Related papers: Zone-based Keyword Spotting in Bangla and Devanaga…
Overhead line inspection greatly benefits from defect recognition using visible light imagery. Addressing the limitations of existing feature extraction techniques and the heavy data dependency of deep learning approaches, this paper…
In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder. We consider retrieval frameworks in which the user expects a retrieval list ranked…
An unconstrained end-to-end text localization and recognition method is presented. The method detects initial text hypothesis in a single pass by an efficient region-based method and subsequently refines the text hypothesis using a more…
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. Information retrieval for handwritten document images is more challenging due to…
The task of partial scene text retrieval involves localizing and searching for text instances that are the same or similar to a given query text from an image gallery. However, existing methods can only handle text-line instances, leaving…
Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a…
Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in…
Search has for a long time been an important tool for users to retrieve information. Syntactic search is matching documents or objects containing specific keywords like user-history, location, preference etc. to improve the results.…
Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over…
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression…
Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are…
Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detection. Typically, text prompt complements the text encoder's…
This paper describes a new feature set, called the extended directional features (EDF) for use in the recognition of online handwritten strokes. We use EDF specifically to recognize strokes that form a basis for producing Devanagari script,…
Several SLAM methods benefit from the use of semantic information. Most integrate photometric methods with high-level semantics such as object detection and semantic segmentation. We propose that adding a semantic segmentation decoder in a…
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…
Various machine learning methods for writer independent recognition of Malayalam handwritten district names are discussed in this paper. Data collected from 56 different writers are used for the experiments. The proposed work can be used…
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The…
Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a conformer encoder with trainable binary gates that allow us…
Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural…
Scene-text recognition is remarkably better in Latin languages than the non-Latin languages due to several factors like multiple fonts, simplistic vocabulary statistics, updated data generation tools, and writing systems. This paper…