{"total":168,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694,"area":null},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2112.02236","title":"SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing","created":"2021-12-04","cited_by_count":58,"area":null},{"id":"2411.19417","title":"Any-Resolution AI-Generated Image Detection by Spectral Learning","created":"2024-11-28","cited_by_count":57,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51,"area":null},{"id":"2112.12047","title":"Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications","created":"2021-12-22","cited_by_count":47,"area":null},{"id":"2108.12141","title":"DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis","created":"2021-08-27","cited_by_count":45,"area":null},{"id":"2109.08857","title":"Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts","created":"2021-09-18","cited_by_count":40,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2206.03066","title":"Recent Advances for Quantum Neural Networks in Generative Learning","created":"2022-06-07","cited_by_count":39,"area":null},{"id":"2204.05539","title":"Content and Style Aware Generation of Text-line Images for Handwriting Recognition","created":"2022-04-12","cited_by_count":35,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2105.09266","title":"Copyright in Generative Deep Learning","created":"2021-05-19","cited_by_count":29,"area":null},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2105.14173","title":"FoveaTer: Foveated Transformer for Image Classification","created":"2021-05-29","cited_by_count":28,"area":null},{"id":"2305.10124","title":"Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems","created":"2023-05-17","cited_by_count":28,"area":null},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2103.15910","title":"Sign Language Production: A Review","created":"2021-03-29","cited_by_count":26,"area":null},{"id":"2102.12037","title":"Conditional Image Generation by Conditioning Variational Auto-Encoders","created":"2021-02-24","cited_by_count":25,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2312.10549","title":"Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy","created":"2023-12-16","cited_by_count":24,"area":null},{"id":"2103.01071","title":"A survey on Variational Autoencoders from a GreenAI perspective","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2410.15644","title":"Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration","created":"2024-10-21","cited_by_count":22,"area":null},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2110.10183","title":"Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2308.12191","title":"Sign Language Translation with Iterative Prototype","created":"2023-08-23","cited_by_count":20,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16,"area":null},{"id":"2407.11588","title":"Progressive Pretext Task Learning for Human Trajectory Prediction","created":"2024-07-16","cited_by_count":16,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2108.01988","title":"Sparse Continuous Distributions and Fenchel-Young Losses","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2104.09371","title":"Non-linear Functional Modeling using Neural Networks","created":"2021-04-19","cited_by_count":13,"area":null},{"id":"2105.14678","title":"Image-to-Video Generation via 3D Facial Dynamics","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2207.06812","title":"Comparing the latent space of generative models","created":"2022-07-14","cited_by_count":12,"area":null},{"id":"2204.10482","title":"Recurrent Affine Transformation for Text-to-image Synthesis","created":"2022-04-22","cited_by_count":11,"area":null},{"id":"2302.11101","title":"Learning from Predictions: Fusing Training and Autoregressive Inference for Long-Term Spatiotemporal Forecasts","created":"2023-02-22","cited_by_count":11,"area":null},{"id":"2107.00400","title":"Lossless Coding of Point Cloud Geometry using a Deep Generative Model","created":"2021-07-01","cited_by_count":10,"area":null},{"id":"2301.12351","title":"Emerging Synergies in Causality and Deep Generative Models: A Survey","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2306.08984","title":"Tree Variational Autoencoders","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2101.06070","title":"Efficient Semi-Implicit Variational Inference","created":"2021-01-15","cited_by_count":9,"area":null},{"id":"2205.06448","title":"FRIH: Fine-grained Region-aware Image Harmonization","created":"2022-05-13","cited_by_count":9,"area":null},{"id":"2206.09513","title":"$C^*$-algebra Net: A New Approach Generalizing Neural Network Parameters to $C^*$-algebra","created":"2022-06-20","cited_by_count":9,"area":null},{"id":"2306.17170","title":"An Overview on Generative AI at Scale with Edge-Cloud Computing","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2310.10060","title":"Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2201.01609","title":"All You Need In Sign Language Production","created":"2022-01-05","cited_by_count":8,"area":null},{"id":"2305.19550","title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","created":"2023-05-31","cited_by_count":8,"area":null},{"id":"2312.01450","title":"Foveation in the Era of Deep Learning","created":"2023-12-03","cited_by_count":8,"area":null},{"id":"2408.11541","title":"Evolution of Detection Performance throughout the Online Lifespan of Synthetic Images","created":"2024-08-21","cited_by_count":8,"area":null},{"id":"2211.17267","title":"Variational Laplace Autoencoders","created":"2022-11-30","cited_by_count":7,"area":null},{"id":"2110.12279","title":"SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation","created":"2021-10-23","cited_by_count":6,"area":null},{"id":"2405.18808","title":"BRACTIVE: A Brain Activation Approach to Human Visual Brain Learning","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2411.16370","title":"A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation","created":"2024-11-25","cited_by_count":6,"area":null},{"id":"2201.06648","title":"OmniPrint: A Configurable Printed Character Synthesizer","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2206.01829","title":"Drawing out of Distribution with Neuro-Symbolic Generative Models","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2208.09596","title":"Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2307.00668","title":"Active Sensing with Predictive Coding and Uncertainty Minimization","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2308.14925","title":"Patient-specific, mechanistic models of tumor growth incorporating artificial intelligence and big data","created":"2023-08-28","cited_by_count":5,"area":null},{"id":"2601.03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","created":"2026-01-07","cited_by_count":5,"area":null},{"id":"2104.10544","title":"Lossless Compression with Latent Variable Models","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2109.09120","title":"ComicGAN: Text-to-Comic Generative Adversarial Network","created":"2021-09-19","cited_by_count":4,"area":null},{"id":"2111.13282","title":"Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2201.12414","title":"Posterior Matching for Arbitrary Conditioning","created":"2022-01-28","cited_by_count":4,"area":null},{"id":"2205.01399","title":"Outdoor Monocular Depth Estimation: A Research Review","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2209.05680","title":"Switchable Self-attention Module","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2302.04149","title":"Domain Adaptation of Synthetic Driving Datasets for Real-World Autonomous Driving","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2306.12045","title":"Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2402.15710","title":"A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data","created":"2024-02-24","cited_by_count":4,"area":null},{"id":"2508.03625","title":"AttZoom: Attention Zoom for Better Visual Features","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2103.03905","title":"Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory","created":"2021-02-20","cited_by_count":3,"area":null},{"id":"2108.08205","title":"An Attention Module for Convolutional Neural Networks","created":"2021-08-18","cited_by_count":3,"area":null},{"id":"2108.08955","title":"CIGLI: Conditional Image Generation from Language & Image","created":"2021-08-20","cited_by_count":3,"area":null},{"id":"2109.02580","title":"Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2110.14947","title":"Probabilistic Autoencoder using Fisher Information","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2111.02947","title":"Variational Inference with Holder Bounds","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2204.04876","title":"Lyapunov-Guided Representation of Recurrent Neural Network Performance","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2208.10322","title":"Mix-Pooling Strategy for Attention Mechanism","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2209.06096","title":"Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition","created":"2022-09-13","cited_by_count":3,"area":null},{"id":"2209.11277","title":"FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2210.05258","title":"EOCSA: Predicting Prognosis of Epithelial Ovarian Cancer with Whole Slide Histopathological Images","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2212.13295","title":"Structure-based drug discovery with deep learning","created":"2022-12-26","cited_by_count":3,"area":null},{"id":"2305.10267","title":"State Representation Learning Using an Unbalanced Atlas","created":"2023-05-17","cited_by_count":3,"area":null}],"next_cursor":"100"}