{"total":99,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2206.03789","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","created":"2022-06-08","cited_by_count":50,"area":null},{"id":"2111.14745","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","created":"2021-11-29","cited_by_count":49,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"area":"mllm"},{"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":"2302.06232","title":"Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data","created":"2023-02-13","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":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2311.00968","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","created":"2023-11-02","cited_by_count":37,"area":null},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","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":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2209.02485","title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors","created":"2022-09-06","cited_by_count":30,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"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":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21,"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":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","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":"2303.09756","title":"Video Action Recognition with Attentive Semantic Units","created":"2023-03-17","cited_by_count":12,"area":"mllm"},{"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":"2311.15619","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","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":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","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":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2604.04875","title":"DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2403.08049","title":"TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks","created":"2024-03-12","cited_by_count":6,"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":"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":"2303.07519","title":"Architext: Language-Driven Generative Architecture Design","created":"2023-03-13","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":"2404.10539","title":"VideoSAGE: Video Summarization with Graph Representation Learning","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2410.05586","title":"TeaserGen: Generating Teasers for Long Documentaries","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2510.08458","title":"SummDiff: Generative Modeling of Video Summarization with Diffusion","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2210.16644","title":"Unsupervised Audio-Visual Lecture Segmentation","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2302.13173","title":"MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models","created":"2023-02-25","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":"2411.03531","title":"Personalized Video Summarization by Multimodal Video Understanding","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2503.00364","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion","created":"2025-03-01","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":"2505.03319","title":"SD-VSum: A Method and Dataset for Script-Driven Video Summarization","created":"2025-05-06","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":"2509.01439","title":"SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization","created":"2025-09-01","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":"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":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","cited_by_count":2,"area":"ssm"},{"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":"2509.25745","title":"FinCap: Topic-Aligned Captions for Short-Form Financial YouTube Videos","created":"2025-09-30","cited_by_count":2,"area":"mllm"},{"id":"2512.04426","title":"Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2603.01169","title":"TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2308.10554","title":"Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations","created":"2023-08-21","cited_by_count":1,"area":null},{"id":"2310.19554","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2310.19743","title":"Tell Me What Is Good About This Property: Leveraging Reviews For Segment-Personalized Image Collection Summarization","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2312.01575","title":"A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2405.11487","title":"\"Previously on ...\" From Recaps to Story Summarization","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2408.05363","title":"AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge","created":"2024-07-25","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":"2501.07983","title":"V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2504.21831","title":"Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization","created":"2025-04-30","cited_by_count":1,"area":"mllm"},{"id":"2505.18880","title":"REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing","created":"2025-05-24","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":"2510.26978","title":"Semantic Frame Aggregation-based Transformer for Live Video Comment Generation","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2605.01659","title":"TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning","created":"2026-05-03","cited_by_count":1,"area":"deeprl"},{"id":"2605.27067","title":"BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation","created":"2026-05-26","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":"2208.11307","title":"Visual Subtitle Feature Enhanced Video Outline Generation","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2303.12068","title":"Machine Learning for Brain Disorders: Transformers and Visual Transformers","created":"2023-03-21","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":"2407.04258","title":"Reinforcement Learning for Unsupervised Video Summarization with Reward Generator Training","created":"2024-07-05","cited_by_count":0,"area":"alignment"},{"id":"2410.03323","title":"Does SpatioTemporal information benefit Two video summarization benchmarks?","created":"2024-10-04","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":"2509.05604","title":"Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.05652","title":"SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.17501","title":"Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarization","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2512.11399","title":"Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction","created":"2025-12-12","cited_by_count":0,"area":"mllm"},{"id":"2602.11004","title":"Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.29631","title":"Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.10024","title":"LVSum: A Benchmark for Timestamp-Aware Long Video Summarization","created":"2026-04-11","cited_by_count":0,"area":"mllm"},{"id":"2605.09507","title":"Uncertainty-Aware and Decoder-Aligned Learning for Video Summarization","created":"2026-05-10","cited_by_count":0,"area":"alignment"},{"id":"2605.19578","title":"Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.17994","title":"HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization","created":"2026-07-20","cited_by_count":0,"area":"mllm"},{"id":"2608.22313","title":"Adapting Dense Vision-Language Relationships for Multi-label Classification with Partial Label","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.08331","title":"Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2609.25837","title":"Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31873","title":"CueKFS: Agentic Cue-Driven Keyframe Selection for Long Video Understanding","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.33083","title":"dKFD: Phase-Structured Evidence Allocation for Fixed-Budget Localized Event Understanding","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}