, Umapada

“…In this paper, we introduce a novel technique to recover the pen trajectory of offline characters which is a crucial step for handwritten character…”
Get full text

Improving Document Binarization Via Adversarial Noise-Texture Augmentation by Bhunia, Ankan Kumar, Bhunia, Ayan Kumar, Sain, Aneeshan, Roy, Partha Pratim

“…Binarization of degraded document images is an elementary step in most problems involving document image analysis. The paper re-visits the binarization problem…”
Get full text

User Constrained Thumbnail Generation Using Adaptive Convolutions by Raj Kishore, Perla Sai, Kumar Bhunia, Ayan, Ghose, Shuvozit, Roy, Partha Pratim

“…Thumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any…”
Get full text

Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks by Kumar Bhunia, Ankan, Kumar Bhunia, Ayan, Banerjee, Prithaj, Konwer, Aishik, Bhowmick, Abir, Pratim Roy, Partha, Pal, Umapada

“…Conversion of one font to another font is very useful in real life applications. In this paper, we propose a Convolutional Recurrent Generative model to solve…”
Get full text

Local Neighborhood Intensity Pattern–A new texture feature descriptor for image retrieval by Banerjee, Prithaj, Bhunia, Ayan Kumar, Bhattacharyya, Avirup, Roy, Partha Pratim, Murala, Subrahmanyam

“…•A new texture descriptor named LNIP is proposed for image retrieval.•It is based on the local neighborhood intensity difference.•LNIPS focuses on the sign and…”
Get full text

HMM-based Indic handwritten word recognition using zone segmentation by Roy, Partha Pratim, Bhunia, Ayan Kumar, Das, Ayan, Dey, Prasenjit, Pal, Umapada

“…This paper presents a novel approach towards Indic handwritten word recognition using zone-wise information. Because of complex nature due to compound…”
Get full text

Cross-language framework for word recognition and spotting of Indic scripts by Bhunia, Ayan Kumar, Roy, Partha Pratim, Mohta, Akash, Pal, Umapada

“…•We introduce a cross-language-based text recognition and word spotting in handwritten recognition platform.•A novel script similarity measure evaluation is…”
Get full text

Multi-oriented text detection and verification in video frames and scene images by Sain, Aneeshan, Bhunia, Ayan Kumar, Roy, Partha Pratim, Pal, Umapada

“…•An efficient approach is proposed which is able to detect horizontal, non-horizontal and curvedly oriented texts in video frames and scene images.•The concept…”
Get full text

StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval by Sain, Aneeshan, Bhunia, Ayan Kumar, Yang, Yongxin, Xiang, Tao, Song, Yi-Zhe

“…Sketch-based image retrieval (SBIR) is a cross-modal matching problem which is typically solved by learning a joint embedding space where the semantic content…”
Get full text

Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval by Bhunia, Ayan Kumar, Yang, Yongxin, Hospedales, Timothy M., Xiang, Tao, Song, Yi-Zhe

“…Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user's query sketch. Its widespread…”
Get full text

A deep one-shot network for query-based logo retrieval by Bhunia, Ayan Kumar, Bhunia, Ankan Kumar, Ghose, Shuvozit, Das, Abhirup, Roy, Partha Pratim, Pal, Umapada

“…•A scalable solution is proposed for the logo detection problem by redesigning the traditional problem setting.•It is based on one-shot learning…”
Get full text

A novel feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern by Bhunia, Ayan Kumar, Bhattacharyya, Avirup, Banerjee, Prithaj, Roy, Partha Pratim, Murala, Subrahmanyam

“…In this paper, we have proposed a novel feature descriptors combining color and texture information collectively. In our proposed color descriptor component,…”
Get full text

Date-field retrieval in scene image and video frames using text enhancement and shape coding by Roy, Partha Pratim, Bhunia, Ayan Kumar, Pal, Umapada

“…Text recognition in scene image and video frames is difficult because of low resolution, blur, background noise, etc. Since traditional OCRs do not perform…”
Get full text

HMM-based writer identification in music score documents without staff-line removal by Roy, Partha Pratim, Bhunia, Ayan Kumar, Pal, Umapada

“…•A writer identification system in musical documents without removing staff-lines.•An improved feature selection method for better writer identification…”
Get full text

CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not by Sain, Aneeshan, Bhunia, Ayan Kumar, Chowdhury, Pinaki Nath, Koley, Subhadeep, Xiang, Tao, Song, Yi-Zhe

“…In this paper, we leverage CLIP for zero-shot sketch based image retrieval (ZS-SBIR). We are largely inspired by recent advances on foundation models and the…”
Get full text

Indic handwritten script identification using offline-online multi-modal deep network by Bhunia, Ayan Kumar, Mukherjee, Subham, Sain, Aneeshan, Bhunia, Ankan Kumar, Roy, Partha Pratim, Pal, Umapada

“…•Deep multi-modal framework for efficient utilization of offline and online modalities.•A novel conditional fusion scheme for effective combination of two…”
Get full text

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval by Bhunia, Ayan Kumar, Chowdhury, Pinaki Nath, Sain, Aneeshan, Yang, Yongxin, Xiang, Tao, Song, Yi-Zhe

“…A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity - model performances are largely…”
Get full text