ICVGIP 2023
IIT Ropar | 15th-17th December 2023
Program
Note 1: The main conference will be held in the Auditorium, unless specified otherwise.
Note 2: Lunch and Dinner will be held in the Auditorium
Note 3: Coffee and Snacks wil be offered in S.Ramanujan Block on 15th Dec, and in Auditorium on 16th and 17th December.
| Time | 15th December | ||
|---|---|---|---|
| 9.00-10.30 | Tutorial: Unlocking Creativity: A Tutorial on Generative Image-AI (CS1, S.Ramanujan Block) |
Tutorial: Framework for Federated Learning with Diversified Edge Resource Allocation (CS2, S.Ramanujan Block) |
Workshop: Document Analysis and Recognition (Seminar Hall, S.Ramanujan Block) |
| 10.30-11.00 | Coffee Break | ||
| 11.00-12.30 | Tutorial: Unlocking Creativity: A Tutorial on Generative Image-AI (CS1, S.Ramanujan Block) |
Tutorial: Framework for Federated Learning with Diversified Edge Resource Allocation (CS2, S.Ramanujan Block) |
Workshop: Document Analysis and Recognition (Seminar Hall, S.Ramanujan Block) |
| 12.30-14.00 | Lunch | ||
| 14.00-15.30 | Tutorial: Exploring Video Understanding through Language (CS1, S.Ramanujan Block) |
Doctoral Consortium (Seminar Hall, S.Ramanujan Block) |
|
| 15.30-16.00 | Coffee Break | ||
| 16.00-17.30 | Tutorial: Exploring Video Understanding through Language (CS1, S.Ramanujan Block) |
Doctoral Consortium (Seminar Hall, S.Ramanujan Block) |
|
| 17.30-18.30 | |||
| 18.30-20.30 | Dinner | ||
| Time | 16th December | 17th December |
|---|---|---|
| 9.00-10.00 | Inauguration | Industry talks |
| 10.00-11.00 | Keynote 1 | Keynote 2 |
| 11.00-11.30 | Coffee Break + Posters | Coffee Break + Posters |
| 11.30-13.00 | Oral Session 1 | Oral Session 3 |
| 13.00-14.00 | Lunch + Posters | Lunch + Posters |
| 14.00-15.00 | Spotlight | Vision India |
| 15.00-15.30 | Coffee Break + Posters | Coffee Break + Posters |
| 15.30-17.00 | Oral Session 2 | Results and Closing Remarks |
| 17.00-17.30 | GBM | |
| 17.30-18.30 | ||
| 18.30-20.30 | Gala Dinner | Dinner |
Oral Sessions
Note: All papers accepted for ICVGIP 2023 Conference are either Oral or Spotlight. They also have to be presented as poster. If your paper has been accepted and is not in the list below, this means it is part of the Spotlight, and is scheduled as per the program above. Based on this, kindly follow the guidelines as mentioned on the Instructions page
For detailed information on oral papers, visit here.
| Oral Session 1 | Oral Session 2 | Oral Session 3 |
|---|---|---|
| ADDMDNet: A Slice Ranking based Approach for Alzheimer’s Disease Detection from Multi-modal Data | Single View Blind Homography Estimation (BHE) for an Inclined Textured Planar Surface: Overcoming the Inverse and Ill-Posed Challenge! | Aggregated Co-attention based Visual Question Answering |
| ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition | Mandala as computational art: Vectorization and beyond | Knowledge Distillation with Ensemble Calibration |
| MoMSGAN: Mode Collapse based Degradation Agnostic Multi-Scale Super-Resolution of Medical Images | Degradation Aware Multi-Scale Approach to No Reference Image Quality Assessment | Dense captioning for Text-Image ReID |
| Unique Identity Generation with Global Features from Multimodal Biometric Data | Dual Stage Semantic Information Based Generative Adversarial Network For Image Super-Resolution | Indian Regional Sign Language Recognition |
| Towards the Influence of Eyeglasses on the Cross-spectral Periocular Verification: Does Eyeglass Detection Improve Verification Performance? | A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network | Automatic assessment of communication skill in real-world job interviews: A comparative study using deep learning and domain adaptation. |
| InMDb: Indian Movie Database for Emotion Analysis | Self-Supervised 3D Mesh Object Retrieval | Designing a Sequential Hybrid BCI Speller on Fusion of Motor Imagery and Steady-State Visually Evoked Potentials EEG Data |
| Global Space Modelling Of Biological Processes With Cross-sectional Data | MCDNet: Multi Context Dense Network for multi-frame super resolution of satellite images | C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing |
Spotlight
List of accepted papers for Spotlight are listed below.
For detailed information on spotlight papers, visit here.
| List of Papers for Spotlight | ||
|---|---|---|
| MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image | Improved Discrepancy based Domain Adaptation Network using combined loss functions and Feature transformations | S-BAN: Secure Biometric Authentication using Noise |
| TransDocUNet: A Transformer-based UNet Architecture for Effective Document Image Binarization | STTGC-Net: Spatial-Temporal Transformer with Graph Convolution for Skeleton-Based Action Recognition | An Efficient Motor Imagery Classification Framework using Sparse Brain Connectivity and Class-consistent Dictionary Learning from Electroencephalogram Signals |
| Fine-grain Cluster Estimation of Land Cover Classes using Landsat 8 Multispectral images | Advancing Fingerprint Recognition Quality Assessment: Introducing the FRBQ Metric for Enhanced Fingerprint Recognition | Hybrid SNN-based Privacy-Preserving Fall Detection using Neuromorphic Sensors |
| A Novel Framework for Robust Fingerprint Representations using Deep Convolution Network with Attention Mechanism | TLR-Net :Transfer Learning in Residual U-Net for Enhancing Skin Lesion Segmentation | An Algorithm to Calculate Retinal Vessel Diameter in Fundus Images |
| Examining the Influence of Personality and Multimodal Behavior on Hireability Impressions | What Sweet it is?: SweetNet: A comprehensive Classification of Milk Sweets | CDA-Net: Computer Vision based Automatic Car Damage Analysis |
| Optimizing Knowledge Transfer in Sequential Models: Leveraging Residual Connections in Flow Transfer Learning for Lung Cancer Classification | An Efficient Model for Non-Distal Presentation Attack Detection | S-VQA: Sentence-Based Visual Question Answering |
Poster Sessions
Poster sessions are tentatively divided as listed below.
| 16th December | 17th December |
|---|---|
| ADDMDNet: A Slice Ranking based Approach for Alzheimer’s Disease Detection from Multi-modal Data | Single View Blind Homography Estimation (BHE) for an Inclined Textured Planar Surface: Overcoming the Inverse and Ill-Posed Challenge! |
| MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image | Improved Discrepancy based Domain Adaptation Network using combined loss functions and Feature transformations |
| ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition | Automatic assessment of communication skill in real-world job interviews: A comparative study using deep learning and domain adaptation. |
| S-BAN: Secure Biometric Authentication using Noise | TransDocUNet: A Transformer-based UNet Architecture for Effective Document Image Binarization |
| STTGC-Net: Spatial-Temporal Transformer with Graph Convolution for Skeleton-Based Action Recognition | An Efficient Motor Imagery Classification Framework using Sparse Brain Connectivity and Class-consistent Dictionary Learning from Electroencephalogram Signals |
| Mandala as computational art: Vectorization and beyond | MoMSGAN: Mode Collapse based Degradation Agnostic Multi-Scale Super-Resolution of Medical Images |
| Fine-grain Cluster Estimation of Land Cover Classes using Landsat 8 Multispectral images | Knowledge Distillation with Ensemble Calibration |
| Degradation Aware Multi-Scale Approach to No Reference Image Quality Assessment | Dense captioning for Text-Image ReID |
| Dual Stage Semantic Information Based Generative Adversarial Network For Image Super-Resolution | Hybrid SNN-based Privacy-Preserving Fall Detection using Neuromorphic Sensors |
| Advancing Fingerprint Recognition Quality Assessment: Introducing the FRBQ Metric for Enhanced Fingerprint Recognition | Unique Identity Generation with Global Features from Multimodal Biometric Data |
| A Novel Framework for Robust Fingerprint Representations using Deep Convolution Network with Attention Mechanism | Towards the Influence of Eyeglasses on the Cross-spectral Periocular Verification: Does Eyeglass Detection Improve Verification Performance? |
| TLR-Net :Transfer Learning in Residual U-Net for Enhancing Skin Lesion Segmentation | Examining the Influence of Personality and Multimodal Behavior on Hireability Impressions |
| An Algorithm to Calculate Retinal Vessel Diameter in Fundus Images | Automatic Detection of Virus Infection Patterns in Images Using Switchable Convolutions |
| A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network | Indian Regional Sign Language Recognition |
| Self-Supervised 3D Mesh Object Retrieval | CDA-Net: Computer Vision based Automatic Car Damage Analysis |
| What Sweet it is?: SweetNet: A comprehensive Classification of Milk Sweets | MCDNet: Multi Context Dense Network for multi-frame super resolution of satellite images |
| Optimizing Knowledge Transfer in Sequential Models: Leveraging Residual Connections in Flow Transfer Learning for Lung Cancer Classification | Designing a Sequential Hybrid BCI Speller on Fusion of Motor Imagery and Steady-State Visually Evoked Potentials EEG Data |
| InMDb: Indian Movie Database for Emotion Analysis | C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing |
| Global Space Modelling Of Biological Processes With Cross-sectional Data | S-VQA: Sentence-Based Visual Question Answering |
| An Efficient Model for Non-Distal Presentation Attack Detection | Accurate Classification and Interpretation of Osteoarthritis Conditions in X-ray and Thermal Images |
| Autotuned Classification Based on Knowledge Transferred from Self-supervised Models | Automated Approach for Pneumonia Detection using Chest X-Ray Images |
| Optimal Graph Compression for Efficient Graph ML | Accurate Brain Tumor Segmentation And Classification from MRI Images Using Novel Deep Learning Methods |
| Interpretation and Clinical Validation of Fetal Stress Condition using Cardiotocograpy Signals and Biophysical Profile Images | Automated Retinal Vasculature Analysis for Early Disease Detection and Treatment |
| Aggregated Co-attention based Visual Question Answering |