{"total":81,"rows":[{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2209.11178","title":"Poisson Flow Generative Models","created":"2022-09-22","cited_by_count":95,"area":null},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77,"area":null},{"id":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61,"area":null},{"id":"2502.12191","title":"AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors","created":"2025-02-15","cited_by_count":48,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2206.09479","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","created":"2022-06-19","cited_by_count":38,"area":null},{"id":"2202.14020","title":"State-of-the-Art in the Architecture, Methods and Applications of StyleGAN","created":"2022-02-28","cited_by_count":34,"area":null},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2203.16248","title":"InstaFormer: Instance-Aware Image-to-Image Translation with Transformer","created":"2022-03-30","cited_by_count":28,"area":null},{"id":"2312.00634","title":"A Recent Survey of Vision Transformers for Medical Image Segmentation","created":"2023-12-01","cited_by_count":23,"area":null},{"id":"2204.05538","title":"NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night","created":"2022-04-12","cited_by_count":21,"area":null},{"id":"2210.11557","title":"Learning Attention Propagation for Compositional Zero-Shot Learning","created":"2022-10-20","cited_by_count":20,"area":null},{"id":"2303.09735","title":"SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2303.11424","title":"Polynomial Implicit Neural Representations For Large Diverse Datasets","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2203.16015","title":"ITTR: Unpaired Image-to-Image Translation with Transformers","created":"2022-03-30","cited_by_count":15,"area":null},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2306.06849","title":"Mitigating Transformer Overconfidence via Lipschitz Regularization","created":"2023-06-12","cited_by_count":15,"area":null},{"id":"2302.11306","title":"Human MotionFormer: Transferring Human Motions with Vision Transformers","created":"2023-02-22","cited_by_count":14,"area":null},{"id":"2309.03244","title":"EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation","created":"2023-09-06","cited_by_count":14,"area":null},{"id":"2402.18062","title":"Generative AI for Unmanned Vehicle Swarms: Challenges, Applications and Opportunities","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2112.15439","title":"Facial-Sketch Synthesis: A New Challenge","created":"2021-12-31","cited_by_count":13,"area":null},{"id":"2209.08217","title":"Delving Globally into Texture and Structure for Image Inpainting","created":"2022-09-17","cited_by_count":13,"area":null},{"id":"2207.05312","title":"Outpainting by Queries","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2404.04531","title":"Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation","created":"2024-04-06","cited_by_count":12,"area":null},{"id":"2511.22475","title":"Adversarial Flow Models","created":"2025-11-27","cited_by_count":12,"area":null},{"id":"2212.12322","title":"Infrared Image Super-Resolution: Systematic Review, and Future Trends","created":"2022-12-22","cited_by_count":11,"area":null},{"id":"2203.01587","title":"Multi-Tailed Vision Transformer for Efficient Inference","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2210.04883","title":"SCAM! Transferring humans between images with Semantic Cross Attention Modulation","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2302.08641","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2207.11081","title":"Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers","created":"2022-07-22","cited_by_count":9,"area":null},{"id":"2406.02968","title":"GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2204.00833","title":"PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation","created":"2022-04-02","cited_by_count":5,"area":null},{"id":"2306.14678","title":"Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs","created":"2023-06-26","cited_by_count":5,"area":null},{"id":"2509.24935","title":"Scalable GANs with Transformers","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2209.01320","title":"Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglement","created":"2022-09-03","cited_by_count":4,"area":null},{"id":"2312.08264","title":"Kunyu: A High-Performing Global Weather Model Beyond Regression Losses","created":"2023-12-04","cited_by_count":4,"area":null},{"id":"2409.11836","title":"NT-ViT: Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2212.09977","title":"Unified Framework for Histopathology Image Augmentation and Classification via Generative Models","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2110.13107","title":"The Nuts and Bolts of Adopting Transformer in GANs","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2112.08117","title":"Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2203.11453","title":"DepthGAN: GAN-based Depth Generation of Indoor Scenes from Semantic Layouts","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2302.00089","title":"Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2302.01608","title":"CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2307.05616","title":"Image Reconstruction using Enhanced Vision Transformer","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2309.01950","title":"RADIO: Reference-Agnostic Dubbing Video Synthesis","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2309.08160","title":"Cross-Modal Synthesis of Structural MRI and Functional Connectivity Networks via Conditional ViT-GANs","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2404.00521","title":"CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2411.01443","title":"Activating Self-Attention for Multi-Scene Absolute Pose Regression","created":"2024-11-03","cited_by_count":2,"area":null},{"id":"2501.10197","title":"CSHNet: A Novel Information Asymmetric Image Translation Method","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2302.08047","title":"TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation","created":"2023-02-16","cited_by_count":1,"area":null},{"id":"2304.04960","title":"Panoramic Image-to-Image Translation","created":"2023-04-11","cited_by_count":1,"area":null},{"id":"2310.01843","title":"Selective Feature Adapter for Dense Vision Transformers","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2312.01999","title":"SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2410.20097","title":"Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2109.00919","title":"Reiterative Domain Aware Multi-Target Adaptation","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2207.03899","title":"Big Learning","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2207.06831","title":"iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer","created":"2022-07-14","cited_by_count":0,"area":null},{"id":"2301.00592","title":"Edge Enhanced Image Style Transfer via Transformers","created":"2023-01-02","cited_by_count":0,"area":null},{"id":"2301.06962","title":"Long Range Pooling for 3D Large-Scale Scene Understanding","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2303.09012","title":"Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Review","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2304.05556","title":"An End-to-End Network for Upright Adjustment of Panoramic Images","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2305.03977","title":"Unlocking the Power of GANs in Non-Autoregressive Text Generation","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2306.06914","title":"Enhancing COVID-19 Diagnosis through Vision Transformer-Based Analysis of Chest X-ray Images","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2310.13216","title":"PTSR: Patch Translator for Image Super-Resolution","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2310.16777","title":"MixerFlow: MLP-Mixer meets Normalising Flows","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2312.00689","title":"Infrared Image Super-Resolution via GAN","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2312.07040","title":"Rethinking Model Inversion Attacks With Patch-Wise Reconstruction","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2406.13153","title":"SwinStyleformer is a favorable choice for image inversion","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2407.21319","title":"Big Cooperative Learning","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2408.00940","title":"A dual-task mutual learning framework for predicting post-thrombectomy cerebral hemorrhage","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2411.14403","title":"Landing Trajectory Prediction for UAS Based on Generative Adversarial Network","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2502.01842","title":"Texture Image Synthesis Using Spatial GAN Based on Vision Transformers","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2508.04181","title":"Deeper Inside Deep ViT","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.01681","title":"GaussianGAN: Real-Time Photorealistic controllable Human Avatars","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2512.16140","title":"ResDynUNet++: A nested U-Net with residual dynamic convolution blocks for dual-spectral CT","created":"2025-12-18","cited_by_count":0,"area":null}],"next_cursor":null}