IFVSNet : Intermediate Features Fusion based CNN for Video Subtitles Identification

Naosekpam, Veronica; Sahu, Nilkanta

doi:10.1109/i2ct54291.2022.9825167

Cited by 3 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Videos primarily feature two text types: scene text [2][3][4][5][6] and captions. 7 Billboards, trucks, t-shirts, streets, and buildings commonly display scene text, whereas captions, comprising subtitles and overlay text, undergo manual video edits. We can efficiently process and recognize captions since they are editable.…”

Section: Introductionmentioning

confidence: 99%

Video text rediscovery: Predicting and tracking text across complex scenes

Naosekpam,

Sahu

2024

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Dynamic texts in scene videos provide valuable insights and semantic cues crucial for video applications. However, the movement of this text presents unique challenges, such as blur, shifts, and blockages. While efficient in tracking text, state‐of‐the‐art systems often need help when text becomes obscured or complicated scenes. This study introduces a novel method for detecting and tracking video text, specifically designed to predict the location of obscured or occluded text in subsequent frames using a tracking‐by‐detection paradigm. Our approach begins with a primary detector to identify text within individual frames, thus enhancing tracking accuracy. Using the Kalman filter, Munkres algorithm, and deep visual features, we establish connections between text instances across frames. Our technique works on the concept that when text goes missing in a frame due to obstructions, we use its previous speed and location to predict its next position. Experiments conducted on the ICDAR2013 Video and ICDAR2015 Video datasets confirm our method's efficacy, matching or surpassing established methods in performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Video text rediscovery: Predicting and tracking text across complex scenes

Naosekpam,

Sahu

2024

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…The term "script" refers to a writing system of various symbols used in human communication. The research area of multi-lingual unconstrained scene text understanding 1 involves text detection, [2][3][4] identification of the scripts, [5][6][7][8][9] and recognition. [10][11][12] The domain is an active research area in the computer vision fraternity owing to its wide range of potential applications, such as language translation, image-to-text conversion, assistance for tourists, intelligent license reading systems, product reading assistance for specially-abled people in indoor environments and so forth.…”

Section: Introductionmentioning

confidence: 99%

Few‐shot learning for word‐level scene text script identification

Naosekpam,

Sahu

2023

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Script identification of text in scene images has attracted massive attention recently. However, the existing techniques primarily emphasize on scripts where data are available abundantly, such as English, European, or East Asian. Although these methods are robust in dealing with high‐resource data, how these techniques will work on low‐resource scripts has yet to be discovered. For example, in India, there is a disparity among the text scripts across the country's demographic. To bridge the research gap for resource‐constraint script identification, we present a few‐shot learning network called the TextScriptFSLNet. This network does not require huge training data while achieving state‐of‐the‐art performance on benchmark datasets. Our proposed method acts in accordance with a ‐way ‐shot paradigm by splitting the train set as support and query set, respectively. The support set learns representative knowledge of each class and creates its prototypes. We use multi‐kernel spatial attention fused 2‐layer convolutional neural network and averaging technique to generate the prototype of each class. This spatial attention aids in grasping important information in an image and enriches the feature representation. To the best of our knowledge, the proposed work is the first of its kind in the scene text understanding domain. Additionally, we created a dataset called Indic‐FSL2023 comprising 10 of the 22 officially recognized Indian scripts. The proposed method achieves the highest accuracy among the tested methods on the newly created Indic‐FSL2023. Experiments are also conducted on MLe2e to demonstrate its versatility. Furthermore, we also showed how our proposed model performed concerning illumination changes and blur on scene text script images.

show abstract