{"total":116,"rows":[{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516,"area":"lr"},{"id":"2103.00860","title":"Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation","created":"2021-03-01","cited_by_count":192,"area":null},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183,"area":"mllm"},{"id":"2104.10729","title":"Low-Light Image and Video Enhancement Using Deep Learning: A Survey","created":"2021-04-21","cited_by_count":148,"area":null},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2306.00306","title":"Low-Light Image Enhancement with Wavelet-based Diffusion Models","created":"2023-06-01","cited_by_count":127,"area":"diffusion"},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2106.14501","title":"R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network","created":"2021-06-28","cited_by_count":106,"area":null},{"id":"2112.13522","title":"Dual Contrastive Learning for General Face Forgery Detection","created":"2021-12-27","cited_by_count":100,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2103.16076","title":"Face Forensics in the Wild","created":"2021-03-30","cited_by_count":87,"area":null},{"id":"2112.13977","title":"Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning","created":"2021-12-28","cited_by_count":60,"area":null},{"id":"2211.09454","title":"DeepPrivacy2: Towards Realistic Full-Body Anonymization","created":"2022-11-17","cited_by_count":51,"area":null},{"id":"2307.16545","title":"Towards General Visual-Linguistic Face Forgery Detection","created":"2023-07-31","cited_by_count":45,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43,"area":null},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"area":null},{"id":"2108.05479","title":"Automatic Gaze Analysis: A Survey of Deep Learning based Approaches","created":"2021-08-12","cited_by_count":33,"area":null},{"id":"2202.12972","title":"FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment","created":"2022-02-25","cited_by_count":33,"area":null},{"id":"2104.01984","title":"HLA-Face: Joint High-Low Adaptation for Low Light Face Detection","created":"2021-04-05","cited_by_count":28,"area":null},{"id":"2306.17206","title":"FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude","created":"2023-06-29","cited_by_count":27,"area":null},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26,"area":null},{"id":"2308.06217","title":"Continual Face Forgery Detection via Historical Distribution Preserving","created":"2023-08-11","cited_by_count":23,"area":null},{"id":"2112.04719","title":"Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision","created":"2021-12-09","cited_by_count":22,"area":null},{"id":"2302.08931","title":"LDFA: Latent Diffusion Face Anonymization for Self-driving Applications","created":"2023-02-17","cited_by_count":21,"area":"diffusion"},{"id":"2108.06968","title":"3D High-Fidelity Mask Face Presentation Attack Detection Challenge","created":"2021-08-16","cited_by_count":19,"area":null},{"id":"2212.10772","title":"Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond","created":"2022-12-21","cited_by_count":17,"area":null},{"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":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2201.02193","title":"Realistic Full-Body Anonymization with Surface-Guided GANs","created":"2022-01-06","cited_by_count":15,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2109.10688","title":"Finding Facial Forgery Artifacts with Parts-Based Detectors","created":"2021-09-21","cited_by_count":14,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2308.16187","title":"Boosting Detection in Crowd Analysis via Underutilized Output Features","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2206.05717","title":"Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2210.00712","title":"PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement","created":"2022-10-03","cited_by_count":12,"area":null},{"id":"2306.05135","title":"Does Image Anonymization Impact Computer Vision Training?","created":"2023-06-08","cited_by_count":12,"area":null},{"id":"2103.11139","title":"MogFace: Towards a Deeper Appreciation on Face Detection","created":"2021-03-20","cited_by_count":10,"area":null},{"id":"2103.14983","title":"Going Deeper Into Face Detection: A Survey","created":"2021-03-27","cited_by_count":10,"area":null},{"id":"2308.00574","title":"PVG: Progressive Vision Graph for Vision Recognition","created":"2023-08-01","cited_by_count":10,"area":null},{"id":"2105.03632","title":"CASIA-Face-Africa: A Large-scale African Face Image Database","created":"2021-05-08","cited_by_count":9,"area":null},{"id":"2201.10781","title":"ASFD: Automatic and Scalable Face Detector","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2305.00817","title":"Racial Bias within Face Recognition: A Survey","created":"2023-05-01","cited_by_count":9,"area":null},{"id":"2305.02143","title":"GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions","created":"2023-05-03","cited_by_count":9,"area":null},{"id":"2307.14241","title":"DisguisOR: Holistic Face Anonymization for the Operating Room","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2503.08168","title":"TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2209.09111","title":"DeePhy: On Deepfake Phylogeny","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2104.04606","title":"RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes","created":"2021-04-09","cited_by_count":7,"area":null},{"id":"2404.11159","title":"Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2412.14515","title":"Relational Programming with Foundation Models","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2103.07017","title":"CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement","created":"2021-03-12","cited_by_count":6,"area":null},{"id":"2112.01787","title":"Detect Faces Efficiently: A Survey and Evaluations","created":"2021-12-03","cited_by_count":6,"area":null},{"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":"2507.04277","title":"Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2201.04777","title":"A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19","created":"2022-01-13","cited_by_count":5,"area":null},{"id":"2207.07317","title":"Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2210.03792","title":"Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2404.03327","title":"DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2106.08829","title":"A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2305.19556","title":"Exploring Phonetic Context-Aware Lip-Sync For Talking Face Generation","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2307.15257","title":"Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications","created":"2023-07-28","cited_by_count":4,"area":null},{"id":"2409.16143","title":"Seeing Faces in Things: A Model and Dataset for Pareidolia","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.16317","title":"A Survey on Physical Adversarial Attacks against Face Recognition Systems","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2412.01101","title":"Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection","created":"2024-12-02","cited_by_count":4,"area":null},{"id":"2509.12653","title":"Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2509.25991","title":"Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2104.11721","title":"Safe Fakes: Evaluating Face Anonymizers for Face Detectors","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2110.04727","title":"LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2112.11290","title":"Review of Face Presentation Attack Detection Competitions","created":"2021-12-21","cited_by_count":3,"area":null},{"id":"2211.03588","title":"Are Face Detection Models Biased?","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2302.11816","title":"EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection","created":"2023-02-23","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":"2505.15772","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2507.08380","title":"From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2101.04051","title":"Horizontal-to-Vertical Video Conversion","created":"2021-01-11","cited_by_count":2,"area":null},{"id":"2105.10104","title":"EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2309.03548","title":"Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation","created":"2023-09-07","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":"2405.19173","title":"Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservation","created":"2024-05-29","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":"2502.19867","title":"Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement","created":"2025-02-27","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":"2508.07795","title":"Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2104.08373","title":"Constructing Robust Emotional State-based Feature with a Novel Voting Scheme for Multi-modal Deception Detection in Videos","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2106.10944","title":"Hard hat wearing detection based on head keypoint localization","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2107.05025","title":"Similarity Guided Deep Face Image Retrieval","created":"2021-07-11","cited_by_count":1,"area":null},{"id":"2212.04764","title":"AuE-IPA: An AU Engagement Based Infant Pain Assessment Method","created":"2022-12-09","cited_by_count":1,"area":null},{"id":"2306.02277","title":"EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2306.02883","title":"Unsupervised network for low-light enhancement","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2308.03381","title":"Bilevel Generative Learning for Low-Light Vision","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2308.06780","title":"Neural Networks at a Fraction with Pruned Quaternions","created":"2023-08-13","cited_by_count":1,"area":null},{"id":"2311.02995","title":"Zero-Shot Enhancement of Low-Light Image Based on Retinex Decomposition","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2402.13152","title":"AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2406.07840","title":"SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2510.08567","title":"MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2103.05993","title":"Wide Aspect Ratio Matching for Robust Face Detection","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2104.14126","title":"CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications","created":"2021-04-29","cited_by_count":0,"area":null},{"id":"2106.06971","title":"NLHD: A Pixel-Level Non-Local Retinex Model for Low-Light Image Enhancement","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2110.03302","title":"MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildings","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2110.03892","title":"Bounding-box deep calibration for high performance face detection","created":"2021-10-08","cited_by_count":0,"area":null}],"next_cursor":"100"}