Manmadhan, S.[Sruthy]
Co Author Listing * Multi-Tier Attention Network using Term-weighted Question Features for Visual Question Answering
Manmatha, R.
Co Author Listing * Home Page.
* email: Manmatha, R.: manmatha AT cs umass edu
* Adapting BLSTM Neural Network Based Keyword Spotting Trained on Modern Data to Historical Documents
* Aligning Transcripts to Automatically Segmented Handwritten Manuscripts
* Automatic Segmentation and Indexing in a Database of Bird Images
* Automatic Text Detection and Recognition
* BLSTM Neural Network Based Word Retrieval for Hindi Documents
* Characterization of Visual Appearance Applied to Image Retrieval, A
* Classification models for historical manuscript recognition
* Compressed Video Action Recognition
* Computing Global Image Similarity
* Creating an Improved Version Using Noisy OCR from Multiple Editions
* Data Set for Quantitative Motion Analysis, A
* Deep Decision Network for Multi-class Image Classification
* Dependence Models for Searching Text in Document Images
* discrete direct retrieval model for image and video retrieval, A
* DocFormer: End-to-End Transformer for Document Understanding
* DocTr: Document Transformer for Structured Information Extraction in Documents
* Efficient Exploration of Text Regions in Natural Scene Images Using Adaptive Image Sampling
* Efficient Search in Document Image Collections
* Enabling Search over Large Collections of Telugu Document Images: An Automatic Annotation Based Approach
* Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition
* Extracting Affine Deformations from Image Patches - I: Finding Scale and Rotation
* Extracting Text From Greyscale Images
* Fast Alignment Scheme for Automatic OCR Evaluation of Books, A
* Fast, Background-Independent Retrieval Strategy for Color Image Databases, A
* Features for word spotting in historical manuscripts
* Finding Text In Images
* Finding words in alphabet soup: Inference on freeform character recognition for historical scripts
* Formulating Action Recognition as a Ranking Problem
* Framework for Recovering Affine Transforms Using Points, Lines or Image Brightnesses, A
* Further explorations in text alignment with handwritten documents
* GLASS: Global to Local Attention for Scene-Text Spotting
* Holistic word recognition for handwritten historical documents
* Image retrieval using Markov Random Fields and global image features
* Image Retrieval Using Scale-Space Matching
* Improving Semantic Segmentation via Efficient Self-Training
* Indexing Flowers by Color Names
* Indexing Flowers by Color Names Using Domain Knowledge-Driven Segmentation
* Indexing Handwriting Using Word Matching
* Inference Network Approach to Image Retrieval, An
* Issues in Extracting Motion Parameters and Depth from Approximate Translation Motion
* Large Scale Document Image Retrieval by Automatic Word Annotation
* LaTr: Layout-Aware Transformer for Scene-Text VQA
* Learning Shapes for Image Classification and Retrieval
* Measuring the Affine Transform - I: Recovering Scale and Rotation
* Measuring the Affine Transform Using Gaussian Filters
* Multiple Bernoulli relevance models for image and video annotation
* Novel Word Spotting Method Based on Recurrent Neural Networks, A
* On Calibration of Scene-text Recognition Models
* On Computing Global Similarity in Images
* On Influence of Line Segmentation in Efficient Word Segmentation in Old Manuscripts
* PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
* ResNeSt: Split-Attention Networks
* Retrieving Images by Appearance
* Retrieving Images by Similarity of Visual Appearance
* Robust Recognition of Documents by Fusing Results of Word Clusters
* Saliency Driven Perceptual Image Compression
* Sampling Matters in Deep Embedding Learning
* Scale Space Approach for Automatically Segmenting Words from Historical Handwritten Documents, A
* Scale space technique for word segmentation in handwritten manuscripts
* Scale-Space Matching and Image Retrieval
* SCATTER: Selective Context Attentional Scene Text Recognizer
* Sequence-to-Sequence Contrastive Learning for Text Recognition
* Special issue on Multimedia Event Detection
* Text alignment with handwritten documents
* Text Image Clean-Up and Thresholding: A Comparative Study
* TextFinder
* TextFinder: An Automatic System to Detect and Recognize Text in Images
* Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer
* Using Maximum Entropy for Automatic Image Annotation
* Word image matching using dynamic time warping
* Word Spotting
* Word spotting for historical documents
* Word Spotting: A New Approach to Indexing Handwriting
* YORO - Lightweight End to End Visual Grounding
Includes: Manmatha, R. Manmatha, R.[Raghavan]
76 for Manmatha, R.