Search Results for author:
Found 9 papers, 4 papers with code
AttResDU-Net: Medical Image Segmentation Using Attention-based Residual Double U-Net
Inspired by the Double U-Net, this architecture incorporates attention gates on the skip connections and residual connections in the convolutional blocks.
An Efficient Transfer Learning-based Approach for Apple Leaf Disease Classification
Correct identification and categorization of plant diseases are crucial for ensuring the safety of the global food supply and the overall financial success of stakeholders.
DEPTWEET: A Typology for Social Media Texts to Detect Depression Severities
Mental health research through data-driven methods has been hindered by a lack of standard typology and scarcity of adequate data.
Multiple Object Tracking in Recent Times: A Literature Review
To take these scattered techniques under an umbrella, we have studied more than a hundred papers published over the last three years and have tried to extract the techniques that are more focused on by researchers in recent times to solve the problems of MOT.
Two Decades of Bengali Handwritten Digit Recognition: A Survey
This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas.
Handwritten Digit Recognition
Optical Character Recognition
+1
HEATGait: Hop-Extracted Adjacency Technique in Graph Convolution based Gait Recognition
Biometric authentication using gait has become a promising field due to its unobtrusive nature.
Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification
Evaluation on tomato leaf images from the PlantVillage dataset shows that the proposed architecture achieves 99. 30% accuracy with a model size of 9. 60MB and 4. 87M floating-point operations, making it a suitable choice for real-life applications in low-end devices.
Densely-Populated Traffic Detection using YOLOv5 and Non-Maximum Suppression Ensembling
The performance of our proposed model was measured on Dhaka AI dataset which contains densely crowded vehicular images.
Improving Action Quality Assessment using Weighted Aggregation
We assess the effects of the depth and input clip size of the convolutional neural network on the quality of action score predictions.
Ranked #6 on
Action Quality Assessment
on MTL-AQA
