{"total":18,"rows":[{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"area":null},{"id":"2509.03883","title":"Human Motion Video Generation: A Survey","created":"2025-09-04","cited_by_count":25,"area":null},{"id":"2312.15190","title":"SAIC: Integration of Speech Anonymization and Identity Classification","created":"2023-12-23","cited_by_count":7,"area":null},{"id":"2507.02900","title":"Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions","created":"2025-06-23","cited_by_count":6,"area":null},{"id":"2404.12400","title":"Efflex: Efficient and Flexible Pipeline for Spatio-Temporal Trajectory Graph Modeling and Representation Learning","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2404.08021","title":"VeTraSS: Vehicle Trajectory Similarity Search Through Graph Modeling and Representation Learning","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2404.10901","title":"CrossGP: Cross-Day Glucose Prediction Excluding Physiological Information","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2404.12605","title":"GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2404.11924","title":"Toward Short-Term Glucose Prediction Solely Based on CGM Time Series","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2501.06524","title":"Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2504.03135","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2411.18267","title":"Incomplete Multi-view Multi-label Classification via a Dual-level Contrastive Learning Framework","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2507.19225","title":"Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.01161","title":"Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.01164","title":"A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2511.05432","title":"Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2603.06071","title":"Text-Driven Emotionally Continuous Talking Face Generation","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}