{"total":93,"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":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"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":"2211.09120","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","created":"2022-11-16","cited_by_count":43,"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":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34,"area":null},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26,"area":null},{"id":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","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":"2201.04388","title":"OCSampler: Compressing Videos to One Clip with Single-step Sampling","created":"2022-01-12","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":"2209.02957","title":"A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels","created":"2022-09-07","cited_by_count":20,"area":null},{"id":"2301.00896","title":"Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos","created":"2023-01-03","cited_by_count":20,"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":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","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":"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":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2108.13872","title":"Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"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":"2309.11091","title":"Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval","created":"2023-09-20","cited_by_count":9,"area":null},{"id":"2404.03477","title":"Towards Automated Movie Trailer Generation","created":"2024-04-04","cited_by_count":9,"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":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2105.12532","title":"Unsupervised Video Summarization via Multi-source Features","created":"2021-05-26","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":"2109.01799","title":"PR-Net: Preference Reasoning for Personalized Video Highlight Detection","created":"2021-09-04","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":"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":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","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":"2303.08906","title":"VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression","created":"2023-03-15","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":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2210.08578","title":"Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices","created":"2022-10-16","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":"2104.06142","title":"Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning","created":"2021-04-06","cited_by_count":3,"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":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","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":"2311.03745","title":"Unsupervised Video Summarization via Iterative Training and Simplified GAN","created":"2023-11-07","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":"2504.18689","title":"HierSum: A Global and Local Attention Mechanism for Video Summarization","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2511.10953","title":"Language-Guided Graph Representation Learning for Video Summarization","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2203.15778","title":"Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method","created":"2022-03-29","cited_by_count":2,"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":"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":"2306.01395","title":"Masked Autoencoder for Unsupervised Video Summarization","created":"2023-06-02","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":"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":"2602.02630","title":"Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.14297","title":"RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360{\\deg}Image Quality Assessment","created":"2026-03-15","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":"2109.01309","title":"Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging","created":"2021-09-03","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":"2205.00694","title":"A Multi-stage deep architecture for summary generation of soccer videos","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2209.09033","title":"A Transferable and Automatic Tuning of Deep Reinforcement Learning for Cost Effective Phishing Detection","created":"2022-09-19","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":"2309.15683","title":"End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning","created":"2023-09-27","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":"2403.17727","title":"FastPerson: Enhancing Video Learning through Effective Video Summarization that Preserves Linguistic and Visual Contexts","created":"2024-03-26","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":"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":"2205.14042","title":"Reinforced Pedestrian Attribute Recognition with Group Optimization Reward","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2208.00620","title":"Software Package for Automated Analysis of Lung Ultrasound Videos","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2208.11307","title":"Visual Subtitle Feature Enhanced Video Outline Generation","created":"2022-08-24","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":"2406.13715","title":"Converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2408.12121","title":"Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysis","created":"2024-08-22","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":"2501.01094","title":"MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions","created":"2025-01-02","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":"2506.23714","title":"Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization","created":"2025-06-30","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}],"next_cursor":null}