{"total":63,"rows":[{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"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":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"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":"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":"2103.09458","title":"Learning Discriminative Prototypes with Dynamic Time Warping","created":"2021-03-17","cited_by_count":23,"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":"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":"2109.14834","title":"IntentVizor: Towards Generic Query Guided Interactive Video Summarization","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2104.13473","title":"TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains","created":"2021-04-27","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":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10,"area":null},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10,"area":null},{"id":"2404.03477","title":"Towards Automated Movie Trailer Generation","created":"2024-04-04","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":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"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":"2311.12159","title":"Conditional Modeling Based Automatic Video Summarization","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2404.04511","title":"Cluster-based Video Summarization with Temporal Context Awareness","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2407.13933","title":"Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence","created":"2024-07-18","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":"2201.09049","title":"LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN","created":"2022-01-22","cited_by_count":4,"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":"2205.09068","title":"VRAG: Region Attention Graphs for Content-Based Video Retrieval","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2504.18689","title":"HierSum: A Global and Local Attention Mechanism for Video Summarization","created":"2025-04-25","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":"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":"2512.04426","title":"Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation","created":"2025-12-04","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":"2102.05811","title":"Audiovisual Highlight Detection in Videos","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2201.11345","title":"Exploring Global Diversity and Local Context for Video Summarization","created":"2022-01-27","cited_by_count":1,"area":null},{"id":"2209.05166","title":"Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark","created":"2022-09-12","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":"2309.06102","title":"Can we predict the Most Replayed data of video streaming platforms?","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2311.17940","title":"Scene Summarization: Clustering Scene Videos into Spatially Diverse Frames","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2405.10082","title":"An Integrated Framework for Multi-Granular Explanation of Video Summarization","created":"2024-05-16","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":"2506.10430","title":"MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2605.27067","title":"BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation","created":"2026-05-26","cited_by_count":1,"area":null},{"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":"2109.12581","title":"A Stacking Ensemble Approach for Supervised Video Summarization","created":"2021-09-26","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},{"id":"2408.01859","title":"Graph Unfolding and Sampling for Transitory Video Keyframe Selection via Gershgorin Disc Alignment","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2409.14724","title":"EDSNet: Efficient-DSNet for Video Summarization","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2410.03323","title":"Does SpatioTemporal information benefit Two video summarization benchmarks?","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2501.00882","title":"FullTransNet: Full Transformer with Local-Global Attention for Video Summarization","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2506.14854","title":"Efficient Retail Video Annotation: A Robust Key Frame Generation Approach for Product and Customer Interaction Analysis","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2602.14214","title":"HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming","created":"2026-02-15","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":"2609.39051","title":"TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight Detection","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}