Search Results for author:
Found 73 papers, 28 papers with code
SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
In response, this work introduces SVGCraft, a novel end-to-end framework for the creation of vector graphics depicting entire scenes from textual descriptions.
GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements.
Static and Dynamic Synthesis of Bengali and Devanagari Signatures
This paper aims to adapt this scheme for the generation of synthetic signatures in two Indic scripts, Bengali (Bangla), and Devanagari (Hindi).
A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement
Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results.
DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization
Instead of using a simple vision transformer block to extract information from the image patches, the proposed architecture uses two transformer blocks for greater coverage of the extracted feature space on a global and local scale.
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions.
Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system.
FAST: Font-Agnostic Scene Text Editing
However, most of the existing STE methods show inferior editing performance because of (1) complex image backgrounds, (2) various font styles, and (3) varying word lengths within the text.
DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
We propose a cosine similarity-dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space.
Scene Text Recognition with Image-Text Matching-guided Dictionary
Inspired by ITC, the SITM network combines the visual features and the text features of all candidates to identify the candidate with the minimum distance in the feature space.
SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation
Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image.
SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc.
MMC: Multi-Modal Colorization of Images using Textual Descriptions
Handling various objects with different colors is a significant challenge for image colorization techniques.
ICDAR 2023 Video Text Reading Competition for Dense and Small Text
In this competition report, we establish a video text reading benchmark, DSText, which focuses on dense and small text reading challenges in the video with various scenarios.
A CNN Based Framework for Unistroke Numeral Recognition in Air-Writing
Air-writing refers to virtually writing linguistic characters through hand gestures in three-dimensional space with six degrees of freedom.
Global Context-Aware Person Image Generation
The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context.
Effective Document Image Enhancement Using tokens-to-token Transformer Network
Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokeniza-tion technique to capture this local information from an image for achieving more effective results.
Ranked #1 on
Binarization
on H-DIBCO 2012
TIPS: Text-Induced Pose Synthesis
In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person.
SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
For target images (scene text images), the Semantic Generator Module generates simple semantic features that share the same feature distribution with support images (clear text images).
Scene Aware Person Image Generation through Global Contextual Conditioning
Finally, the target image is generated from the refined skeleton using another generative network conditioned on a given image of the target person.
SWIS: Self-Supervised Representation Learning For Writer Independent Offline Signature Verification
Writer independent offline signature verification is one of the most challenging tasks in pattern recognition as there is often a scarcity of training data.
Multi-scale Attention Guided Pose Transfer
Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose.
DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer
has emerged as an interesting problem for the document analysis and understanding community.
SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification
This results in robust discriminative learning of the embedding space.
DocEnTr: An End-to-End Document Image Enhancement Transformer
Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties.
Ranked #1 on
Binarization
on H-DIBCO 2011
MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning
After 200 epochs of pre-training with ResNet-18 as the backbone, the proposed model achieves an accuracy of 86. 2\%, 58. 18\%, 77. 49\%, and 30. 87\% on CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet datasets, respectively, and surpasses the SOTA contrastive baseline by 1. 23\%, 3. 57\%, 2. 00\%, and 0. 33\%, respectively.
GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation
The repeated fusion operations gated by CMSA and MSFS demonstrate improved generalizability of the network.
Ranked #13 on
Medical Image Segmentation
on Kvasir-SEG
AGA-GAN: Attribute Guided Attention Generative Adversarial Network with U-Net for Face Hallucination
The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively.
Exploiting Multi-Scale Fusion, Spatial Attention and Patch Interaction Techniques for Text-Independent Writer Identification
Our methods are based on the hypothesis that handwritten text images have specific spatial regions which are more unique to a writer's style, multi-scale features propagate characteristic features with respect to individual writers and patch-based features give more general and robust representations that helps to discriminate handwriting from different writers.
PAANet: Progressive Alternating Attention for Automatic Medical Image Segmentation
We develop progressive alternating attention dense (PAAD) blocks, which construct a guiding attention map (GAM) after every convolutional layer in the dense blocks using features from all scales.
GradML: A Gradient-based Loss for Deep Metric Learning
Deep metric learning (ML) uses a carefully designed loss function to learn distance metrics for improving the discriminatory ability for tasks like clustering and retrieval.
LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning
Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc.
Graph-based Deep Generative Modelling for Document Layout Generation
One of the major prerequisites for any deep learning approach is the availability of large-scale training data.
DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis
The results highlight that our model can successfully generate realistic and diverse document images with multiple objects.
MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation
The proposed MSRF-Net allows to capture object variabilities and provides improved results on different biomedical datasets.
Ranked #3 on
Medical Image Segmentation
on 2018 Data Science Bowl
PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection
Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms.
SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data
The downstream task in our paper is a class imbalanced multi-label classification.
Ranked #2 on
Multi-Label Classification
on MRNet
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
Position and Rotation Invariant Sign Language Recognition from 3D Kinect Data with Recurrent Neural Networks
Sign language is a gesture-based symbolic communication medium among speech and hearing impaired people.
Self-Supervised Representation Learning for Detection of ACL Tear Injury in Knee MR Videos
In this paper, we propose a self-supervised learning approach to learn transferable features from MR video clips by enforcing the model to learn anatomical features.
UDBNET: Unsupervised Document Binarization Network via Adversarial Game
In this paper, we present a novel approach towards document image binarization by introducing three-player min-max adversarial game.
Ranked #2 on
Binarization
on DIBCO 2011
A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video
The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions.
Modeling Extent-of-Texture Information for Ground Terrain Recognition
Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image.
DELP-DAR System for License Plate Detection and Recognition
For this, we present in this paper an automatic framework for License Plate (LP) detection and recognition from complex scenes.
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense.
Cultural Vocal Bursts Intensity Prediction
General Classification
+2
Distance Metric Learned Collaborative Representation Classifier
We present a simple effective way of achieving this by learning a generic Mahalanabis distance in a collaborative loss function in an end-to-end fashion with any standard convolutional network as the feature learner.
PProCRC: Probabilistic Collaboration of Image Patches
We present a conditional probabilistic framework for collaborative representation of image patches.
STEFANN: Scene Text Editor using Font Adaptive Neural Network
In this paper, we propose a method to modify text in an image at character-level.
CoCoNet: A Collaborative Convolutional Network
We present an end-to-end deep network for fine-grained visual categorization called Collaborative Convolutional Network (CoCoNet).
Fine-Grained Visual Categorization
Fine-Grained Visual Recognition
+1
A Deep One-Shot Network for Query-based Logo Retrieval
Logo detection in real-world scene images is an important problem with applications in advertisement and marketing.
Effects of Degradations on Deep Neural Network Architectures
Deep convolutional neural networks (CNN) have massively influenced recent advances in large-scale image classification.
Bag-of-Visual-Words for Signature-Based Multi-Script Document Retrieval
Finally, three distance measures were used to match a query signature with the signature present in target documents for retrieval.
A New COLD Feature based Handwriting Analysis for Ethnicity/Nationality Identification
For each line segment, the proposed method estimates angle and length, which gives a point in polar domain.
Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query.
Indic Handwritten Script Identification using Offline-Online Multimodal Deep Network
In this paper, we propose a novel approach of word-level Indic script identification using only character-level data in training stage.
Staff line Removal using Generative Adversarial Networks
Staff line removal is a crucial pre-processing step in Optical Music Recognition.
Handwriting Trajectory Recovery using End-to-End Deep Encoder-Decoder Network
Our encoder module consists of Convolutional LSTM network, which takes an offline character image as the input and encodes the feature sequence to a hidden representation.
Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks
We employ a novel convolutional recurrent model architecture in the Generator that efficiently deals with the word images of arbitrary width.
Script Identification in Natural Scene Image and Video Frame using Attention based Convolutional-LSTM Network
In this paper, we propose a novel method that involves extraction of local and global features using CNN-LSTM framework and weighting them dynamically for script identification.
Cross-language Framework for Word Recognition and Spotting of Indic Scripts
This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script).
Zone-based Keyword Spotting in Bangla and Devanagari Documents
Also, we propose a novel feature combining foreground and background information of text line images for keyword-spotting by character filler models.
LOOP Descriptor: Local Optimal Oriented Pattern
This letter introduces the LOOP binary descriptor (local optimal oriented pattern) that encodes rotation invariance into the main formulation itself.
Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding
To evaluate the proposed system for searching keyword from natural scene image and video frames, we have considered two popular Indic scripts such as Bangla (Bengali) and Devanagari along with English.
HMM-based Indic Handwritten Word Recognition using Zone Segmentation
To avoid character segmentation in such scripts, HMM-based sequence modeling has been used earlier in holistic way.
Multi-Oriented Text Detection and Verification in Video Frames and Scene Images
Until now only a few methods have been proposed that look into curved text detection in video frames, wherein lies our novelty.
HMM-based Writer Identification in Music Score Documents without Staff-Line Removal
A novel Factor Analysis based feature selection technique is applied in sliding window features to reduce the noise appearing from staff lines which proves efficiency in writer identification performance. In our framework we have also proposed a novel score line detection approach in musical sheet using HMM.
Date-Field Retrieval in Scene Image and Video Frames using Text Enhancement and Shape Coding
We propose a line based date spotting approach using Hidden Markov Model (HMM) which is used to detect the date information in a given text.
Text Recognition in Scene Image and Video Frame using Color Channel Selection
In this paper, we present a novel approach based on color channel selection for text recognition from scene images and video frames.
SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification
Offline signature verification is one of the most challenging tasks in biometrics and document forensics.
Ranked #1 on
Handwriting Verification
on CEDAR Signature
Product Graph-based Higher Order Contextual Similarities for Inexact Subgraph Matching
Many algorithms formulate graph matching as an optimization of an objective function of pairwise quantification of nodes and edges of two graphs to be matched.
Evaluation of the Effect of Improper Segmentation on Word Spotting
Word spotting is an important recognition task in historical document analysis.
Local Binary Pattern for Word Spotting in Handwritten Historical Document
Digital libraries store images which can be highly degraded and to index this kind of images we resort to word spot- ting as our information retrieval system.
