{"total":25,"rows":[{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2106.06509","title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching","created":"2021-06-11","cited_by_count":26,"area":null},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"area":null},{"id":"2104.08910","title":"Towards Open-World Text-Guided Face Image Generation and Manipulation","created":"2021-04-18","cited_by_count":25,"area":null},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22,"area":null},{"id":"2306.16650","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","created":"2023-06-29","cited_by_count":19,"area":null},{"id":"2208.09843","title":"CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval","created":"2022-08-21","cited_by_count":13,"area":null},{"id":"2102.04980","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","created":"2021-02-09","cited_by_count":12,"area":null},{"id":"2208.04254","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2402.03658","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2110.00335","title":"Geometry Attention Transformer with Position-aware LSTMs for Image Captioning","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2502.07391","title":"Target-Augmented Shared Fusion-based Multimodal Sarcasm Explanation Generation","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2203.05349","title":"Two-stream Hierarchical Similarity Reasoning for Image-text Matching","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2106.05876","title":"Data Fusion for Deep Learning on Transport Mode Detection: A Case Study","created":"2021-05-31","cited_by_count":1,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2209.08759","title":"Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2304.02488","title":"SCB-Dataset: A Dataset for Detecting Student and Teacher Classroom Behavior","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2203.06937","title":"Modelling word learning and recognition using visually grounded speech","created":"2022-03-14","cited_by_count":0,"area":null},{"id":"2208.11061","title":"Large-Scale Traffic Congestion Prediction based on Multimodal Fusion and Representation Mapping","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2310.02528","title":"On the Cognition of Visual Question Answering Models and Human Intelligence: A Comparative Study","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2411.06872","title":"Multi-Modal interpretable automatic video captioning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2411.07305","title":"PICZL: Image-based Photometric Redshifts for AGN","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2505.01255","title":"PREMISE: Matching-based Prediction for Accurate Review Recommendation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2507.12677","title":"Data Transformation Strategies to Remove Heterogeneity","created":"2025-07-16","cited_by_count":0,"area":null}],"next_cursor":null}