{"total":61,"rows":[{"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":"2103.00128","title":"PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection","created":"2021-02-27","cited_by_count":51,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26,"area":null},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","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":"2109.10559","title":"Hierarchical Multimodal Transformer to Summarize Videos","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2312.01061","title":"Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction","created":"2023-12-02","cited_by_count":17,"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":"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":"2105.06441","title":"DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization","created":"2021-05-13","cited_by_count":8,"area":null},{"id":"2305.00455","title":"Causalainer: Causal Explainer for Automatic Video Summarization","created":"2023-04-30","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":"2204.03734","title":"MHMS: Multimodal Hierarchical Multimedia Summarization","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2210.04722","title":"Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment","created":"2022-10-10","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":"2502.07096","title":"Lotus: Creating Short Videos From Long Videos With Abstractive and Extractive Summarization","created":"2025-02-10","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":"2508.15389","title":"Spiking Variational Graph Representation Inference for Video Summarization","created":"2025-08-21","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":"2307.01947","title":"Causal Video Summarizer for Video Exploration","created":"2023-07-04","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":"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":"2109.02625","title":"ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2203.13166","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","created":"2022-03-24","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":"2207.11838","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","created":"2022-07-24","cited_by_count":3,"area":null},{"id":"2210.08481","title":"TLDW: Extreme Multimodal Summarisation of News Videos","created":"2022-10-16","cited_by_count":3,"area":null},{"id":"2309.12574","title":"Classification of Alzheimers Disease with Deep Learning on Eye-tracking Data","created":"2023-09-22","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":"2509.01439","title":"SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2207.08352","title":"Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention","created":"2022-07-18","cited_by_count":2,"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":"2311.17940","title":"Scene Summarization: Clustering Scene Videos into Spatially Diverse Frames","created":"2023-11-28","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":"2410.04449","title":"Video Summarization Techniques: A Comprehensive Review","created":"2024-10-06","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":"2507.16020","title":"Micromobility Flow Prediction: A Bike Sharing Station-level Study via Multi-level Spatial-Temporal Attention Neural Network","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2101.11249","title":"Efficient Video Summarization Framework using EEG and Eye-tracking Signals","created":"2021-01-27","cited_by_count":0,"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":"2109.14695","title":"Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding","created":"2021-09-29","cited_by_count":0,"area":null},{"id":"2206.15192","title":"Privacy-preserving household load forecasting based on non-intrusive load monitoring: A federated deep learning approach","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2212.01040","title":"Role of Audio in Audio-Visual Video Summarization","created":"2022-12-02","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":"2307.07214","title":"Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2307.07682","title":"Learning Subjective Time-Series Data via Utopia Label Distribution Approximation","created":"2023-07-15","cited_by_count":0,"area":null},{"id":"2307.08145","title":"Self-Attention Based Generative Adversarial Networks For Unsupervised Video Summarization","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2401.10254","title":"Beyond the Frame: Single and mutilple video summarization method with user-defined length","created":"2023-12-23","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":"2409.14724","title":"EDSNet: Efficient-DSNet for Video Summarization","created":"2024-09-23","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":"2509.05604","title":"Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization","created":"2025-09-06","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}],"next_cursor":null}