Vinay P. Namboodiri

Latest

FACTS: Facial Animation Creation using the Transfer of Styles
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
Rectification-Based Knowledge Retention for Task Incremental Learning
Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data
VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
Attentive Contractive Flow with Lipschitz Constrained Self-Attention
Audio-Visual Face Reenactment
FaceOff: A Video-to-Video Face Swapping System
READ Avatars: Realistic Emotion-controllable Audio Driven Avatars
Streaming LifeLong Learning With Any-Time Inference
Towards Accurate Lip-to-Speech Synthesis in-the-Wild
Towards Generating Ultra-High Resolution Talking-Face Videos with Lip synchronization
Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale
Auto QA: The Question Is Not Only What, but Also Where
Compressing Video Calls using Synthetic Talking Heads
Context extraction module for deep convolutional neural networks
Explanation vs. attention: A two-player game to obtain attention for VQA and visual dialog
Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation
First Workshop on Content Understanding and Generation for E-commerce
Generalized Keyword Spotting using ASR embeddings
Gradient Based Activations for Accurate Bias-Free Learning
INR-V: A Continuous Representation Space for Video-based Generative Tasks
Learning Speaker-specific Lip-to-Speech Generation
Learning to Predict Speech in Silent Videos Via Audiovisual Analogy
Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
VQuAD: Video Question Answering Diagnostic Dataset
Audio-Visual Speech Super-Resolution
AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings
Collaborative Learning to Generate Audio-Video Jointly
Deep Knowledge Distillation using Trainable Dense Attention
Do not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting
Domain Impression: A Source Data Free Domain Adaptation Method
Improving Few-Shot Learning using Composite Rotation based Auxiliary Task
Intelligent video editing: incorporating modern talking face generation algorithms in a video editor
Knowledge Consolidation based Class Incremental Online Learning with Limited Data
More Parameters? No Thanks!
Multimodal Humor Dataset: Predicting Laughter tracks for Sitcoms
MUMC: Minimizing uncertainty of mixture of cues
Personalized One-Shot Lipreading for an ALS Patient
Probabilistic framework for solving visual dialog
Rectification-Based Knowledge Retention for Continual Learning
Revisiting Low Resource Status of Indian Languages in Machine Translation
RNNP: A Robust Few-Shot Learning Approach
Self Supervision for Attention Networks
SHAD3S: A model to Sketch, Shade and Shadow
Speech Prediction in Silent Videos Using Variational Autoencoders
Towards Automatic Speech to Sign Language Generation
Translating sign language videos to talking faces
Uncertainty Class Activation Map (U-CAM) Using Gradient Certainty Method
Visual Speech Enhancement Without A Real Visual Stream
A \"Network Pruning Network\" Approach to Deep Model Compression
A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild
A Multilingual Parallel Corpora Collection Effort for Indian Languages
Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning
Accuracy Booster: Performance Boosting using Feature Map Re-calibration
Bridged Variational Autoencoders for Joint Modeling of Images and Attributes
Can I teach a robot to replicate a line art
Cooperative Initialization based Deep Neural Network Training
CPWC: Contextual Point Wise Convolution for Object Recognition
Deep Bayesian Network for Visual Question Generation
Determinantal Point Process as an alternative to NMS
EDS pooling layer
Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA
Exploring Pair-Wise NMT for Indian Languages
FALF ConvNets: Fatuous auxiliary loss based filter-pruning for efficient deep CNNs
GIFSL - grafting based improved few-shot learning
Jointly Trained Image and Video Generation using Residual Vectors
Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing
Leveraging Filter Correlations for Deep Model Compression
Minimizing Supervision in Multi-label Categorization
Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution
PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation
Robust Explanations for Visual Question Answering
SD-MTCNN: Self-Distilled Multi-Task CNN
SkipConv: Skip Convolution for Computationally Efficient Deep CNNs
STEER : Simple Temporal Regularization For Neural ODE
Stochastic Talking Face Generation Using Latent Distribution Matching
Visually Precise Query
Attending to Discriminative Certainty for Domain Adaptation
Cross-language Speech Dependent Lip-synchronization
Curriculum based Dropout Discriminator for Domain Adaptation
CVIT's submissions to WAT-2019
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
Looking back at Labels: A Class based Domain Adaptation Technique
Multi-Layer Pruning Framework for Compressing Single Shot MultiBox Detector
Play and Prune: Adaptive Filter Pruning for Deep Model Compression
Spotting words in silent speech videos: a retrieval-based approach
Stability Based Filter Pruning for Accelerating Deep CNNs
Towards Automatic Face-to-Face Translation
U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps
Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal
CVIT-MT Systems for WAT-2018
Deep active learning for object detection
Deep Domain Adaptation in Action Space
Differential Attention for Visual Question Answering
Eclectic domain mixing for effective adaptation in action spaces
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
Monoaural Audio Source Separation Using Variational Autoencoders
Multi-Agent Diverse Generative Adversarial Networks
Multimodal Differential Network for Visual Question Generation
No Modes Left Behind: Capturing the Data Distribution Effectively Using GANs
U-DADA: Unsupervised Deep Action Domain Adaptation
Unsupervised domain adaptation of deep object detectors
Word Spotting in Silent Lip Videos
Compact Environment-Invariant Codes for Robust Visual Place Recognition
Contextual RNN-GANs for Abstract Reasoning Diagram Generation
Reactive Displays for Virtual Reality
Visual Odometry Based Omni-directional Hyperlapse
Deep Attributes for One-Shot Face Recognition
Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes
Adapting RANSAC SVM to Detect Outliers for Robust Classification
Subspace Alignment Based Domain Adaptation for RCNN Detector
Where is my friend? - Person identification in social networks
Object Classification with Adaptable Regions
Nonuniform image patch exemplars for low level vision
Classification with Global, Local and Shared Features
Action recognition: A region based approach
Object and Action Classification with Latent Variables
Systematic evaluation of super-resolution using classification
Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera
Regularized depth from defocus
Image Restoration using Geometrically Stabilized Reverse Heat Equation
On defocus, diffusion and depth estimation
Retrieval of images of man-made structures based on projective invariance
Shape Recovery Using Stochastic Heat Flow
Super-Resolution Using Sub-band Constrained Total Variation
Improved Kernel-Based Object Tracking Under Occluded Scenarios
Shock Filters Based on Implicit Cluster Separation
Image retrieval based on projective invariance
Use of Linear Diffusion in Depth Estimation Based on Defocus Cue