.

index.html

@@ -238,42 +238,58 @@ <h2>Contact Me</h2>
         <div class="modal-content">
             <span class="close">&times;</span>
             <h2>Text-Based Object Identification: A Lightweight Approach</h2>
-            <img src="vid1.webm" alt="Screenshot" class="article-image">
+            <video width="640" height="200" controls>
+                <source src="vid1.webm" type="video/webm" class="article-image">
+            </video>
             <p>Text-based object identification is an approach that leverages text recognition and machine learning
                 techniques to identify objects in images based on the associated text information. This method has
                 gained attention as a lightweight alternative to more complex computer vision techniques for object
                 recognition.
                 The concept of using text for object identification has been explored in various research papers and
-                projects. Shen et al. (2016) proposed a deep learning approach for text-based image retrieval, utilizing
-                Convolutional Neural Networks (CNNs) to learn the mapping between text queries and image features [1].
-                Barbu et al. (2014) presented a system for text-based object recognition in natural scenes, combining
+                projects. Shen et al. (2016) proposed a deep learning approach for text-based image retrieval,
+                utilizing
+                Convolutional Neural Networks (CNNs) to learn the mapping between text queries and image features
+                [1].
+                Barbu et al. (2014) presented a system for text-based object recognition in natural scenes,
+                combining
                 text detection, optical character recognition (OCR), and object recognition techniques [2].</p>
-            <p>Zhang et al. (2011) focused on retrieving objects in videos based on text queries, proposing a framework
-                that integrates text detection, tracking, and recognition with object retrieval techniques [3]. Schuster
-                et al. (2015) introduced a method for text-based image retrieval using scene graphs, which capture the
-                relationships between objects in an image and use natural language processing techniques to parse text
+            <p>Zhang et al. (2011) focused on retrieving objects in videos based on text queries, proposing a
+                framework
+                that integrates text detection, tracking, and recognition with object retrieval techniques [3].
+                Schuster
+                et al. (2015) introduced a method for text-based image retrieval using scene graphs, which capture
+                the
+                relationships between objects in an image and use natural language processing techniques to parse
+                text
                 queries [4].
                 While text-based object identification has shown promise in certain scenarios, it is important to
-                acknowledge its limitations compared to more advanced computer vision techniques. Deep learning-based
+                acknowledge its limitations compared to more advanced computer vision techniques. Deep
+                learning-based
                 approaches using CNNs have achieved state-of-the-art performance in object detection and recognition
                 tasks by directly learning visual features from images [5].</p>
             <p>However, text-based object identification can still be a valuable technique in specific domains where
-                objects are commonly associated with text labels or captions, such as product recognition or document
+                objects are commonly associated with text labels or captions, such as product recognition or
+                document
                 analysis. It can also serve as a complementary approach to enhance the performance of visual object
                 recognition systems.
-                In conclusion, text-based object identification offers a lightweight approach to object recognition by
+                In conclusion, text-based object identification offers a lightweight approach to object recognition
+                by
                 leveraging text information associated with images. While it may not match the performance of more
                 advanced computer vision techniques, it can be effective in certain scenarios and serve as a
                 complementary method to enhance object recognition systems.</p>
             References:
             <p>[1] X. Shen, Z. Lin, J. Brandt, and Y. Wu, "Text-Based Image Retrieval Using Deep Learning," arXiv
                 preprint arXiv:1612.07119, 2016.</p>
-            <p>[2] A. Barbu, C. Wotawa, and J. M. Siskind, "Text-Based Object Recognition in the Wild," in Proceedings
+            <p>[2] A. Barbu, C. Wotawa, and J. M. Siskind, "Text-Based Object Recognition in the Wild," in
+                Proceedings
                 of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 3953-3960.</p>
-            <p>[3] Z. Zhang, L. Zhang, and M. Li, "Text-Based Object Retrieval in Videos," in Proceedings of the IEEE
+            <p>[3] Z. Zhang, L. Zhang, and M. Li, "Text-Based Object Retrieval in Videos," in Proceedings of the
+                IEEE
                 International Conference on Multimedia and Expo, 2011, pp. 1-6.</p>
-            <p>[4] S. Schuster, R. Krishna, A. Chang, L. Fei-Fei, and C. D. Manning, "Text-Based Image Retrieval Using
-                Scene Graphs," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015,
+            <p>[4] S. Schuster, R. Krishna, A. Chang, L. Fei-Fei, and C. D. Manning, "Text-Based Image Retrieval
+                Using
+                Scene Graphs," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,
+                2015,
                 pp. 3945-3954.</p>
             <p>[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional
                 Neural Networks," in Advances in Neural Information Processing Systems, 2012, pp. 1097-1105.</p>