Search Results for author:
Found 23 papers, 8 papers with code
Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
In this work, we introduce VistaLLM, a powerful visual system that addresses coarse- and fine-grained VL tasks over single and multiple input images using a unified framework.
APoLLo: Unified Adapter and Prompt Learning for Vision Language Models
Our method is designed to substantially improve the generalization capabilities of VLP models when they are fine-tuned in a few-shot setting.
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks.
BeAts: Bengali Speech Acts Recognition using Multimodal Attention Fusion
Spoken languages often utilise intonation, rhythm, intensity, and structure, to communicate intention, which can be interpreted differently depending on the rhythm of speech of their utterance.
An Evaluation of Non-Contrastive Self-Supervised Learning for Federated Medical Image Analysis
In this paper, we seek to tackle these concerns head-on and systematically explore the applicability of non-contrastive self-supervised learning (SSL) algorithms under federated learning (FL) simulations for medical image analysis.
Exploring Self-Supervised Representation Learning For Low-Resource Medical Image Analysis
The success of self-supervised learning (SSL) has mostly been attributed to the availability of unlabeled yet large-scale datasets.
IDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image Segmentation
To this end, we extend the concept of metric learning to the segmentation task, using a dense (dis)similarity learning for pre-training a deep encoder network, and employing a semi-supervised paradigm to fine-tune for the downstream task.
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.
Deciphering Environmental Air Pollution with Large Scale City Data
Air pollution poses a serious threat to sustainable environmental conditions in the 21st century.
SERF: Towards better training of deep neural networks using log-Softplus ERror activation Function
Activation functions play a pivotal role in determining the training dynamics and neural network performance.
GraphVICRegHSIC: Towards improved self-supervised representation learning for graphs with a hyrbid loss function
Self-supervised learning and pre-training strategieshave developed over the last few years especiallyfor Convolutional Neural Networks (CNNs).
A Fractal Approach to Characterize Emotions in Audio and Visual Domain: A Study on Cross-Modal Interaction
It is already known that both auditory and visual stimulus is able to convey emotions in human mind to different extent.
Language Independent Emotion Quantification using Non linear Modelling of Speech
In this work we have modelled our articulation system using nonlinear multifractal analysis.
Neural Network architectures to classify emotions in Indian Classical Music
Music is often considered as the language of emotions.
On the stability of equilibria of the physiologically-informed dynamic causal model
Experimental manipulations perturb the neuronal activity.
Lookahead optimizer improves the performance of Convolutional Autoencoders for reconstruction of natural images
Recently, an optimizer was introduced which is known as lookahead optimizer which significantly enhances the performances of Adam as well as SGD.
Speaker Recognition in Bengali Language from Nonlinear Features
The study of Bengali speech recognition and speaker identification is scarce in the literature.
Hybrid Style Siamese Network: Incorporating style loss in complementary apparels retrieval
These low level style features are captured to a large extent in techniques used in neural style transfer.
Ranked #1 on
Complimentary Image Retrieval
on iMaterialist
Image Registration Techniques: A Survey
Image Registration is the process of aligning two or more images of the same scene with reference to a particular image.
An Adaptive Genetic Algorithm for Solving N-Queens Problem
In this paper a Metaheuristic approach for solving the N-Queens Problem is introduced to find the best possible solution in a reasonable amount of time.
Vector Quantization using the Improved Differential Evolution Algorithm for Image Compression
LindeBuzoGray, LBG is a traditional method of generation of VQ Codebook which results in lower PSNR value.
A Type II Fuzzy Entropy Based Multi-Level Image Thresholding Using Adaptive Plant Propagation Algorithm
Thresholding based Image Segmentation using fuzzy entropy combined with intelligent optimization approaches are commonly used direct methods to properly identify the thresholds so that they can be used to segment an Image accurately.
Adaptive Plant Propagation Algorithm for Solving Economic Load Dispatch Problem
Optimization problems in design engineering are complex by nature, often because of the involvement of critical objective functions accompanied by a number of rigid constraints associated with the products involved.
