{"total":52,"rows":[{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45,"area":"diffusion"},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2409.01156","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","created":"2024-09-02","cited_by_count":40,"area":"inference"},{"id":"2403.17998","title":"Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval","created":"2024-03-26","cited_by_count":33,"area":null},{"id":"2305.12218","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","created":"2023-05-20","cited_by_count":32,"area":null},{"id":"2401.10588","title":"DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval","created":"2024-01-19","cited_by_count":26,"area":null},{"id":"2601.12768","title":"Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval","created":"2026-01-19","cited_by_count":23,"area":null},{"id":"2312.02428","title":"FreestyleRet: Retrieving Images from Style-Diversified Queries","created":"2023-12-05","cited_by_count":20,"area":null},{"id":"2501.02807","title":"AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene","created":"2025-01-06","cited_by_count":19,"area":null},{"id":"2401.15652","title":"Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2411.14901","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","created":"2024-11-22","cited_by_count":18,"area":"mllm"},{"id":"2405.13824","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2503.10111","title":"Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2405.17829","title":"LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models","created":"2024-05-28","cited_by_count":11,"area":"diffusion"},{"id":"2402.17532","title":"Retrieval is Accurate Generation","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2407.10528","title":"Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation","created":"2024-07-15","cited_by_count":10,"area":"diffusion"},{"id":"2504.13035","title":"Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval","created":"2025-04-17","cited_by_count":8,"area":null},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2305.10049","title":"TG-VQA: Ternary Game of Video Question Answering","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2503.10526","title":"NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2403.14870","title":"VidLA: Video-Language Alignment at Scale","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2501.16373","title":"Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2507.02316","title":"Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2605.27894","title":"Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs","created":"2026-05-27","cited_by_count":5,"area":"lr"},{"id":"2311.03742","title":"3DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusion","created":"2023-11-07","cited_by_count":4,"area":"diffusion"},{"id":"2406.14938","title":"Towards Retrieval Augmented Generation over Large Video Libraries","created":"2024-06-21","cited_by_count":4,"area":"rag"},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2509.04773","title":"Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2503.17417","title":"Generative Modeling of Class Probability for Multi-Modal Representation Learning","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2601.21193","title":"Generative Recall, Dense Reranking: Learning Multi-View Semantic IDs for Efficient Text-to-Video Retrieval","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2604.03653","title":"Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2308.15109","title":"DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection","created":"2023-08-29","cited_by_count":2,"area":"diffusion"},{"id":"2312.11578","title":"Diffusion-Based Particle-DETR for BEV Perception","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2409.10025","title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval","created":"2024-09-16","cited_by_count":2,"area":"diffusion"},{"id":"2501.17718","title":"Learning Semantic Facial Descriptors for Accurate Face Animation","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2506.03589","title":"BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2504.01591","title":"Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.06543","title":"DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion","created":"2025-04-09","cited_by_count":1,"area":"diffusion"},{"id":"2505.05721","title":"Semantic-Space-Intervened Diffusive Alignment for Visual Classification","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2505.12499","title":"Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2510.10180","title":"TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2305.03614","title":"Denoising-Contrastive Alignment for Continuous Sign Language Recognition","created":"2023-05-05","cited_by_count":0,"area":null},{"id":"2402.07955","title":"ProtIR: Iterative Refinement between Retrievers and Predictors for Protein Function Annotation","created":"2024-02-10","cited_by_count":0,"area":null},{"id":"2402.17156","title":"TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation","created":"2024-02-27","cited_by_count":0,"area":"diffusion"},{"id":"2508.01711","title":"GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2508.02340","title":"Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2605.00826","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2607.20984","title":"Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}