{"total":142,"rows":[{"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":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131,"area":null},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"id":"2310.17577","title":"Global Structure-Aware Diffusion Process for Low-Light Image Enhancement","created":"2023-10-26","cited_by_count":92,"area":"diffusion"},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2111.09748","title":"The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video","created":"2021-11-18","cited_by_count":66,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2109.13357","title":"WarpedGANSpace: Finding non-linear RBF paths in GAN latent space","created":"2021-09-27","cited_by_count":48,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2412.04037","title":"INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36,"area":"diffusion"},{"id":"2202.12972","title":"FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment","created":"2022-02-25","cited_by_count":33,"area":null},{"id":"2107.00396","title":"MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis","created":"2021-07-01","cited_by_count":32,"area":null},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"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":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2308.09534","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","created":"2023-08-18","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":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","cited_by_count":26,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"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":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2402.12636","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","created":"2024-02-20","cited_by_count":21,"area":null},{"id":"2106.11145","title":"FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2404.09819","title":"3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2109.10471","title":"The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimation","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2202.12951","title":"Model Attribution of Face-swap Deepfake Videos","created":"2022-02-25","cited_by_count":17,"area":null},{"id":"2304.12944","title":"Latent Traversals in Generative Models as Potential Flows","created":"2023-04-25","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":"2202.12883","title":"Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video","created":"2022-02-25","cited_by_count":16,"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":"2102.05447","title":"Searching for Alignment in Face Recognition","created":"2021-02-10","cited_by_count":12,"area":null},{"id":"2412.17574","title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","created":"2024-12-23","cited_by_count":11,"area":"mllm"},{"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":"2503.12042","title":"Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing","created":"2025-03-15","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":"2403.14974","title":"AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2412.17295","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2503.08276","title":"PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net","created":"2025-03-11","cited_by_count":8,"area":null},{"id":"2203.03984","title":"Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2408.11593","title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2101.03251","title":"Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training","created":"2021-01-08","cited_by_count":6,"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":"2206.07458","title":"VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection","created":"2022-06-15","cited_by_count":6,"area":null},{"id":"2311.05669","title":"Multi-Modal Gaze Following in Conversational Scenarios","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2505.21954","title":"Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2104.00432","title":"Anchor Pruning for Object Detection","created":"2021-04-01","cited_by_count":5,"area":null},{"id":"2207.01906","title":"Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2307.08012","title":"Householder Projector for Unsupervised Latent Semantics Discovery","created":"2023-07-16","cited_by_count":5,"area":null},{"id":"2407.02394","title":"Similarity Distance-Based Label Assignment for Tiny Object Detection","created":"2024-07-02","cited_by_count":5,"area":null},{"id":"2412.08594","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2101.05260","title":"Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning","created":"2021-01-13","cited_by_count":4,"area":null},{"id":"2205.15895","title":"From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2301.10180","title":"A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2309.01183","title":"Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction","created":"2023-09-03","cited_by_count":4,"area":null},{"id":"2312.06400","title":"DiT-Head: High-Resolution Talking Head Synthesis using Diffusion Transformers","created":"2023-12-11","cited_by_count":4,"area":"diffusion"},{"id":"2407.18245","title":"VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset","created":"2024-07-25","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":"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":"2101.04756","title":"A Compact Deep Learning Model for Face Spoofing Detection","created":"2021-01-12","cited_by_count":3,"area":null},{"id":"2104.04443","title":"A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline","created":"2021-04-09","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2201.10047","title":"Are Commercial Face Detection Models as Biased as Academic Models?","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2209.10930","title":"MGTR: End-to-End Mutual Gaze Detection with Transformer","created":"2022-09-22","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":"2303.11267","title":"Rethinking the backbone architecture for tiny object detection","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","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":"2501.00328","title":"VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition","created":"2024-12-31","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":"2105.10104","title":"EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2110.10953","title":"MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation","created":"2021-10-21","cited_by_count":2,"area":null},{"id":"2203.05178","title":"An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2204.03559","title":"Practical Digital Disguises: Leveraging Face Swaps to Protect Patient Privacy","created":"2022-04-07","cited_by_count":2,"area":null},{"id":"2206.04590","title":"GASP: Gated Attention For Saliency Prediction","created":"2022-06-09","cited_by_count":2,"area":null},{"id":"2207.08380","title":"Visual Representations of Physiological Signals for Fake Video Detection","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2304.04068","title":"Word-level Persian Lipreading Dataset","created":"2023-04-08","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":"2310.14221","title":"The Importance of Anti-Aliasing in Tiny Object Detection","created":"2023-10-22","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":"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":"2506.11477","title":"FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes","created":"2025-06-13","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":"2110.02124","title":"FacialFilmroll: High-resolution multi-shot video editing","created":"2021-10-05","cited_by_count":1,"area":null},{"id":"2111.00660","title":"Evaluation of Human and Machine Face Detection using a Novel Distinctive Human Appearance Dataset","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2203.08765","title":"Efficient conditioned face animation using frontally-viewed embedding","created":"2022-03-16","cited_by_count":1,"area":null}],"next_cursor":"100"}