{"total":14,"rows":[{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2305.18756","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2105.14207","title":"Maintaining Common Ground in Dynamic Environments","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2202.11847","title":"CAISE: Conversational Agent for Image Search and Editing","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2212.10935","title":"Commentary Generation from Data Records of Multiplayer Strategy Esports Game","created":"2022-12-21","cited_by_count":3,"area":null},{"id":"2311.12820","title":"MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2402.11875","title":"M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2212.10515","title":"CausalDialogue: Modeling Utterance-level Causality in Conversations","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2510.26978","title":"Semantic Frame Aggregation-based Transformer for Live Video Comment Generation","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2501.18324","title":"A Video-grounded Dialogue Dataset and Metric for Event-driven Activities","created":"2025-01-30","cited_by_count":0,"area":null}],"next_cursor":null}