Generative Adversarial Text to Image Synthesis

Abstract

Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text and image model- ing, translating visual concepts from characters to pixels. We demonstrate the capability of our model to generate plausible images of birds and flowers from detailed text descriptions.

ICML 2016

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• Exploring Models and Data for Image Question Answering
• Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
• Better Mixing via Deep Representations

Cited by in corpus (459)

• Generative Adversarial Networks: An Overview
• Transformers in Vision: A Survey
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Deep Visual Domain Adaptation: A Survey
• Conditional Image Generation with PixelCNN Decoders
• Generative Adversarial Network in Medical Imaging: A Review
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Zero-Shot Text-to-Image Generation
• Toward Multimodal Image-to-Image Translation
• Media Forensics and DeepFakes: an overview
• Blended Diffusion for Text-driven Editing of Natural Images
• VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
• The Marginal Value of Adaptive Gradient Methods in Machine Learning
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• cGANs with Projection Discriminator
• CogView: Mastering Text-to-Image Generation via Transformers
• Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• Recent Advances in Convolutional Neural Networks
• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
• TransNets: Learning to Transform for Recommendation
• Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Image De-raining Using a Conditional Generative Adversarial Network
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
• Synthesizing Tabular Data using Generative Adversarial Networks
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• Adversarial Text-to-Image Synthesis: A Review
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Representation Learning by Rotating Your Faces
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Semantic Object Accuracy for Generative Text-to-Image Synthesis
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Least Squares Generative Adversarial Networks
• Fighting Deepfake by Exposing the Convolutional Traces on Images
• SpaText: Spatio-Textual Representation for Controllable Image Generation
• Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring
• Dense 3D Object Reconstruction from a Single Depth View
• Deep Identity-aware Transfer of Facial Attributes
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• Video-to-Video Synthesis
• Semantic Autoencoder for Zero-Shot Learning
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Towards Diverse and Natural Image Descriptions via a Conditional GAN
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• What Do We Understand About Convolutional Networks?
• Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
• StarGAN v2: Diverse Image Synthesis for Multiple Domains
• A Generative Model for Volume Rendering
• Soft-Label Dataset Distillation and Text Dataset Distillation
• Visual Reference Resolution using Attention Memory for Visual Dialog
• GP-GAN: Towards Realistic High-Resolution Image Blending
• Fashion-Gen: The Generative Fashion Dataset and Challenge
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Generating Visually Aligned Sound from Videos
• WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
• ChatPainter: Improving Text to Image Generation using Dialogue
• Densely Connected Pyramid Dehazing Network
• On Accurate Evaluation of GANs for Language Generation
• Adversarial Neural Machine Translation
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• You Only Need Adversarial Supervision for Semantic Image Synthesis
• Fine-grained Visual-textual Representation Learning
• Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks
• GANmapper: geographical data translation
• SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
• Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
• Cross-view image synthesis using geometry-guided conditional GANs
• CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
• Stabilizing Generative Adversarial Networks: A Survey
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks
• Multi-modal Deep Analysis for Multimedia
• CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
• Small Sample Learning in Big Data Era
• Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
• GACELA -- A generative adversarial context encoder for long audio inpainting
• A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
• GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
• Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning
• End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis
• Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks
• SSGAN: Secure Steganography Based on Generative Adversarial Networks
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• A Survey of AI Text-to-Image and AI Text-to-Video Generators
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
• Parallel Multiscale Autoregressive Density Estimation
• Activation Maximization Generative Adversarial Nets
• Learning Beyond Human Expertise with Generative Models for Dental Restorations
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• Generative adversarial networks in time series: A survey and taxonomy
• Object-driven Text-to-Image Synthesis via Adversarial Training
• Stacked Generative Adversarial Networks
• DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
• Multi-View Image Generation from a Single-View
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• Improving GANs Using Optimal Transport
• GANimation: Anatomically-aware Facial Animation from a Single Image
• Direct Speech-to-image Translation
• Vector Quantized Diffusion Model for Text-to-Image Synthesis
• Generative Adversarial Self-Imitation Learning
• BourGAN: Generative Networks with Metric Embeddings
• Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
• Polarimetric Thermal to Visible Face Verification via Attribute Preserved Synthesis
• Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
• Understanding GANs: the LQG Setting
• Semi-Latent GAN: Learning to generate and modify facial images from attributes
• Novelty Detection with GAN
• Face Super-Resolution Through Wasserstein GANs
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• From Deep to Physics-Informed Learning of Turbulence: Diagnostics
• InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
• MAGAN: Aligning Biological Manifolds
• Towards Open-Set Identity Preserving Face Synthesis
• DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation
• Generative Adversarial Network for Radar Signal Generation
• Text to Image Synthesis Using Generative Adversarial Networks
• On the Evaluation of Conditional GANs
• Pixel Deconvolutional Networks
• TediGAN: Text-Guided Diverse Face Image Generation and Manipulation
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Generating Multiple Objects at Spatially Distinct Locations
• Scene Graph Generation with External Knowledge and Image Reconstruction
• Language Guided Fashion Image Manipulation with Feature-wise Transformations
• Synthesis of Realistic ECG using Generative Adversarial Networks
• Simple yet Effective Way for Improving the Performance of GAN
• pix2code: Generating Code from a Graphical User Interface Screenshot
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
• ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design
• Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
• Unsupervised Multimodal Representation Learning across Medical Images and Reports
• TextureGAN: Controlling Deep Image Synthesis with Texture Patches
• Learning Generative Models across Incomparable Spaces
• On the capacity of deep generative networks for approximating distributions
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Adversarial Time-to-Event Modeling
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
• VITON: An Image-based Virtual Try-on Network
• Improving Text-to-Image Synthesis Using Contrastive Learning
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• Cross Modal Compression: Towards Human-comprehensible Semantic Compression
• Text-to-Image-to-Text Translation using Cycle Consistent Adversarial Networks
• Behavioural Repertoire via Generative Adversarial Policy Networks
• Autoencoders for music sound modeling: a comparison of linear, shallow, deep, recurrent and variational models
• Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
• Mode Collapse and Regularity of Optimal Transportation Maps
• StoryGAN: A Sequential Conditional GAN for Story Visualization
• DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
• Transferring GANs: generating images from limited data
• OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
• Text-to-Face Generation with StyleGAN2
• SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
• Unsupervised Diverse Colorization via Generative Adversarial Networks
• Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
• Using Scene Graph Context to Improve Image Generation
• Talking Face Generation by Conditional Recurrent Adversarial Network
• Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
• Generalised gravitational burst generation with Generative Adversarial Networks
• Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning
• Compatible and Diverse Fashion Image Inpainting
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Taming Visually Guided Sound Generation
• CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
• PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks
• improving partition-block-based acoustic echo canceler in under-modeling scenarios
• Speech-Image Semantic Alignment Does Not Depend on Any Prior Classification Tasks
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Unsupervised Person Image Synthesis in Arbitrary Poses
• From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
• Towards Multi-pose Guided Virtual Try-on Network
• Cross-modal Hallucination for Few-shot Fine-grained Recognition
• An error analysis of generative adversarial networks for learning distributions
• Learning to Globally Edit Images with Textual Description
• On the Effectiveness of Least Squares Generative Adversarial Networks
• Structured Knowledge Distillation for Dense Prediction
• Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
• Learning Face Age Progression: A Pyramid Architecture of GANs
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Learning to Sketch with Shortcut Cycle Consistency
• Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
• Unsupervised Multi-modal Neural Machine Translation
• Robust Multi-Modal Sensor Fusion: An Adversarial Approach
• LayoutVAE: Stochastic Scene Layout Generation From a Label Set
• Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
• To Create What You Tell: Generating Videos from Captions
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
• Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
• Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
• MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• Text to Image Synthesis using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networks
• Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
• Improving Neural Silent Speech Interface Models by Adversarial Training
• FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face Generation
• Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
• A Comprehensive Survey of Deep Learning for Image Captioning
• Text2Scene: Generating Compositional Scenes from Textual Descriptions
• Generative Convolution Layer for Image Generation
• cGANs with Multi-Hinge Loss
• Distillation Techniques for Pseudo-rehearsal Based Incremental Learning
• Visual Data Synthesis via GAN for Zero-Shot Video Classification
• Semi-parametric Image Synthesis
• IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
• Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
• LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
• Interactive Image Manipulation with Natural Language Instruction Commands
• DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
• Modular Generative Adversarial Networks
• Generative Feature Replay For Class-Incremental Learning
• Vision and Language: from Visual Perception to Content Creation
• Disentangling Propagation and Generation for Video Prediction
• Generating Semantic Adversarial Examples via Feature Manipulation
• The Neural Painter: Multi-Turn Image Generation
• A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
• Tree Memory Networks for Modelling Long-term Temporal Dependencies
• Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• SingleGAN: Image-to-Image Translation by a Single-Generator Network using Multiple Generative Adversarial Learning
• Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
• Data-driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
• AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation
• Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
• Task-Aware Feature Generation for Zero-Shot Compositional Learning
• Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
• Image-to-image Translation via Hierarchical Style Disentanglement
• Conditional GANs with Auxiliary Discriminative Classifier
• Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
• Pose Guided Fashion Image Synthesis Using Deep Generative Model
• Translation-Enhanced Multilingual Text-to-Image Generation
• Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
• Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks
• CAGAN: Text-To-Image Generation with Combined Attention GANs
• Image Synthesis From Reconfigurable Layout and Style
• GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
• PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
• Cycle Text-To-Image GAN with BERT
• What Is It Like Down There? Generating Dense Ground-Level Views and Image Features From Overhead Imagery Using Conditional Generative Adversarial Networks
• JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels
• Generative Design in Minecraft: Chronicle Challenge
• KG-GAN: Knowledge-Guided Generative Adversarial Networks
• Variational Inference for Computational Imaging Inverse Problems
• Language-Driven Image Style Transfer
• Sequential Attention GAN for Interactive Image Editing
• Label-Noise Robust Generative Adversarial Networks
• An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
• Deep Cross-Modal Audio-Visual Generation
• Leveraging Visual Question Answering to Improve Text-to-Image Synthesis
• SDIT: Scalable and Diverse Cross-domain Image Translation
• SegAttnGAN: Text to Image Generation with Segmentation Attention
• Hair-GANs: Recovering 3D Hair Structure from a Single Image
• CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
• cGANs with Conditional Convolution Layer
• A Large-scale Attribute Dataset for Zero-shot Learning
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• Generative Adversarial Frontal View to Bird View Synthesis
• Adversarial Attribute-Image Person Re-identification
• TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks
• Probabilistic Video Generation using Holistic Attribute Control
• toon2real: Translating Cartoon Images to Realistic Images
• Leveraging Long and Short-term Information in Content-aware Movie Recommendation
• Classifier and Exemplar Synthesis for Zero-Shot Learning
• Structured Prediction using cGANs with Fusion Discriminator
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• Weakly supervised cross-domain alignment with optimal transport
• Generative Dual Adversarial Network for Generalized Zero-shot Learning
• ComicGAN: Text-to-Comic Generative Adversarial Network
• WarpGAN: Automatic Caricature Generation
• LUCSS: Language-based User-customized Colourization of Scene Sketches
• MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
• Dual Adversarial Inference for Text-to-Image Synthesis
• Unpaired Photo-to-Caricature Translation on Faces in the Wild
• Asymmetric GANs for Image-to-Image Translation
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• Dual Contrastive Loss and Attention for GANs
• Color Constancy by GANs: An Experimental Survey
• I Want This Product but Different : Multimodal Retrieval with Synthetic Query Expansion
• Visual Conceptual Blending with Large-scale Language and Vision Models
• Multi-View Frame Reconstruction with Conditional GAN
• SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks
• XRayGAN: Consistency-preserving Generation of X-ray Images from Radiology Reports
• Learning Implicit Generative Models with Theoretical Guarantees
• OCTNet: Trajectory Generation in New Environments from Past Experiences
• C4Synth: Cross-Caption Cycle-Consistent Text-to-Image Synthesis
• FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
• Variational Conditional GAN for Fine-grained Controllable Image Generation
• Neural Storyboard Artist: Visualizing Stories with Coherent Image Sequences
• Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks
• Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks
• SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
• Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification
• M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
• Obj-GloVe: Scene-Based Contextual Object Embedding
• Challenges and Prospects in Vision and Language Research
• Text Guided Person Image Synthesis
• Attribute-guided image generation from layout
• World-Consistent Video-to-Video Synthesis
• Text-to-Image Generation Grounded by Fine-Grained User Attention
• SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network
• Enhance Images as You Like with Unpaired Learning
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
• VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks
• New Ideas and Trends in Deep Multimodal Content Understanding: A Review
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning
• Generating Image Sequence from Description with LSTM Conditional GAN
• SDE approximations of GANs training and its long-run behavior
• STAN-CT: Standardizing CT Image using Generative Adversarial Network
• SwapText: Image Based Texts Transfer in Scenes
• Bayesian Reasoning with Trained Neural Networks
• Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
• Fully Automated Image De-fencing using Conditional Generative Adversarial Networks
• Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
• Boosted GAN with Semantically Interpretable Information for Image Inpainting
• VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling
• Conditional Video Generation Using Action-Appearance Captions
• Class-Distinct and Class-Mutual Image Generation with GANs
• Towards Audio to Scene Image Synthesis using Generative Adversarial Network
• Generative Adversarial Estimation of Channel Covariance in Vehicular Millimeter Wave Systems
• From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration
• Cross-Domain Adversarial Auto-Encoder
• Lip Movements Generation at a Glance
• Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning
• Conditional Generative Adversarial Networks for Emoji Synthesis with Word Embedding Manipulation
• Multilevel Context Representation for Improving Object Recognition
• Cartoon-to-real: An Approach to Translate Cartoon to Realistic Images using GAN
• Dilated Temporal Relational Adversarial Network for Generic Video Summarization
• Channel-Recurrent Autoencoding for Image Modeling
• An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges
• Robust GANs against Dishonest Adversaries
• Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
• Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• Generative Imagination Elevates Machine Translation
• TinyGAN: Distilling BigGAN for Conditional Image Generation
• Adversarial Learning of Semantic Relevance in Text to Image Synthesis
• Adversarial Robustness of Flow-Based Generative Models
• DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
• Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis
• Omni-GAN: On the Secrets of cGANs and Beyond
• Grounded and Controllable Image Completion by Incorporating Lexical Semantics
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Lessons learned in multilingual grounded language learning
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• Attribute-Guided Sketch Generation
• DISCO Nets: DISsimilarity COefficient Networks
• Online Anomaly Detection in Surveillance Videos with Asymptotic Bounds on False Alarm Rate
• Cross Domain Image Generation through Latent Space Exploration with Adversarial Loss
• Think Visually: Question Answering through Virtual Imagery
• MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences
• Parametric Synthesis of Text on Stylized Backgrounds using PGGANs
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• Text-to-image Synthesis via Symmetrical Distillation Networks
• Generative Creativity: Adversarial Learning for Bionic Design
• Semantic Text-to-Face GAN -ST^2FG
• DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
• Conditional Adversarial Camera Model Anonymization
• Restricting Greed in Training of Generative Adversarial Network
• Synthetic Dynamic PMU Data Generation: A Generative Adversarial Network Approach
• Lemotif: An Affective Visual Journal Using Deep Neural Networks
• Learning of Colors from Color Names: Distribution and Point Estimation
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• Towards Better Adversarial Synthesis of Human Images from Text
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
• Sparse Label Smoothing Regularization for Person Re-Identification
• Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
• Cross-Modal Virtual Sensing for Combustion Instability Monitoring
• PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
• Teaching a GAN What Not to Learn
• PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
• TreeGAN: Incorporating Class Hierarchy into Image Generation
• Multi-Modal Super Resolution for Dense Microscopic Particle Size Estimation
• Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
• Updating the generator in PPGN-h with gradients flowing through the encoder
• Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation
• Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics
• Cross-Modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Representation Learning
• Video Compression Coding via Colorization: A Generative Adversarial Network (GAN)-Based Approach
• One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network
• Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
• Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks
• Deep Factorised Inverse-Sketching
• Inner Space Preserving Generative Pose Machine
• Learning color space adaptation from synthetic to real images of cirrus clouds
• Deep Semantic Hashing with Generative Adversarial Networks
• CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas
• Local Stability and Performance of Simple Gradient Penalty mu-Wasserstein GAN
• Generating a Fusion Image: One's Identity and Another's Shape
• Normalized Diversification
• Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
• Towards conceptual generalization in the embedding space
• Visual-Relation Conscious Image Generation from Structured-Text
• Logic could be learned from images
• Systematic Analysis of Image Generation using GANs
• MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
• BSD-GAN: Branched Generative Adversarial Network for Scale-Disentangled Representation Learning and Image Synthesis
• Generating Videos of Zero-Shot Compositions of Actions and Objects
• Compact Scene Graphs for Layout Composition and Patch Retrieval
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• FusedProp: Towards Efficient Training of Generative Adversarial Networks
• Adversarial Synthesis of Human Pose from Text
• Compressed Sensing via Measurement-Conditional Generative Models
• Selective Sampling and Mixture Models in Generative Adversarial Networks
• TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator
• Learning to Reconstruct and Segment 3D Objects
• Expression Conditional GAN for Facial Expression-to-Expression Translation
• MUSE: Textual Attributes Guided Portrait Painting Generation
• Efficient Semantic Image Synthesis via Class-Adaptive Normalization
• Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks
• Generative Adversarial Network: Some Analytical Perspectives
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Label Geometry Aware Discriminator for Conditional Generative Networks
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
• Illiterate DALL-E Learns to Compose
• OmiTrans: generative adversarial networks based omics-to-omics translation framework
• Mutltimodal AI Companion for Interactive Fairytale Co-creation
• Convergence of GANs Training: A Game and Stochastic Control Methodology
• Generative Adversarial Learning via Kernel Density Discrimination
• Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN
• CIGLI: Conditional Image Generation from Language & Image
• Physical Context and Timing Aware Sequence Generating GANs
• Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization
• Understanding Entropic Regularization in GANs
• Using Text to Teach Image Retrieval
• DINO: A Conditional Energy-Based GAN for Domain Translation
• Monte Carlo Simulation of SDEs using GANs
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• Surrogate Gradient Field for Latent Space Manipulation
• Revisiting Document Representations for Large-Scale Zero-Shot Learning
• Domain Adaptation with Morphologic Segmentation
• Translate the Facial Regions You Like Using Region-Wise Normalization
• AugLabel: Exploiting Word Representations to Augment Labels for Face Attribute Classification
• Synthetic Convolutional Features for Improved Semantic Segmentation
• Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
• Representation Learning: A Statistical Perspective
• Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
• End-to-End Learning Using Cycle Consistency for Image-to-Caption Transformations