{"total":23,"rows":[{"id":"2110.06510","title":"The Dawn of Quantum Natural Language Processing","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2105.14538","title":"Longer Version for \"Deep Context-Encoding Network for Retinal Image Captioning\"","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2206.08016","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2307.01945","title":"Query-based Video Summarization with Pseudo Label Supervision","created":"2023-07-04","cited_by_count":13,"area":null},{"id":"2408.01723","title":"A Novel Evaluation Framework for Image2Text Generation","created":"2024-08-03","cited_by_count":11,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2405.05109","title":"QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs","created":"2024-05-08","cited_by_count":9,"area":null},{"id":"2305.00455","title":"Causalainer: Causal Explainer for Automatic Video Summarization","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2309.15739","title":"Experience and Evidence are the eyes of an excellent summarizer! Towards Knowledge Infused Multi-modal Clinical Conversation Summarization","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2311.12159","title":"Conditional Modeling Based Automatic Video Summarization","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2407.19041","title":"Optimizing Numerical Estimation and Operational Efficiency in the Legal Domain through Large Language Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2307.01947","title":"Causal Video Summarizer for Video Exploration","created":"2023-07-04","cited_by_count":4,"area":null},{"id":"2405.05039","title":"Reviewing Intelligent Cinematography: AI research for camera-based video production","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2510.08458","title":"SummDiff: Generative Modeling of Video Summarization with Diffusion","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2204.08352","title":"MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2501.04764","title":"Video Summarisation with Incident and Context Information using Generative AI","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2603.01169","title":"TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2105.10005","title":"Robust Unsupervised Multi-Object Tracking in Noisy Environments","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2509.12534","title":"DeepEyeNet: Generating Medical Report for Retinal Images","created":"2025-09-16","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":"2401.05134","title":"Yes, this is what I was looking for! Towards Multi-modal Medical Consultation Concern Summary Generation","created":"2024-01-10","cited_by_count":0,"area":null},{"id":"2401.16076","title":"Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas","created":"2024-01-29","cited_by_count":0,"area":null}],"next_cursor":null}