656 citations · 666 across the 7 of their papers we have counts for
10 papers
Privacy-Preserving Action Recognition via Motion Difference Quantization
Sudhakar Kumawat, Hajime Nagahara
The widespread use of smart computer vision systems in our personal spaces has led to an increased consciousness about the privacy and security risks that these systems pose. On th…
ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
Sudhakar Kumawat, Gagan Kanojia, Shanmuganathan Raman
Deep neural networks have enormous representational power which leads them to overfit on most datasets. Thus, regularizing them is important in order to reduce overfitting and enha…
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
Sudhakar Kumawat, Manisha Verma, Yuta Nakashima +1
Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their f…
Yoga-82: A New Dataset for Fine-grained Classification of Human Poses
Manisha Verma, Sudhakar Kumawat, Yuta Nakashima +1
Human pose estimation is a well-known problem in computer vision to locate joint positions. Existing datasets for the learning of poses are observed to be not challenging enough in…
Depthwise-STFT based separable Convolutional Neural Networks
Sudhakar Kumawat, Shanmuganathan Raman
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer.…
PlantDoc: A Dataset for Visual Plant Disease Detection
Davinder Singh, Naman Jain, Pranjali Jain +3
India loses 35% of the annual crop yield due to plant diseases. Early detection of plant diseases remains difficult due to the lack of lab infrastructure and expertise. In this pap…
Exploring Temporal Differences in 3D Convolutional Neural Networks
Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman
Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less…
Attentive Spatio-Temporal Representation Learning for Diving Classification
Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman
Competitive diving is a well recognized aquatic sport in which a person dives from a platform or a springboard into the water. Based on the acrobatics performed during the dive, di…
LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences
Sudhakar Kumawat, Manisha Verma, Shanmuganathan Raman
Recognizing facial expressions is one of the central problems in computer vision. Temporal image sequences have useful spatio-temporal features for recognizing expressions. In this…
LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
Sudhakar Kumawat, Shanmuganathan Raman
Traditional 3D Convolutional Neural Networks (CNNs) are computationally expensive, memory intensive, prone to overfit, and most importantly, there is a need to improve their featur…