{"total":281,"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":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"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":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84,"area":null},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84,"area":null},{"id":"2103.00484","title":"Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward","created":"2021-02-25","cited_by_count":82,"area":null},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2306.15162","title":"YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus","created":"2023-06-27","cited_by_count":75,"area":null},{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2103.15796","title":"Adaptive Methods for Real-World Domain Generalization","created":"2021-03-29","cited_by_count":66,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61,"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":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2405.00334","title":"A Survey on Deep Active Learning: Recent Advances and New Frontiers","created":"2024-05-01","cited_by_count":54,"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":"2212.14593","title":"NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling","created":"2022-12-30","cited_by_count":51,"area":null},{"id":"2101.10803","title":"ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning","created":"2021-01-26","cited_by_count":50,"area":null},{"id":"2105.09284","title":"SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images","created":"2021-04-25","cited_by_count":50,"area":null},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49,"area":null},{"id":"2105.01047","title":"Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery","created":"2021-05-03","cited_by_count":45,"area":null},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2106.08827","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","created":"2021-06-16","cited_by_count":39,"area":null},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38,"area":null},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"area":null},{"id":"2106.02342","title":"ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency","created":"2021-06-04","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":"2406.09386","title":"SimGen: Simulator-conditioned Driving Scene Generation","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2307.14619","title":"Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior","created":"2023-07-27","cited_by_count":33,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2104.02710","title":"The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions","created":"2021-04-06","cited_by_count":31,"area":null},{"id":"2207.01398","title":"Large-scale Robustness Analysis of Video Action Recognition Models","created":"2022-07-04","cited_by_count":29,"area":null},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"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":"2201.12888","title":"A Dataset for Medical Instructional Video Classification and Question Answering","created":"2022-01-30","cited_by_count":26,"area":null},{"id":"2311.18827","title":"Motion-Conditioned Image Animation for Video Editing","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","cited_by_count":26,"area":null},{"id":"2206.13964","title":"Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark","created":"2022-06-28","cited_by_count":25,"area":null},{"id":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2110.03414","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2304.01143","title":"Use Your Head: Improving Long-Tail Video Recognition","created":"2023-04-03","cited_by_count":22,"area":null},{"id":"2506.17774","title":"PhysiX: A Foundation Model for Physics Simulations","created":"2025-06-21","cited_by_count":22,"area":null},{"id":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2404.05392","title":"T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos","created":"2024-04-08","cited_by_count":21,"area":null},{"id":"2107.09262","title":"FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2203.03990","title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","created":"2022-03-08","cited_by_count":20,"area":null},{"id":"2503.14963","title":"Continual Multimodal Contrastive Learning","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2503.19740","title":"LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings","created":"2025-03-25","cited_by_count":20,"area":null},{"id":"2102.07624","title":"RMS-Net: Regression and Masking for Soccer Event Spotting","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2203.09566","title":"Leveraging Adversarial Examples to Quantify Membership Information Leakage","created":"2022-03-17","cited_by_count":19,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17,"area":null},{"id":"2201.05277","title":"Boundary-aware Self-supervised Learning for Video Scene Segmentation","created":"2022-01-14","cited_by_count":17,"area":null},{"id":"2106.00209","title":"Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning","created":"2021-06-01","cited_by_count":16,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"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":"2404.01891","title":"ASTRA: An Action Spotting TRAnsformer for Soccer Videos","created":"2024-04-02","cited_by_count":16,"area":null},{"id":"2104.06517","title":"Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2101.08734","title":"Clairvoyant Prefetching for Distributed Machine Learning I/O","created":"2021-01-21","cited_by_count":14,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2203.04038","title":"Gait Recognition with Mask-based Regularization","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2301.09595","title":"Zorro: the masked multimodal transformer","created":"2023-01-23","cited_by_count":13,"area":null},{"id":"2407.10947","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2503.06268","title":"Get In Video: Add Anything You Want to the Video","created":"2025-03-08","cited_by_count":12,"area":null},{"id":"2110.04119","title":"A Multi-viewpoint Outdoor Dataset for Human Action Recognition","created":"2021-10-07","cited_by_count":11,"area":null},{"id":"2203.15381","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11,"area":null},{"id":"2406.08079","title":"A$^{2}$-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder","created":"2024-06-12","cited_by_count":11,"area":null},{"id":"2407.16638","title":"Unveiling and Mitigating Bias in Audio Visual Segmentation","created":"2024-07-23","cited_by_count":11,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2105.12855","title":"Multi-Modal Semantic Inconsistency Detection in Social Media News Posts","created":"2021-05-26","cited_by_count":10,"area":null}],"next_cursor":"100"}