{"total":23,"rows":[{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2301.02228","title":"MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology","created":"2023-01-05","cited_by_count":149,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2209.07118","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","created":"2022-09-15","cited_by_count":51,"area":null},{"id":"2109.08039","title":"A Survey on Temporal Sentence Grounding in Videos","created":"2021-09-16","cited_by_count":29,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2304.14204","title":"Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining","created":"2023-04-26","cited_by_count":11,"area":null},{"id":"2311.17122","title":"Large Model Based Referring Camouflaged Object Detection","created":"2023-11-28","cited_by_count":8,"area":null},{"id":"2111.08896","title":"Achieving Human Parity on Visual Question Answering","created":"2021-11-17","cited_by_count":5,"area":null},{"id":"2206.05555","title":"A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training","created":"2022-06-11","cited_by_count":5,"area":null},{"id":"2210.09550","title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2305.16328","title":"Semantic Composition in Visually Grounded Language Models","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2603.16671","title":"$x^2$-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2305.00052","title":"Click-Feedback Retrieval","created":"2023-04-28","cited_by_count":0,"area":null},{"id":"2409.15744","title":"ViKL: A Mammography Interpretation Framework via Multimodal Aggregation of Visual-knowledge-linguistic Features","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2503.07456","title":"Anatomy-Aware Conditional Image-Text Retrieval","created":"2025-03-10","cited_by_count":0,"area":null}],"next_cursor":null}