{"total":60,"rows":[{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113,"area":"diffusion"},{"id":"2108.08755","title":"Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks","created":"2021-08-19","cited_by_count":69,"area":null},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2109.05569","title":"MovieCuts: A New Dataset and Benchmark for Cut Type Recognition","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2304.06116","title":"AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection","created":"2023-04-12","cited_by_count":23,"area":null},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22,"area":"mllm"},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2402.16143","title":"Cinematographic Camera Diffusion Model","created":"2024-02-25","cited_by_count":18,"area":"diffusion"},{"id":"2201.05277","title":"Boundary-aware Self-supervised Learning for Video Scene Segmentation","created":"2022-01-14","cited_by_count":17,"area":null},{"id":"2504.08296","title":"Generative AI for Film Creation: A Survey of Recent Advances","created":"2025-04-11","cited_by_count":17,"area":"diffusion"},{"id":"2112.10194","title":"UnweaveNet: Unweaving Activity Stories","created":"2021-12-19","cited_by_count":14,"area":null},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","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":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2202.10650","title":"Movies2Scenes: Using Movie Metadata to Learn Scene Representation","created":"2022-02-22","cited_by_count":11,"area":null},{"id":"2305.18756","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2205.05487","title":"Scene Consistency Representation Learning for Video Scene Segmentation","created":"2022-05-11","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"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":"2210.05840","title":"LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2304.05634","title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2507.02790","title":"From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding","created":"2025-07-03","cited_by_count":6,"area":null},{"id":"2603.15685","title":"DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression","created":"2026-03-15","cited_by_count":6,"area":"inference"},{"id":"2301.00135","title":"TeViS:Translating Text Synopses to Video Storyboards","created":"2022-12-31","cited_by_count":5,"area":null},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2207.01241","title":"OS-MSL: One Stage Multimodal Sequential Link Framework for Scene Segmentation and Classification","created":"2022-07-04","cited_by_count":4,"area":null},{"id":"2303.14768","title":"Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies","created":"2023-03-26","cited_by_count":4,"area":null},{"id":"2308.11185","title":"MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2308.14922","title":"Automated Conversion of Music Videos into Lyric Videos","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2109.07951","title":"Overview of Tencent Multi-modal Ads Video Understanding Challenge","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2209.12694","title":"Multi-modal Video Chapter Generation","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2210.16644","title":"Unsupervised Audio-Visual Lecture Segmentation","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2503.01201","title":"Parameter-free Video Segmentation for Vision and Language Understanding","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2206.04888","title":"AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2212.04700","title":"Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2512.21778","title":"Scene-VLM: Multimodal Video Scene Segmentation via Vision-Language Models","created":"2025-12-25","cited_by_count":2,"area":"mllm"},{"id":"2108.12868","title":"A Multimodal Framework for Video Ads Understanding","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2306.02252","title":"MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2309.10561","title":"A multimodal deep learning architecture for smoking detection with a small data approach","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2506.12623","title":"MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2508.02480","title":"MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.16190","title":"ComicScene154: A Scene Dataset for Comic Analysis","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2604.27975","title":"TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2108.09215","title":"Video Ads Content Structuring by Combining Scene Confidence Prediction and Tagging","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2203.13281","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2312.00220","title":"Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2412.17238","title":"Modality-Aware Shot Relating and Comparing for Video Scene Detection","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2602.15381","title":"Automatic Funny Scene Extraction from Long-form Cinematic Videos","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2608.23011","title":"Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.28699","title":"Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.29287","title":"PERSIST: Persistent-State Discrimination for Shot Boundary Detection","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}