Notice Board :

Call for Paper
Vol. 12 Issue 6

Submission Start Date:
September 01, 2024

Acceptence Notification Start:
September 15, 2024

Submission End:
October 20, 2024

Final MenuScript Due:
October 25, 2024

Publication Date:
October 29, 2024
                         Notice Board: Call for PaperVol. 12 Issue 6      Submission Start Date: September 01, 2024      Acceptence Notification Start: September 15, 2024      Submission End: October 20, 2024      Final MenuScript Due: October 25, 2024      Publication Date: October 29, 2024




Volume XII Issue VI

Author Name
Lallan Kumar, Asst. Prof. Ayush Kumar
Year Of Publication
2024
Volume and Issue
Volume 12 Issue 6
Abstract
This paper presents a POS tagging approach for Hindi, a morphologically rich language, to demonstrate that strong morphology can offset limited training data. The methodology uses a modestly-sized, locally annotated corpus (15,562 words), detailed morphological analysis, a high-coverage lexicon and a CN2 decision-tree-based learning algorithm. The system’s performance was evaluated using 4-fold cross-validation on news data from BBC Hindi. The POS tagger currently achieves an accuracy of 93.45%, with potential for further improvement.
PaperID
12601

Author Name
Prabhati Bharti, Ayush Kumar
Year Of Publication
2024
Volume and Issue
Volume 12 Issue 6
Abstract
In this paper, we tackle the problem of natural language object retrieval, where the goal is to locate a target object within an image based on a natural language description. Unlike text-based image retrieval, natural language object retrieval requires understanding the spatial relationships between objects in the scene and the overall context of the image. To address this, we introduce a novel Context Recurrent ObjNet (CRO) model that serves as a scoring function for candidate bounding boxes, integrating both spatial configurations and scene-level contextual information. Our model processes query text, local image features, spatial configurations through a recurrent network, producing a probability score for each candidate box based on the query. Additionally, the model leverages visual-linguistic knowledge from the image captioning domain to enhance retrieval accuracy.
PaperID
12602

Publish your own book with us

with ISBN


for more details contact:
snspes@gmail.com