{"total":70,"rows":[{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"area":null},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2304.13265","title":"StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos","created":"2023-04-26","cited_by_count":37,"area":null},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2401.16702","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","created":"2024-01-30","cited_by_count":34,"area":null},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21,"area":null},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2212.13738","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","created":"2022-12-28","cited_by_count":15,"area":null},{"id":"2210.04889","title":"Turbo Training with Token Dropout","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13,"area":null},{"id":"2306.02728","title":"Background-aware Moment Detection for Video Moment Retrieval","created":"2023-06-05","cited_by_count":13,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2303.12370","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","created":"2023-03-22","cited_by_count":10,"area":null},{"id":"2303.13800","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","created":"2023-03-24","cited_by_count":10,"area":null},{"id":"2303.16990","title":"What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions","created":"2023-03-29","cited_by_count":10,"area":null},{"id":"2309.13237","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","created":"2023-09-23","cited_by_count":10,"area":null},{"id":"2312.14055","title":"Multi-Sentence Grounding for Long-term Instructional Video","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2309.05451","title":"Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval","created":"2023-09-11","cited_by_count":9,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2506.24124","title":"Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives","created":"2025-06-30","cited_by_count":7,"area":null},{"id":"2409.16145","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2403.14870","title":"VidLA: Video-Language Alignment at Scale","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2312.11024","title":"Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2311.15075","title":"Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding","created":"2023-11-25","cited_by_count":3,"area":null},{"id":"2507.17844","title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2406.13092","title":"Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2505.16479","title":"Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2507.21945","title":"Attention-Driven Multimodal Alignment for Long-term Action Quality Assessment","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2512.08094","title":"Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2402.02335","title":"Video Editing for Video Retrieval","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2408.07600","title":"Disentangle and denoise: Tackling context misalignment for video moment retrieval","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2505.16425","title":"$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2602.24275","title":"Hierarchical Action Learning for Weakly-Supervised Action Segmentation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.25163","title":"SportSkills: Physical Skill Learning from Sports Instructional Videos","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2311.15964","title":"Efficient Pre-training for Localized Instruction Generation of Videos","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2411.07584","title":"Grounded Video Caption Generation","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2503.16467","title":"Enhancing Explainability with Multimodal Context Representations for Smarter Robots","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2506.00667","title":"Scene Detection Policies and Keyframe Extraction Strategies for Large-Scale Video Analysis","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2604.26565","title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2607.05095","title":"FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}