{"total":71,"rows":[{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"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":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83,"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":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","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":"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":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"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":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","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":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2112.10194","title":"UnweaveNet: Unweaving Activity Stories","created":"2021-12-19","cited_by_count":14,"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":"2403.11463","title":"Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding","created":"2024-03-18","cited_by_count":10,"area":null},{"id":"2507.12062","title":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","created":"2025-07-16","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":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","cited_by_count":7,"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":"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":"2501.12254","title":"Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos","created":"2025-01-21","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":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","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":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2506.10807","title":"Prompts to Summaries: Zero-Shot Language-Guided Video Summarization with Large Language and Video Models","created":"2025-06-12","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":"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":"2207.08352","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":"2309.09405","title":"Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2505.06557","title":"Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining","created":"2025-05-10","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":"2601.05495","title":"MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding","created":"2026-01-09","cited_by_count":2,"area":"mllm"},{"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":"2301.05213","title":"Learning to Summarize Videos by Contrasting Clips","created":"2023-01-12","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":"2312.02616","title":"Facilitating the Production of Well-tailored Video Summaries for Sharing on Social Media","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2410.14087","title":"Your Interest, Your Summaries: Query-Focused Long Video Summarization","created":"2024-10-17","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":"2412.18386","title":"Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos","created":"2024-12-24","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":"2512.17435","title":"ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","created":"2025-12-19","cited_by_count":1,"area":"mllm"},{"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":"2208.11307","title":"Visual Subtitle Feature Enhanced Video Outline Generation","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2208.11885","title":"Visualizing the Passage of Time with Video Temporal Pyramids","created":"2022-08-25","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":"2305.16801","title":"Motion-Based Sign Language Video Summarization using Curvature and Torsion","created":"2023-05-26","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":"2506.23714","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},{"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"}],"next_cursor":null}