{"total":113,"rows":[{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"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":"2404.07610","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","created":"2024-04-11","cited_by_count":36,"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":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19,"area":null},{"id":"2104.08506","title":"Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations","created":"2021-04-17","cited_by_count":18,"area":null},{"id":"2105.09601","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","created":"2021-05-20","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2207.08625","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","created":"2022-07-18","cited_by_count":17,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2310.00608","title":"Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning","created":"2023-10-01","cited_by_count":14,"area":null},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2404.02755","title":"DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement","created":"2024-04-03","cited_by_count":13,"area":null},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2405.07354","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","created":"2024-05-12","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12,"area":"mllm"},{"id":"2206.12845","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","created":"2022-06-26","cited_by_count":11,"area":"moe"},{"id":"2301.05997","title":"Exploiting Auxiliary Caption for Video Grounding","created":"2023-01-15","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9,"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":"2404.08229","title":"Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2412.12791","title":"Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2112.09976","title":"Tell me what you see: A zero-shot action recognition method based on natural language descriptions","created":"2021-12-18","cited_by_count":7,"area":null},{"id":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2306.13968","title":"Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents","created":"2023-06-24","cited_by_count":7,"area":null},{"id":"2310.00670","title":"A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2407.07801","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2112.08455","title":"Dense Video Captioning Using Unsupervised Semantic Information","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2202.05728","title":"Deep soccer captioning with transformer: dataset, semantics-related losses, and multi-level evaluation","created":"2022-02-11","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":"2306.14644","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2410.08255","title":"Investigating Representation Universality: Case Study on Genealogical Representations","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2509.04602","title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2510.09274","title":"MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2601.06559","title":"ArrowGEV: Grounding Events in Video via Learning the Arrow of Time","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2204.05976","title":"Video Captioning: a comparative review of where we are and which could be the route","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2205.03534","title":"Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information","created":"2022-05-07","cited_by_count":3,"area":null},{"id":"2206.12849","title":"Semantic Role Aware Correlation Transformer for Text to Video Retrieval","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2207.11838","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","created":"2022-07-24","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":"2403.19221","title":"Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2408.14441","title":"Attend-Fusion: Efficient Audio-Visual Fusion for Video Classification","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","cited_by_count":3,"area":null},{"id":"2412.11467","title":"Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.24096","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2507.13318","title":"HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2111.10146","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","created":"2021-11-19","cited_by_count":2,"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":"2406.14206","title":"Live Video Captioning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2411.04933","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2510.14617","title":"Shot2Tactic-Caption: Multi-Scale Captioning of Badminton Videos for Tactical Understanding","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2101.05806","title":"Exploration of Visual Features and their weighted-additive fusion for Video Captioning","created":"2021-01-14","cited_by_count":1,"area":null},{"id":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2304.12561","title":"TCR: Short Video Title Generation and Cover Selection with Attention Refinement","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2312.06699","title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2402.17758","title":"ADL4D: Towards A Contextually Rich Dataset for 4D Activities of Daily Living","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2507.09945","title":"ESG-Net: Event-Aware Semantic Guided Network for Dense Audio-Visual Event Localization","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2603.05437","title":"SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.11439","title":"Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.11460","title":"Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null}],"next_cursor":"100"}