{"total":102,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"area":null},{"id":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144,"area":null},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126,"area":"diffusion"},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116,"area":"diffusion"},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80,"area":null},{"id":"2306.06874","title":"VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models","created":"2023-06-12","cited_by_count":68,"area":"diffusion"},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2303.11296","title":"Attribute-preserving Face Dataset Anonymization via Latent Code Optimization","created":"2023-03-20","cited_by_count":43,"area":null},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2312.08207","title":"Black-box Membership Inference Attacks against Fine-tuned Diffusion Models","created":"2023-12-13","cited_by_count":35,"area":"diffusion"},{"id":"2207.02204","title":"Detecting and Recovering Sequential DeepFake Manipulation","created":"2022-07-05","cited_by_count":34,"area":null},{"id":"2212.02122","title":"CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics","created":"2022-12-05","cited_by_count":34,"area":null},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31,"area":null},{"id":"2212.07409","title":"Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion","created":"2022-12-14","cited_by_count":24,"area":null},{"id":"2501.10360","title":"FaceXBench: Evaluating Multimodal LLMs on Face Understanding","created":"2025-01-17","cited_by_count":24,"area":"mllm"},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2209.11224","title":"VToonify: Controllable High-Resolution Portrait Video Style Transfer","created":"2022-09-22","cited_by_count":20,"area":null},{"id":"2302.01162","title":"Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2303.06146","title":"StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces","created":"2023-03-10","cited_by_count":19,"area":null},{"id":"2302.14736","title":"TextIR: A Simple Framework for Text-based Editable Image Restoration","created":"2023-02-28","cited_by_count":17,"area":null},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17,"area":null},{"id":"2204.03641","title":"Unsupervised Image-to-Image Translation with Generative Prior","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2210.12683","title":"GAN-based Facial Attribute Manipulation","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2305.14742","title":"ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation","created":"2023-05-24","cited_by_count":16,"area":"diffusion"},{"id":"2303.01311","title":"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2305.12815","title":"Investigating Agency of LLMs in Human-AI Collaboration Tasks","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2307.02733","title":"MMNet: Multi-Collaboration and Multi-Supervision Network for Sequential Deepfake Detection","created":"2023-07-06","cited_by_count":15,"area":null},{"id":"2410.08074","title":"Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models","created":"2024-10-10","cited_by_count":15,"area":"diffusion"},{"id":"2210.11795","title":"PoseScript: Linking 3D Human Poses and Natural Language","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2404.01101","title":"UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models","created":"2024-04-01","cited_by_count":14,"area":"diffusion"},{"id":"2407.08515","title":"15M Multimodal Facial Image-Text Dataset","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2312.03556","title":"Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention","created":"2023-12-06","cited_by_count":13,"area":"diffusion"},{"id":"2206.02104","title":"ContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentences","created":"2022-06-05","cited_by_count":12,"area":null},{"id":"2303.11108","title":"CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialogue","created":"2023-03-20","cited_by_count":12,"area":null},{"id":"2408.15721","title":"Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks","created":"2024-08-28","cited_by_count":12,"area":"diffusion"},{"id":"2503.21457","title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","created":"2025-03-27","cited_by_count":12,"area":"mllm"},{"id":"2208.07862","title":"StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3","created":"2022-08-16","cited_by_count":11,"area":null},{"id":"2307.08585","title":"Identity-Preserving Aging of Face Images via Latent Diffusion Models","created":"2023-07-17","cited_by_count":11,"area":"diffusion"},{"id":"2311.02826","title":"InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image","created":"2023-11-06","cited_by_count":10,"area":null},{"id":"2402.06223","title":"Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2306.04636","title":"GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation","created":"2023-06-07","cited_by_count":9,"area":null},{"id":"2312.13941","title":"Controllable 3D Face Generation with Conditional Style Code Diffusion","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2210.00445","title":"ManiCLIP: Multi-Attribute Face Manipulation from Text","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2303.10073","title":"DialogPaint: A Dialog-based Image Editing Model","created":"2023-03-17","cited_by_count":8,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2307.14770","title":"3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2411.03034","title":"HumanVLM: Foundation for Human-Scene Vision-Language Model","created":"2024-11-05","cited_by_count":8,"area":"mllm"},{"id":"2502.11798","title":"BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model","created":"2025-02-17","cited_by_count":8,"area":"diffusion"},{"id":"2304.09463","title":"HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks","created":"2023-04-19","cited_by_count":7,"area":null},{"id":"2409.11010","title":"MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2410.16472","title":"DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding","created":"2024-10-21","cited_by_count":7,"area":"mllm"},{"id":"2302.09467","title":"Designing a 3D-Aware StyleNeRF Encoder for Face Editing","created":"2023-02-19","cited_by_count":6,"area":null},{"id":"2308.03059","title":"Language-based Photo Color Adjustment for Graphic Designs","created":"2023-08-06","cited_by_count":6,"area":null},{"id":"2412.19009","title":"FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing","created":"2024-12-26","cited_by_count":6,"area":null},{"id":"2401.08472","title":"Instilling Multi-round Thinking to Text-guided Image Generation","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2309.14991","title":"Robust Sequential DeepFake Detection","created":"2023-09-26","cited_by_count":4,"area":null},{"id":"2310.18142","title":"Semi-Supervised Panoptic Narrative Grounding","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2410.00485","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","created":"2024-10-01","cited_by_count":4,"area":"lr"},{"id":"2507.05397","title":"Neural-Driven Image Editing","created":"2025-07-07","cited_by_count":4,"area":"diffusion"},{"id":"2211.14573","title":"Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model","created":"2022-11-26","cited_by_count":3,"area":null},{"id":"2312.16274","title":"Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2402.02369","title":"M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2409.15781","title":"Training Data Attribution: Was Your Model Secretly Trained On Data Created By Mine?","created":"2024-09-24","cited_by_count":3,"area":"safety"},{"id":"2411.15702","title":"Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2502.02465","title":"Towards Consistent and Controllable Image Synthesis for Face Editing","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.17724","title":"Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models","created":"2025-03-22","cited_by_count":3,"area":"diffusion"},{"id":"2504.20518","title":"Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models","created":"2025-04-29","cited_by_count":3,"area":"diffusion"},{"id":"2506.00562","title":"SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Models","created":"2025-05-31","cited_by_count":3,"area":"diffusion"},{"id":"2212.05667","title":"Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2403.06470","title":"3D-aware Image Generation and Editing with Multi-modal Conditions","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2502.13987","title":"SelfAge: Personalized Facial Age Transformation Using Self-reference Images","created":"2025-02-19","cited_by_count":2,"area":"diffusion"},{"id":"2503.23888","title":"MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach","created":"2025-03-31","cited_by_count":2,"area":"diffusion"},{"id":"2504.11309","title":"Big Brother is Watching: Proactive Deepfake Detection via Learnable Hidden Face","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2507.03979","title":"Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control","created":"2025-07-05","cited_by_count":2,"area":null},{"id":"2508.07432","title":"Freeze and Reveal: Exposing Modality Bias in Vision-Language Models","created":"2025-08-10","cited_by_count":2,"area":"mllm"},{"id":"2312.09367","title":"Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2401.13213","title":"Common-Sense Bias Modeling for Classification Tasks","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2402.10941","title":"Text2Data: Low-Resource Data Generation with Textual Control","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.08092","title":"Mitigating the Impact of Attribute Editing on Face Recognition","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2404.05063","title":"AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement","created":"2024-04-07","cited_by_count":1,"area":null},{"id":"2412.13565","title":"CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2504.03188","title":"Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2507.04692","title":"Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal","created":"2025-07-07","cited_by_count":1,"area":"diffusion"},{"id":"2509.00658","title":"Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2510.18345","title":"GPTFace: Generative Pre-training of Facial-Linguistic Transformer by Span Masking and Weakly Correlated Text-image Data","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2601.08179","title":"Instruction-Driven 3D Facial Expression Generation and Transition","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2607.02674","title":"EmoteGPT: 3D Human Facial Expressions from Natural Language Descriptions","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2306.06684","title":"Happy People -- Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2309.11923","title":"TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2410.20573","title":"Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2504.15259","title":"Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation","created":"2025-04-21","cited_by_count":0,"area":"diffusion"},{"id":"2507.21015","title":"Learning Transferable Facial Emotion Representations from Large-Scale Semantically Rich Captions","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2510.21775","title":"Face-MakeUpV2: Facial Consistency Learning for Controllable Text-to-Image Generation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.07221","title":"Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2606.23362","title":"TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger","created":"2026-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2607.04339","title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","created":"2026-07-05","cited_by_count":0,"area":"safety"},{"id":"2607.25642","title":"Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.16251","title":"SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":"100"}