{"total":181,"rows":[{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128,"area":null},{"id":"2109.04290","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","created":"2021-09-09","cited_by_count":116,"area":"moe"},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108,"area":null},{"id":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104,"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":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82,"area":"mllm"},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2112.00656","title":"Object-aware Video-language Pre-training for Retrieval","created":"2021-12-01","cited_by_count":57,"area":null},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"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":"2305.12140","title":"Movie101: A New Movie Understanding Benchmark","created":"2023-05-20","cited_by_count":25,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2301.11357","title":"Multimodal Event Transformer for Image-guided Story Ending Generation","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","cited_by_count":20,"area":null},{"id":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2210.10828","title":"Grounded Video Situation Recognition","created":"2022-10-19","cited_by_count":13,"area":null},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2507.12566","title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","created":"2025-07-16","cited_by_count":13,"area":"mllm"},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","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":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2202.12626","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","created":"2022-02-25","cited_by_count":11,"area":"lr"},{"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":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2203.07086","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"area":null},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9,"area":null},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2406.11890","title":"Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2105.07122","title":"Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues","created":"2021-05-15","cited_by_count":8,"area":null},{"id":"2109.12264","title":"More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering","created":"2021-09-25","cited_by_count":8,"area":null},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2404.15909","title":"Learning Long-form Video Prior via Generative Pre-Training","created":"2024-04-24","cited_by_count":8,"area":null},{"id":"2506.02448","title":"VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2510.00808","title":"What You See is What You Ask: Evaluating Audio Descriptions","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2311.01233","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2212.04231","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","created":"2022-12-08","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":"2310.03311","title":"Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2409.19865","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2604.11102","title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","created":"2026-04-13","cited_by_count":6,"area":"mllm"},{"id":"2210.10820","title":"VTC: Improving Video-Text Retrieval with User Comments","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2211.05895","title":"Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense","created":"2022-11-10","cited_by_count":5,"area":null},{"id":"2301.00135","title":"TeViS:Translating Text Synopses to Video Storyboards","created":"2022-12-31","cited_by_count":5,"area":null}],"next_cursor":"100"}