{"total":623,"rows":[{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181,"area":null},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126,"area":null},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100,"area":null},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83,"area":null},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"id":"2104.00239","title":"Positive Sample Propagation along the Audio-Visual Event Line","created":"2021-04-01","cited_by_count":69,"area":null},{"id":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"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":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2205.10683","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","created":"2022-05-21","cited_by_count":48,"area":null},{"id":"2303.12930","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","created":"2023-03-22","cited_by_count":46,"area":null},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"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":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39,"area":null},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39,"area":null},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2308.08288","title":"Improving Audio-Visual Segmentation with Bidirectional Generation","created":"2023-08-16","cited_by_count":37,"area":null},{"id":"2309.07929","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","created":"2023-09-13","cited_by_count":37,"area":null},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"area":null},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2304.02970","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","created":"2023-04-06","cited_by_count":34,"area":null},{"id":"2304.08981","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","created":"2023-04-18","cited_by_count":33,"area":null},{"id":"2307.13236","title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation","created":"2023-07-25","cited_by_count":33,"area":null},{"id":"2308.14395","title":"UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization","created":"2023-08-28","cited_by_count":33,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2203.13412","title":"Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes","created":"2022-03-25","cited_by_count":31,"area":null},{"id":"2103.09154","title":"Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition","created":"2021-03-16","cited_by_count":30,"area":null},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30,"area":null},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2309.09501","title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","created":"2023-09-18","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":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29,"area":null},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28,"area":null},{"id":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2104.07123","title":"The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stress","created":"2021-04-14","cited_by_count":27,"area":null},{"id":"2112.14005","title":"Towards Relatable Explainable AI with the Perceptual Process","created":"2021-12-28","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":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27,"area":null},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"area":null},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2110.04176","title":"PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2312.06462","title":"Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2407.08126","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2303.10849","title":"Multi-modal Facial Affective Analysis based on Masked Autoencoder","created":"2023-03-20","cited_by_count":23,"area":null},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2407.11820","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","created":"2024-07-16","cited_by_count":23,"area":null},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23,"area":null},{"id":"2101.06053","title":"The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements","created":"2021-01-15","cited_by_count":22,"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":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2207.07646","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","created":"2022-07-15","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21,"area":null},{"id":"2308.04978","title":"Transferable Models for Bioacoustics with Human Language Supervision","created":"2023-08-09","cited_by_count":21,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null}],"next_cursor":"100"}