Publications | MAGIc@Bath Research Group

FACTS: Facial Animation Creation using the Transfer of Styles

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Rectification-Based Knowledge Retention for Task Incremental Learning

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference

Mon, 01 Jan 2024 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Attentive Contractive Flow with Lipschitz Constrained Self-Attention

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Audio-Visual Face Reenactment

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

FaceOff: A Video-to-Video Face Swapping System

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

READ Avatars: Realistic Emotion-controllable Audio Driven Avatars

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Streaming LifeLong Learning With Any-Time Inference

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Accurate Lip-to-Speech Synthesis in-the-Wild

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Generating Ultra-High Resolution Talking-Face Videos with Lip synchronization

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale

Sun, 01 Jan 2023 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Auto QA: The Question Is Not Only What, but Also Where

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Compressing Video Calls using Synthetic Talking Heads

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Context extraction module for deep convolutional neural networks

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Explanation vs. attention: A two-player game to obtain attention for VQA and visual dialog

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

First Workshop on Content Understanding and Generation for E-commerce

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Generalized Keyword Spotting using ASR embeddings

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Gradient Based Activations for Accurate Bias-Free Learning

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

INR-V: A Continuous Representation Space for Video-based Generative Tasks

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Learning Speaker-specific Lip-to-Speech Generation

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Learning to Predict Speech in Silent Videos Via Audiovisual Analogy

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

VQuAD: Video Question Answering Diagnostic Dataset

Sat, 01 Jan 2022 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Audio-Visual Speech Super-Resolution

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Collaborative Learning to Generate Audio-Video Jointly

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Deep Knowledge Distillation using Trainable Dense Attention

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Do not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Domain Impression: A Source Data Free Domain Adaptation Method

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Improving Few-Shot Learning using Composite Rotation based Auxiliary Task

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Intelligent video editing: incorporating modern talking face generation algorithms in a video editor

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Knowledge Consolidation based Class Incremental Online Learning with Limited Data

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

More Parameters? No Thanks!

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Multimodal Humor Dataset: Predicting Laughter tracks for Sitcoms

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

MUMC: Minimizing uncertainty of mixture of cues

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Personalized One-Shot Lipreading for an ALS Patient

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Probabilistic framework for solving visual dialog

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Rectification-Based Knowledge Retention for Continual Learning

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Revisiting Low Resource Status of Indian Languages in Machine Translation

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

RNNP: A Robust Few-Shot Learning Approach

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Self Supervision for Attention Networks

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SHAD3S: A model to Sketch, Shade and Shadow

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Speech Prediction in Silent Videos Using Variational Autoencoders

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Automatic Speech to Sign Language Generation

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Translating sign language videos to talking faces

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Uncertainty Class Activation Map (U-CAM) Using Gradient Certainty Method

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Visual Speech Enhancement Without A Real Visual Stream

Fri, 01 Jan 2021 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A \"Network Pruning Network\" Approach to Deep Model Compression

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

A Multilingual Parallel Corpora Collection Effort for Indian Languages

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Acceleration of Deep Convolutional Neural Networks Using Adaptive Filter Pruning

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Accuracy Booster: Performance Boosting using Feature Map Re-calibration

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Bridged Variational Autoencoders for Joint Modeling of Images and Attributes

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Can I teach a robot to replicate a line art

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Cooperative Initialization based Deep Neural Network Training

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

CPWC: Contextual Point Wise Convolution for Object Recognition

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Deep Bayesian Network for Visual Question Generation

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Determinantal Point Process as an alternative to NMS

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

EDS pooling layer

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Exploring Pair-Wise NMT for Indian Languages

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

FALF ConvNets: Fatuous auxiliary loss based filter-pruning for efficient deep CNNs

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

GIFSL - grafting based improved few-shot learning

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Jointly Trained Image and Video Generation using Residual Vectors

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Leveraging Filter Correlations for Deep Model Compression

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Minimizing Supervision in Multi-label Categorization

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Robust Explanations for Visual Question Answering

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SD-MTCNN: Self-Distilled Multi-Task CNN

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

SkipConv: Skip Convolution for Computationally Efficient Deep CNNs

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

STEER : Simple Temporal Regularization For Neural ODE

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Stochastic Talking Face Generation Using Latent Distribution Matching

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Visually Precise Query

Wed, 01 Jan 2020 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Attending to Discriminative Certainty for Domain Adaptation

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Cross-language Speech Dependent Lip-synchronization

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Curriculum based Dropout Discriminator for Domain Adaptation

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

CVIT's submissions to WAT-2019

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Looking back at Labels: A Class based Domain Adaptation Technique

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Multi-Layer Pruning Framework for Compressing Single Shot MultiBox Detector

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Play and Prune: Adaptive Filter Pruning for Deep Model Compression

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Spotting words in silent speech videos: a retrieval-based approach

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Stability Based Filter Pruning for Accelerating Deep CNNs

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Towards Automatic Face-to-Face Translation

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal

Tue, 01 Jan 2019 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

CVIT-MT Systems for WAT-2018

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Deep active learning for object detection

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Deep Domain Adaptation in Action Space

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Differential Attention for Visual Question Answering

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Eclectic domain mixing for effective adaptation in action spaces

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Monoaural Audio Source Separation Using Variational Autoencoders

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Multi-Agent Diverse Generative Adversarial Networks

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Multimodal Differential Network for Visual Question Generation

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

No Modes Left Behind: Capturing the Data Distribution Effectively Using GANs

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

U-DADA: Unsupervised Deep Action Domain Adaptation

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Unsupervised domain adaptation of deep object detectors

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Word Spotting in Silent Lip Videos

Mon, 01 Jan 2018 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Compact Environment-Invariant Codes for Robust Visual Place Recognition

Sun, 01 Jan 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Contextual RNN-GANs for Abstract Reasoning Diagram Generation

Sun, 01 Jan 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Reactive Displays for Virtual Reality

Sun, 01 Jan 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Visual Odometry Based Omni-directional Hyperlapse

Sun, 01 Jan 2017 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Deep Attributes for One-Shot Face Recognition

Fri, 01 Jan 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes

Fri, 01 Jan 2016 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Adapting RANSAC SVM to Detect Outliers for Robust Classification

Thu, 01 Jan 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Subspace Alignment Based Domain Adaptation for RCNN Detector

Thu, 01 Jan 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Where is my friend? - Person identification in social networks

Thu, 01 Jan 2015 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Object Classification with Adaptable Regions

Wed, 01 Jan 2014 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Nonuniform image patch exemplars for low level vision

Tue, 01 Jan 2013 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Classification with Global, Local and Shared Features

Sun, 01 Jan 2012 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Action recognition: A region based approach

Sat, 01 Jan 2011 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Object and Action Classification with Latent Variables

Sat, 01 Jan 2011 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Systematic evaluation of super-resolution using classification

Sat, 01 Jan 2011 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Recovery of relative depth from a single observation using an uncalibrated (real-aperture) camera

Tue, 01 Jan 2008 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Regularized depth from defocus

Tue, 01 Jan 2008 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Image Restoration using Geometrically Stabilized Reverse Heat Equation

Mon, 01 Jan 2007 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

On defocus, diffusion and depth estimation

Mon, 01 Jan 2007 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Retrieval of images of man-made structures based on projective invariance

Mon, 01 Jan 2007 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Shape Recovery Using Stochastic Heat Flow

Mon, 01 Jan 2007 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Super-Resolution Using Sub-band Constrained Total Variation

Mon, 01 Jan 2007 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Improved Kernel-Based Object Tracking Under Occluded Scenarios

Sun, 01 Jan 2006 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Shock Filters Based on Implicit Cluster Separation

Sat, 01 Jan 2005 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Image retrieval based on projective invariance

Thu, 01 Jan 2004 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.

Use of Linear Diffusion in Depth Estimation Based on Defocus Cue

Thu, 01 Jan 2004 00:00:00 +0000

Add the full text or supplementary notes for the publication here using Markdown formatting.