No abstract available.
ADDMDNet: A Slice Ranking based Approach for Alzheimer’s Disease Detection from Multi-modal Data
Alzheimer’s Disease (AD) is a type of progressive brain disorder that gradually diminishes cognitive abilities, memory, and even the ability to carry out simple tasks. In this paper, a slice-ranking based technique - ADDMDNet, to differentiate between ...
Single View Homography Estimation for an Inclined Textured Planar Surface: Overcoming the Inverse and Ill-Posed Challenge!
Homography estimation is a crucial step in many computer vision problems involving the planar transformation of an image from one view to another. Generally, from two image views of a scene with a planar patch, one can compute the homography matrix (H) ...
MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image
In order to effectively interact with its environment, an agent must possess the ability to comprehend the ’what’ and the ’where.’ Two vision-based approaches, namely semantic segmentation and depth estimation, can be employed to provide this ...
Improved Discrepancy based Domain Adaptation Network using combined loss functions and Feature transformations✱
Domain shifts are a common problem in computer vision. As a result, a classifier trained on a source domain cannot perform well on a target domain. Due to this, a source classifier trained to differentiate based on a specific distribution cannot ...
Automatic assessment of communication skill in real-world job interviews: A comparative study using deep learning and domain adaptation.
With the increasing use of video-based job interviews, there is a growing demand for automated tools that can accurately evaluate the interviewee’s performance. While hiring decisions have traditionally been made based on a combination of a candidate’s ...
ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition
Video Action Recognition (VAR) is a challenging task due to its inherent complexities. Though different approaches have been explored in the literature, designing a unified framework to recognize a large number of human actions is still a challenging ...
S-BAN: Secure Biometric Authentication using Noise
Biometric signal consisting of irrelevant or non-distinctive features can contain useful correlational properties that privacy-preserving verification schemes can exploit. While an efficient protocol for iris verification using noise has been presented [...
TransDocUNet: A Transformer-based UNet Architecture for Degraded Document Image Binarization
The enhancement of historical document images is critical for improving the quality and legibility of scanned or captured document images. Convolutional-based techniques previously generated competitive results for document image binarization, however, ...
STTGC-Net: Spatial-Temporal Transformer with Graph Convolution for Skeleton-Based Action Recognition
Skeleton data plays an important role in human action recognition due to the compact and distinct information of human poses provided by the skeleton data. Skeleton-based action recognition is gaining interest due to the availability of Kinect cameras ...
An Efficient Motor Imagery Classification Framework using Sparse Brain Connectivity and Class-consistent Dictionary Learning from Electroencephalogram Signals
Identifying patterns in high-dimensional and noisy neuro-imaging data such as Electroencephalogram (EEG) has always been challenging. This fact hampers the performance of the real-time Brain-Computer Interfaces (BCI) controlled by EEG recordings of ...
Mandala as computational art: Vectorization and beyond
This paper introduces a novel technique of computational art with mandala—an iconic heritage of Indian folk art. Its novelty lies in several fundamental steps. The first one is fixing the asymmetries and the imperfections in a hand-drawn piece of art ...
Fine-grain Cluster Estimation of Land Cover Classes using Landsat 8 Multispectral images
Earth observation satellites provide us with ample amount of raw data for land cover analysis. However, annotating these data is a cumbersome process, subjected to human error which compel us to shift from supervised to unsupervised techniques. Although ...
Degradation Aware Multi-Scale Approach to No Reference Image Quality Assessment
With the advent of smartphones and social media, images have become a popular medium for sharing information. As a result understanding the perceived quality of images has gained importance. In the recent years No-Reference Image Quality Assessment (NR-...
MoMSGAN: Mode Collapse based Degradation Agnostic Multi-Scale Super-Resolution of Medical Images
- Samiran Dey,
- Tapabrata Chakraborti,
- Partha Basuchowdhuri,
- Debasis Mitra,
- Robin Augustine,
- Sanjoy Kumar Saha
Existing super-resolution (SR) models require separate training for different scales of SR because of the fixed upsampling levels in their architecture. We propose a novel one-time training approach for multi-scale SR models with a fixed upsampling unit,...
Dual Stage Semantic Information Based Generative Adversarial Network For Image Super-Resolution✱
Deep learning methods for the super-resolution problem are showing great performance compared to other traditional techniques. However, these methods are unable to learn complex spatial structures and high frequency details; which leads to over-smooth ...
Knowledge Distillation with Ensemble Calibration
Knowledge Distillation is a transfer learning and compression technique that aims to transfer hidden knowledge from a teacher model to a student model. However, this transfer often leads to poor calibration in the student model. This can be problematic ...
Dense captioning for Text-Image ReID
Text-to-Image (T2I) ReID has attracted a lot of attention in the recent past. CUHK-PEDES, RSTPReid and ICFG-PEDES are the three available benchmarks to evaluate T2I ReID methods. RSTPReid and ICFG-PEDES comprise of identities from MSMT17 but due to ...
Advancing Fingerprint Recognition Quality Assessment: Introducing the FRBQ Metric for Enhanced Fingerprint Recognition
In the field of biometric security, the quality assessment of fingerprint images is paramount for boosting the accuracy of fingerprint recognition systems. These systems are fundamental for the secure and efficient authentication and identification of ...
Hybrid SNN-based Privacy-Preserving Fall Detection using Neuromorphic Sensors
Indoor surveillance is crucial for ensuring the safety and security of occupants within the premises. Only those who are ill or elderly tend to spend the most time at home. The use of indoor surveillance to continuously monitor these people’s security ...
A Novel Framework for Robust Fingerprint Representations using Deep Convolution Network with Attention Mechanism
Fingerprint recognition systems are highly dependent on the quality and accuracy of the fingerprint representation. Traditional fingerprint recognition algorithms often employ handcrafted features designed manually based on domain knowledge and ...
TLR-Net :Transfer Learning in Residual U-Net for Enhancing Skin Lesion Segmentation
Skin lesion semantic segmentation is a critical task in dermatology, aiding early diagnosis and treatment of skin disorders, including melanoma and other forms of skin cancer. Challenge datasets in skin lesion segmentation play a pivotal role in ...
An Algorithm to Calculate Retinal Vessel Diameter in Fundus Images
Retinal blood vessels are the arteries and veins that supply blood to the human eye. Fundus images obtained through a fundus camera capture retinal information like, the macula, optic disc, cup, fovea, retinal blood vessels, and abnormalities. The ...
Unique Identity Generation with Global Features from Multimodal Biometric Data
The patterns in biometric data, such as fingerprints, iris, etc., are random and distinct from one individual to another, making them ideal for generating unique identities suitable for many applications. This work proposes creating users’ unique ...
A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network
A neuromorphic camera is an image sensor that emulates the human eyes capturing only changes in local brightness levels. They are widely known as event cameras, silicon retinas or dynamic vision sensors (DVS). DVS records asynchronous per-pixel ...
Towards the Influence of Eyeglasses on the Cross-spectral Periocular Verification: Does Eyeglass Detection Improve Verification Performance?
The influence of eyeglasses has significantly impacted the performance of ocular biometrics in recent times, and the problem of detecting eyeglasses is crucial for ensuring stable and reliable ocular biometric system performance. However, despite the ...
Self-Supervised 3D Mesh Object Retrieval
Digital representations of 3D objects are increasingly being used for engineering, entertainment, education, etc. Efforts to search and retrieve digital 3D models from a collection have not attracted sufficient attention, unlike digital representations ...
Examining the Influence of Personality and Multimodal Behavior on Hireability Impressions
While personality traits have been traditionally modeled as behavioral constructs, we novelly posit job hireability as a personality construct. To this end, we examine correlates among personality and hireability measures on the First Impressions ...
Aggregated Co-attention based Visual Question Answering
Recent developments in the field of Visual Question Answering (VQA) have witnessed promising improvements in performance through contributions in attention based networks. Most such approaches have focused on unidirectional attention that leverage over ...
Indian Regional Sign Language Recognition
Sign Language is a medium of communication in the Deaf and Hard of Hearing community (DHH community). According to WHO, there are approximately 63 million people in India, including 3.3 million from the state of Karnataka, with 0.3 million children ...
What Sweet it is?: SweetNet: A comprehensive Classification of Milk Sweets
Developing technology to classify milk sweets aids in preserving culinary customs. It enables the creation of a mobile app for younger generations, assists those with dietary preferences, and improves sorting in the sweet industry. However, accurate ...
Index Terms
- Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing
Recommendations
Acceptance Rates
Year | Submitted | Accepted | Rate |
---|---|---|---|
ICVGIP '16 | 286 | 95 | 33% |
Overall | 286 | 95 | 33% |