{"total":26,"rows":[{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"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":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"area":null},{"id":"2405.19465","title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","created":"2024-05-29","cited_by_count":16,"area":null},{"id":"2406.13165","title":"Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model","created":"2024-06-19","cited_by_count":16,"area":null},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15,"area":null},{"id":"2311.15769","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","created":"2023-11-27","cited_by_count":11,"area":null},{"id":"2409.13609","title":"MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension","created":"2024-09-20","cited_by_count":6,"area":null},{"id":"2306.12642","title":"TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter","created":"2023-06-22","cited_by_count":5,"area":null},{"id":"2405.06217","title":"DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2405.07046","title":"RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2410.09383","title":"Deep Transfer Learning: Model Framework and Error Analysis","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2312.06950","title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2404.18253","title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","created":"2024-04-28","cited_by_count":2,"area":null},{"id":"2405.15155","title":"CLIP model is an Efficient Online Lifelong Learner","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2409.11059","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2411.01975","title":"SPECTRUM: Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2505.16756","title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2501.10638","title":"A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2508.14812","title":"Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2603.04037","title":"DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.20429","title":"Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing","created":"2026-04-22","cited_by_count":0,"area":null}],"next_cursor":null}