{"total":89,"rows":[{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2211.01917","title":"Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset","created":"2022-11-03","cited_by_count":61,"area":null},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61,"area":null},{"id":"2305.19962","title":"GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations","created":"2023-05-31","cited_by_count":49,"area":"diffusion"},{"id":"2502.09533","title":"Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model","created":"2025-02-13","cited_by_count":49,"area":"diffusion"},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36,"area":null},{"id":"2503.14151","title":"Concat-ID: Towards Universal Identity-Preserving Video Synthesis","created":"2025-03-18","cited_by_count":28,"area":null},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22,"area":null},{"id":"2304.12483","title":"Towards Realistic Generative 3D Face Models","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2406.19875","title":"InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows","created":"2024-06-28","cited_by_count":20,"area":"mllm"},{"id":"2510.11000","title":"ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation","created":"2025-10-13","cited_by_count":18,"area":"diffusion"},{"id":"2312.01220","title":"Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation","created":"2023-12-02","cited_by_count":17,"area":null},{"id":"2409.02828","title":"ExpLLM: Towards Chain of Thought for Facial Expression Recognition","created":"2024-09-04","cited_by_count":15,"area":"lr"},{"id":"2503.17671","title":"ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation","created":"2025-03-22","cited_by_count":14,"area":"agents"},{"id":"2402.09225","title":"Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics","created":"2024-02-14","cited_by_count":13,"area":"safety"},{"id":"2405.14677","title":"RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance","created":"2024-05-23","cited_by_count":11,"area":"diffusion"},{"id":"2209.07366","title":"3DMM-RF: Convolutional Radiance Fields for 3D Face Modeling","created":"2022-09-15","cited_by_count":10,"area":null},{"id":"2504.02433","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2502.07203","title":"Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion","created":"2025-02-11","cited_by_count":8,"area":"diffusion"},{"id":"2510.14255","title":"Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization","created":"2025-10-16","cited_by_count":8,"area":"diffusion"},{"id":"2404.14568","title":"UVMap-ID: A Controllable and Personalized UV Map Generative Model","created":"2024-04-22","cited_by_count":7,"area":"diffusion"},{"id":"2204.01209","title":"EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2412.02259","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2024-12-03","cited_by_count":6,"area":null},{"id":"2504.15848","title":"Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2404.00301","title":"Monocular Identity-Conditioned Facial Reflectance Reconstruction","created":"2024-03-30","cited_by_count":5,"area":null},{"id":"2208.07142","title":"Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression","created":"2022-08-15","cited_by_count":4,"area":null},{"id":"2510.14179","title":"Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures","created":"2025-10-16","cited_by_count":4,"area":"diffusion"},{"id":"2607.13681","title":"Towards Spatial Supersensing in the Wild","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2211.06408","title":"Physically-Based Face Rendering for NIR-VIS Face Recognition","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2211.15377","title":"Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2303.16053","title":"Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2304.00838","title":"MetaHead: An Engine to Create Realistic Digital Head","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2406.19107","title":"FDLite: A Single Stage Lightweight Face Detector Network","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2409.09832","title":"Template-based Multi-Domain Face Recognition","created":"2024-09-15","cited_by_count":3,"area":null},{"id":"2508.21052","title":"FakeParts: a New Family of AI-Generated DeepFakes","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2511.21002","title":"Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning","created":"2025-11-26","cited_by_count":3,"area":"rag"},{"id":"2209.04093","title":"Learning Audio-Visual embedding for Person Verification in the Wild","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2212.06400","title":"Improving Depression estimation from facial videos with face alignment, training optimization and scheduling","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2311.16613","title":"Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2312.00856","title":"QAFE-Net: Quality Assessment of Facial Expressions with Landmark Heatmaps","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2401.14088","title":"Double Trouble? Impact and Detection of Duplicates in Face Image Datasets","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2406.02881","title":"Inv-Adapter: ID Customization Generation via Image Inversion and Lightweight Adapter","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2409.08444","title":"Towards Unified Facial Action Unit Recognition Framework by Large Language Models","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2501.16917","title":"B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2505.07552","title":"Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2606.16731","title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2408.07642","title":"Boosting Unconstrained Face Recognition with Targeted Style Adversary","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2411.12319","title":"CLIP Unreasonable Potential in Single-Shot Face Recognition","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2504.09530","title":"Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorders","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2511.05464","title":"Photo Dating by Facial Age Aggregation","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2604.00903","title":"IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off","created":"2026-04-01","cited_by_count":1,"area":"diffusion"},{"id":"2607.22830","title":"ID-V2V: Identity-Preserving Video Restylization","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2205.05783","title":"MEWS: Real-time Social Media Manipulation Detection and Analysis","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2305.00352","title":"Embedding Aggregation for Forensic Facial Comparison","created":"2023-04-29","cited_by_count":0,"area":null},{"id":"2309.06095","title":"Estimating exercise-induced fatigue from thermal facial images","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2310.06945","title":"End-to-end Evaluation of Practical Video Analytics Systems for Face Detection and Recognition","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2402.13771","title":"Mask-up: Investigating Biases in Face Re-identification for Masked Faces","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2404.09686","title":"AntBatchInfer: Elastic Batch Inference in the Kubernetes Cluster","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2405.02317","title":"Long-term Human Participation Assessment In Collaborative Learning Environments Using Dynamic Scene Analysis","created":"2024-04-14","cited_by_count":0,"area":null},{"id":"2501.07158","title":"Eye Sclera for Fair Face Image Quality Assessment","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2504.00401","title":"Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.00558","title":"Archival Faces: Detection of Faces in Digitized Historical Documents","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.02060","title":"Transforming faces into video stories -- VideoFace2.0","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2505.20985","title":"Assessing the Use of Face Swapping Methods as Face Anonymizers in Videos","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2508.06552","title":"Age-Diverse Deepfake Dataset: Bridging the Age Gap in Deepfake Detection","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.02563","title":"The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2604.08990","title":"ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.24419","title":"BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.20449","title":"InfantFace: Detecting infant faces in neonatal clinical environments","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20823","title":"NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21030","title":"FlowCodec: One-Step Flow Prior for Generative Image Compression","created":"2026-06-19","cited_by_count":0,"area":"diffusion"},{"id":"2606.26942","title":"TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.30321","title":"Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.08112","title":"VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.08402","title":"Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITS","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.13515","title":"DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.17042","title":"Articulated Humanoid Head for a Robot Receptionist Capable of Natural Human Interaction","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.23292","title":"Hiding in Plain Sight: An Effective Physical Adversarial Patch Attack against Visual-Infrared Fused Face Detection","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.25078","title":"Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models","created":"2026-07-27","cited_by_count":0,"area":"diffusion"},{"id":"2608.02841","title":"Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.06878","title":"ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE","created":"2026-08-07","cited_by_count":0,"area":"diffusion"},{"id":"2608.28685","title":"Data Diversity, Not Frequency Invariance: A Controlled and Self-Audited Study of Compression-Robust Deepfake Detection","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.25837","title":"Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33627","title":"StoryEngine: A State-Grounded Agentic Framework for Video Storytelling","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.05865","title":"Weave Mamba Fusion: Global Cross-Scale Interaction for Lightweight Face Detection","created":"2026-10-05","cited_by_count":0,"area":"ssm"},{"id":"2610.11023","title":"Expression-Diverse References for Identity-Preserving Video Generation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13733","title":"KVeil: First-Place Solution to ECCV 2026 LifeGenIP Challenge on Unlearnable Videos","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}