{"total":62,"rows":[{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99,"area":null},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"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":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2208.06773","title":"TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency","created":"2022-08-14","cited_by_count":35,"area":null},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34,"area":null},{"id":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26,"area":null},{"id":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23,"area":null},{"id":"2106.10528","title":"Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net","created":"2021-06-19","cited_by_count":22,"area":null},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21,"area":null},{"id":"2109.10559","title":"Hierarchical Multimodal Transformer to Summarize Videos","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2404.03398","title":"Scaling Up Video Summarization Pretraining with Large Language Models","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2204.04615","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10,"area":null},{"id":"2105.06441","title":"DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization","created":"2021-05-13","cited_by_count":8,"area":null},{"id":"2101.10514","title":"How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization","created":"2021-01-26","cited_by_count":6,"area":null},{"id":"2210.11707","title":"Video Summarization Overview","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2105.07667","title":"AudioVisual Video Summarization","created":"2021-05-17","cited_by_count":5,"area":null},{"id":"2211.10056","title":"Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization","created":"2022-11-18","cited_by_count":5,"area":null},{"id":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2404.10539","title":"VideoSAGE: Video Summarization with Graph Representation Learning","created":"2024-04-14","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":"2107.03783","title":"Use of Affective Visual Information for Summarization of Human-Centric Videos","created":"2021-07-08","cited_by_count":3,"area":null},{"id":"2405.08890","title":"Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2505.03319","title":"SD-VSum: A Method and Dataset for Script-Driven Video Summarization","created":"2025-05-06","cited_by_count":3,"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":"2306.01395","title":"Masked Autoencoder for Unsupervised Video Summarization","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","cited_by_count":2,"area":"ssm"},{"id":"2506.20588","title":"TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2509.16421","title":"AHA -- Predicting What Matters Next: Online Highlight Detection Without Looking Ahead","created":"2025-09-19","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":"2606.00664","title":"SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models","created":"2026-05-30","cited_by_count":2,"area":"wm"},{"id":"2201.11345","title":"Exploring Global Diversity and Local Context for Video Summarization","created":"2022-01-27","cited_by_count":1,"area":null},{"id":"2301.05213","title":"Learning to Summarize Videos by Contrasting Clips","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2406.16301","title":"UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2412.08357","title":"Video Summarization using Denoising Diffusion Probabilistic Model","created":"2024-12-11","cited_by_count":1,"area":"diffusion"},{"id":"2504.21831","title":"Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization","created":"2025-04-30","cited_by_count":1,"area":"mllm"},{"id":"2605.01659","title":"TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning","created":"2026-05-03","cited_by_count":1,"area":"deeprl"},{"id":"2607.25300","title":"MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2105.11131","title":"Unsupervised Video Summarization with a Convolutional Attentive Adversarial Network","created":"2021-05-24","cited_by_count":0,"area":null},{"id":"2108.04187","title":"Scaling New Peaks: A Viewership-centric Approach to Automated Content Curation","created":"2021-08-09","cited_by_count":0,"area":null},{"id":"2303.15993","title":"SELF-VS: Self-supervised Encoding Learning For Video Summarization","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2407.04258","title":"Reinforcement Learning for Unsupervised Video Summarization with Reward Generator Training","created":"2024-07-05","cited_by_count":0,"area":"alignment"},{"id":"2410.03323","title":"Does SpatioTemporal information benefit Two video summarization benchmarks?","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2411.04859","title":"A multi-purpose automatic editing system based on lecture semantics for remote education","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2505.23268","title":"Unsupervised Transcript-assisted Video Summarization and Highlight Detection","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2509.05604","title":"Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.05652","title":"SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.26569","title":"AdSum: Two-stream Audio-visual Summarization for Automated Video Advertisement Clipping","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2601.13974","title":"STEC: A Reference-Free Spatio-Temporal Entropy Coverage Metric for Evaluating Sampled Video Frames","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.10024","title":"LVSum: A Benchmark for Timestamp-Aware Long Video Summarization","created":"2026-04-11","cited_by_count":0,"area":"mllm"},{"id":"2605.19223","title":"HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2606.14762","title":"Scribby: A Multi-Level LLM Framework for Semantic Video Analysis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.13966","title":"SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.14790","title":"Zero-shot video highlight detection based on text descriptions and synthetic images","created":"2026-09-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.25837","title":"Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.39051","title":"TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight Detection","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}