Search Results for author: Suraj Tripathi

Found 14 papers, 1 papers with code


no code implementations25 Sep 2019 Suraj Tripathi, Chirag Singh, Abhay Kumar

And our proposed decoder network serves the purpose of reducing the transformation present in the input image by learning to construct a representative image of the input image class.

Representation Learning Rotated MNIST

Smaller Models, Better Generalization

no code implementations29 Aug 2019 Mayank Sharma, Suraj Tripathi, Abhimanyu Dubey, Jayadeva, Sai Guruju, Nihal Goalla

Reducing network complexity has been a major research focus in recent years with the advent of mobile technology.


MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation

no code implementations23 Aug 2019 Abhay Kumar, Nishant Jain, Suraj Tripathi, Chirag Singh, Kamal Krishna

The auxiliary task helps in capturing the relevant scale-related information to improve the performance of the main task.

Data Augmentation Density Estimation +1

Learning Discriminative features using Center Loss and Reconstruction as Regularizer for Speech Emotion Recognition

no code implementations19 Jun 2019 Suraj Tripathi, Abhiram Ramesh, Abhay Kumar, Chirag Singh, Promod Yenigalla

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech.

Metric Learning Speech Emotion Recognition

Visual Context-aware Convolution Filters for Transformation-invariant Neural Network

no code implementations15 Jun 2019 Suraj Tripathi, Abhay Kumar, Chirag Singh

We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs).

Rotated MNIST

From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation

no code implementations11 Jun 2019 Abhay Kumar, Nishant Jain, Suraj Tripathi, Chirag Singh

To overcome this limitation, we propose a Zero Shot Learning (ZSL) paradigm for predicting unseen hashtag labels by learning the relationship between the semantic space of tweets and the embedding space of hashtag labels.

Zero-Shot Learning

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition

no code implementations11 Jun 2019 Suraj Tripathi, Abhay Kumar, Abhiram Ramesh, Chirag Singh, Promod Yenigalla

This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech.

Speech Emotion Recognition

Deep Learning Techniques for Humor Detection in Hindi-English Code-Mixed Tweets

no code implementations WS 2019 Sushmitha Reddy Sane, Suraj Tripathi, Koushik Reddy Sane, Radhika Mamidi

We propose bilingual word embeddings based on word2vec and fastText models (CBOW and Skip-gram) to address the problem of Humor detection in Hindi-English code-mixed tweets in combination with deep learning architectures.

Humor Detection Word Embeddings

Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network

no code implementations30 Mar 2019 Abhay Kumar, Nishant Jain, Chirag Singh, Suraj Tripathi

The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer.

Learning Neural Network Classifiers with Low Model Complexity

no code implementations31 Jul 2017 Jayadeva, Himanshu Pant, Mayank Sharma, Abhimanyu Dubey, Sumit Soman, Suraj Tripathi, Sai Guruju, Nihal Goalla

Our proposed approach yields benefits across a wide range of architectures, in comparison to and in conjunction with methods such as Dropout and Batch Normalization, and our results strongly suggest that deep learning techniques can benefit from model complexity control methods such as the LCNN learning rule.

Cannot find the paper you are looking for? You can Submit a new open access paper.