Search Results for author: Brejesh lall

Found 43 papers, 8 papers with code

IIITD-20K: Dense captioning for Text-Image ReID

no code implementations8 May 2023 A V Subramanyam, Niranjan Sundararajan, Vibhu Dubey, Brejesh lall

IIITD-20K comprises of 20, 000 unique identities captured in the wild and provides a rich dataset for text-to-image ReID.

Dense Captioning

A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentation

1 code implementation27 Feb 2023 Prashant Pandey, Mustafa Chasmai, Monish Natarajan, Brejesh lall

To this end, we propose a novel unified weakly supervised OVSS pipeline that can perform ZSS, FSS and Cross-dataset segmentation on novel classes without using pixel-level labels for either the base (seen) or the novel (unseen) classes in an inductive setting.

Few-Shot Semantic Segmentation Language Modelling +3

Knowledge Distillation in Vision Transformers: A Critical Review

no code implementations4 Feb 2023 Gousia Habib, Tausifa Jan Saleem, Brejesh lall

A number of model compression methods have been proposed in the literature such as weight quantization, weight multiplexing, pruning and Knowledge Distillation (KD).

Image Classification Knowledge Distillation +5

KL Regularized Normalization Framework for Low Resource Tasks

no code implementations21 Dec 2022 Neeraj Kumar, Ankur Narang, Brejesh lall

A lot of normalization techniques have been proposed but the success of normalization in low resource downstream NLP and speech tasks is limited.

Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs

1 code implementation7 Oct 2022 Prashant Pandey, Aleti Vardhan, Mustafa Chasmai, Tanuj Sur, Brejesh lall

We show that our framework is more robust compared to traditional adversarial defense mechanisms such as adversarial training.

Adversarial Defense Few-Shot Learning +1

Matrix Adaptive Synthesis Filter for Uniform Filter Bank

no code implementations22 Sep 2022 Sandeep Patel, Ravindra Dhuli, Brejesh lall

In this paper, we use a matrix adaptive filter as the synthesis stage of a Uniform Filter Bank (UFB) to reconstruct the input signal.

Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs

1 code implementation26 Aug 2022 Prashant Pandey, Mustafa Chasmai, Tanuj Sur, Brejesh lall

We further demonstrate that while many existing Deep CNN based methods tend to be extremely vulnerable to adversarial attacks, R-PNODE exhibits increased adversarial robustness for a wide array of these attacks.

Adversarial Robustness Few-Shot Learning +2

MaskMTL: Attribute prediction in masked facial images with deep multitask learning

1 code implementation9 Jan 2022 Prerana Mukherjee, Vinay Kaushik, Ronak Gupta, Ritika Jha, Daneshwari Kankanwadi, Brejesh lall

Predicting attributes in the landmark free facial images is itself a challenging task which gets further complicated when the face gets occluded due to the usage of masks.

Multi-Task Learning

Altering Backward Pass Gradients improves Convergence

no code implementations24 Nov 2021 Bishshoy Das, Milton Mondal, Brejesh lall, Shiv Dutt Joshi, Sumantra Dutta Roy

In standard neural network training, the gradients in the backward pass are determined by the forward pass.

Estimation and Prediction of Deterministic Human Intent Signal to augment Haptic Glove aided Control of Robotic Hand

no code implementations15 Oct 2021 Rajesh Kumar, Pimmy Gandotra, Brejesh lall, Arzad A. Kherani, Sudipto Mukherjee

Hence, a method is proposed to estimate the human intent from the high dimensional HG motion signal and reconstruct the signal at the RH to ensure object relocation.

One Shot Audio to Animated Video Generation

no code implementations19 Feb 2021 Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh lall, Mujtaba Hasan, Pranshu Agarwal, Dipankar Sarkar

We propose a novel method OneShotAu2AV to generate an animated video of arbitrary length using an audio clip and a single unseen image of a person as an input.

Video Generation

Few Shot Adaptive Normalization Driven Multi-Speaker Speech Synthesis

no code implementations14 Dec 2020 Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh lall

High quality multi-speaker speech synthesis while considering prosody and in a few shot manner is an area of active research with many real-world applications.

Cultural Vocal Bursts Intensity Prediction Speech Synthesis

Multi Modal Adaptive Normalization for Audio to Video Generation

no code implementations14 Dec 2020 Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh lall

The multi-modal adaptive normalization uses the various features of audio and video such as Mel spectrogram, pitch, energy from audio signals and predicted keypoint heatmap/optical flow and a single image to learn the respective affine parameters to generate highly expressive video.

Optical Flow Estimation SSIM +1

Deep Learning for Automated Screening of Tuberculosis from Indian Chest X-rays: Analysis and Update

no code implementations19 Nov 2020 Anushikha Singh, Brejesh lall, B. K. Panigrahi, Anjali Agrawal, Anurag Agrawal, Balamugesh Thangakunam, DJ Christopher

Methods: The proposed work explores the performance of convolutional neural networks (CNNs) for the diagnosis of TB in Indian chest x-ray images.

Deep LF-Net: Semantic Lung Segmentation from Indian Chest Radiographs Including Severely Unhealthy Images

no code implementations19 Nov 2020 Anushikha Singh, Brejesh lall, B. K. Panigrahi, Anjali Agrawal, Anurag Agrawal, DJ Christopher, Balamugesh Thangakunam

A chest radiograph, commonly called chest x-ray (CxR), plays a vital role in the diagnosis of various lung diseases, such as lung cancer, tuberculosis, pneumonia, and many more.

Semantic Segmentation

Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments

1 code implementation28 Aug 2020 Ronak Gupta, Prerana Mukherjee, Brejesh lall, Varshul Gupta

We have curated a large, novel Indian heritage monuments dataset comprising of images of historical, cultural and religious importance with subtypes of eras, dynasties and architectural styles.


Deep feature fusion for self-supervised monocular depth prediction

no code implementations16 May 2020 Vinay Kaushik, Brejesh lall

Recent advances in end-to-end unsupervised learning has significantly improved the performance of monocular depth prediction and alleviated the requirement of ground truth depth.

Depth Estimation Depth Prediction

Image fusion using symmetric skip autoencodervia an Adversarial Regulariser

no code implementations1 May 2020 Snigdha Bhagat, S. D. Joshi, Brejesh lall

The spectral information in the infrared image is incorporated by adding the feature maps over several layers in the encoder part of the fusion structure, which makes inference on both the visual and infrared images separately.

Compressive sensing based privacy for fall detection

no code implementations10 Jan 2020 Ronak Gupta, Prashant Anand, Santanu Chaudhury, Brejesh lall, Sanjay Singh

Fall detection holds immense importance in the field of healthcare, where timely detection allows for instant medical assistance.

Compressive Sensing

Aerial multi-object tracking by detection using deep association networks

no code implementations4 Sep 2019 Ajit Jadhav, Prerana Mukherjee, Vinay Kaushik, Brejesh lall

Using the RetinaNet model as our base, we modify the anchor scales to better handle the detection of dense distribution and small size of the objects.

Multi-Object Tracking object-detection +1

Learning Activation Functions: A new paradigm for understanding Neural Networks

2 code implementations23 Jun 2019 Mohit Goyal, Rajan Goyal, Brejesh lall

Since the optimization of SLNNs is still a challenge, we show that using SLAF along with standard activations (like ReLU) can provide performance improvements with only a small increase in number of parameters.

Few Shot Speaker Recognition using Deep Neural Networks

no code implementations17 Apr 2019 Prashant Anand, Ajeet Kumar Singh, Siddharth Srivastava, Brejesh lall

The recent advances in deep learning are mostly driven by availability of large amount of training data.

Few-Shot Learning Speaker Recognition

VayuAnukulani: Adaptive Memory Networks for Air Pollution Forecasting

no code implementations8 Apr 2019 Divyam Madaan, Radhika Dua, Prerana Mukherjee, Brejesh lall

Extensive experiments on data sources obtained in Delhi demonstrate that the proposed adaptive attention based Bidirectional LSTM Network outperforms several baselines for classification and regression models.

DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks

no code implementations2 Apr 2019 Prerana Mukherjee, Manoj Sharma, Megh Makwana, Ajay Pratap Singh, Avinash Upadhyay, Akkshita Trivedi, Brejesh lall, Santanu Chaudhury

In this paper, we present a novel end-to-end coupled Denoising based Saliency Prediction with Generative Adversarial Network (DSAL-GAN) framework to address the problem of salient object detection in noisy images.

Denoising object-detection +3

Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification

no code implementations2 Apr 2019 Shiva Azimi, Brejesh lall, Tapan K. Gandhi

Plant Phenomics based on imaging based techniques can be used to monitor the health and the diseases of plants and crops.

General Classification

DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds

no code implementations27 Mar 2019 Siddharth Srivastava, Brejesh lall

The method constitutes a deep network for learning permutation invariant representation of 3D points.

Metric Learning

Fast Hierarchical Depth Map Computation from Stereo

no code implementations28 Jan 2019 Vinay Kaushik, Brejesh lall

Disparity by Block Matching stereo is usually used in applications with limited computational power in order to get depth estimates.

Nrityantar: Pose oblivious Indian classical dance sequence classification system

no code implementations13 Dec 2018 Vinay Kaushik, Prerana Mukherjee, Brejesh lall

To circumvent this problem, we construct a pose-oblivious shape signature which is fed to a sequence learning framework.

Action Recognition Classification +3

IIT Delhi at SemEval-2018 Task 1 : Emotion Intensity Prediction

no code implementations SEMEVAL 2018 Bhaskar Kotakonda, Prashanth Gowda, Brejesh lall

This paper discusses the experiments performed for predicting the emotion intensity in tweets using a generalized supervised learning approach.

Emotion Recognition POS +1

Object cosegmentation using deep Siamese network

no code implementations7 Mar 2018 Prerana Mukherjee, Brejesh lall, Snehith Lattupally

Object cosegmentation addresses the problem of discovering similar objects from multiple images and segmenting them as foreground simultaneously.

Object Proposal Generation Semantic Segmentation

Enhanced Characterness for Text Detection in the Wild

no code implementations4 Dec 2017 Aarushi Agrawal, Prerana Mukherjee, Siddharth Srivastava, Brejesh lall

We show that a simple combination of characterness cues help in rejecting the non text regions.

Text Spotting

Drought Stress Classification using 3D Plant Models

no code implementations21 Sep 2017 Siddharth Srivastava, Swati Bhugra, Brejesh lall, Santanu Chaudhury

Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner.

3D Reconstruction Classification +1

3D Binary Signatures

no code implementations26 Aug 2017 Siddharth Srivastava, Brejesh lall

3DBS describes keypoints from point clouds with a binary vector resulting in extremely fast matching.

SalProp: Salient object proposals via aggregated edge cues

no code implementations14 Jun 2017 Prerana Mukherjee, Brejesh lall, Sarvaswa Tandon

In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context.

Classification Edge Classification +3

Large Scale Novel Object Discovery in 3D

no code implementations22 Jan 2017 Siddharth Srivastava, Gaurav Sharma, Brejesh lall

We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery.

Object Discovery

Ranking academic institutions on potential paper acceptance in upcoming conferences

no code implementations10 Oct 2016 Jobin Wilson, Ram Mohan, Muhammad Arif, Santanu Chaudhury, Brejesh lall

The crux of the problem in KDD Cup 2016 involves developing data mining techniques to rank research institutions based on publications.

Benchmarking KAZE and MCM for Multiclass Classification

no code implementations20 May 2015 Siddharth Srivastava, Prerana Mukherjee, Brejesh lall

In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features.

Benchmarking Classification +1

Improving Collaborative Filtering based Recommenders using Topic Modelling

no code implementations25 Feb 2014 Jobin Wilson, Santanu Chaudhury, Brejesh lall, Prateek Kapadia

While computing similarity between users, we make use of a combined similarity measure involving rating overlap as well as similarity in the latent topic space.

Collaborative Filtering

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