{"list":"other","total":100,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"2406.18583","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","created":"2024-06-05","cited_by_count":132},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117},{"id":"2101.02402","title":"Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs","created":"2021-01-07","cited_by_count":110},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2008.07142","title":"POP909: A Pop-song Dataset for Music Arrangement Generation","created":"2020-08-17","cited_by_count":83},{"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},{"id":"1802.02774","title":"Learning to score the figure skating sports videos","created":"2018-02-08","cited_by_count":73},{"id":"1605.02677","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","created":"2016-05-09","cited_by_count":71},{"id":"2503.08638","title":"YuE: Scaling Open Foundation Models for Long-Form Music Generation","created":"2025-03-11","cited_by_count":71},{"id":"2011.11731","title":"HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms","created":"2020-11-23","cited_by_count":64},{"id":"1612.08727","title":"Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications","created":"2016-12-27","cited_by_count":61},{"id":"2011.06801","title":"A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions","created":"2020-11-13","cited_by_count":56},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"2006.14348","title":"Audeo: Audio Generation for a Silent Performance Video","created":"2020-06-23","cited_by_count":47},{"id":"2007.15474","title":"Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling","created":"2020-07-29","cited_by_count":45},{"id":"2206.07771","title":"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation","created":"2022-06-15","cited_by_count":44},{"id":"2211.12112","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark","created":"2022-11-22","cited_by_count":41},{"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},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37},{"id":"2311.00968","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","created":"2023-11-02","cited_by_count":37},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37},{"id":"2307.10304","title":"Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls","created":"2023-07-19","cited_by_count":35},{"id":"2410.16162","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning","created":"2024-10-21","cited_by_count":34},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34},{"id":"2402.07204","title":"ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning","created":"2024-02-11","cited_by_count":33},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27},{"id":"2311.11255","title":"M$^{2}$UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models","created":"2023-11-19","cited_by_count":24},{"id":"2405.11913","title":"Diff-BGM: A Diffusion Model for Video Background Music Generation","created":"2024-05-20","cited_by_count":23},{"id":"2012.03478","title":"Multi-Instrumentalist Net: Unsupervised Generation of Music from Body Movements","created":"2020-12-07","cited_by_count":22},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18},{"id":"2305.01319","title":"Long-Term Rhythmic Video Soundtracker","created":"2023-05-02","cited_by_count":17},{"id":"2107.06252","title":"Dance2Music: Automatic Dance-driven Music Generation","created":"2021-07-13","cited_by_count":16},{"id":"2503.07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","created":"2025-03-10","cited_by_count":16},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15},{"id":"2501.08809","title":"XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework","created":"2025-01-15","cited_by_count":15},{"id":"2410.12957","title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","created":"2024-10-16","cited_by_count":14},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14},{"id":"2306.13512","title":"DISCO-10M: A Large-Scale Music Dataset","created":"2023-06-23","cited_by_count":13},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13},{"id":"2108.12290","title":"Music Composition with Deep Learning: A Review","created":"2021-08-27","cited_by_count":12},{"id":"2401.17800","title":"Dance-to-Music Generation with Encoder-based Textual Inversion","created":"2024-01-31","cited_by_count":12},{"id":"1704.06761","title":"Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint","created":"2017-04-22","cited_by_count":9},{"id":"2308.12982","title":"A Survey of AI Music Generation Tools and Models","created":"2023-08-24","cited_by_count":9},{"id":"2412.06296","title":"VidMusician: Video-to-Music Generation with Semantic-Rhythmic Alignment via Hierarchical Visual Features","created":"2024-12-09","cited_by_count":9},{"id":"2501.09972","title":"GVMGen: A General Video-to-Music Generation Model with Hierarchical Attentions","created":"2025-01-17","cited_by_count":9},{"id":"1904.00150","title":"Learning Affective Correspondence between Music and Image","created":"2019-03-30","cited_by_count":8},{"id":"2410.03879","title":"SONIQUE: Video Background Music Generation Using Unpaired Audio-Visual Data","created":"2024-10-04","cited_by_count":8},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8},{"id":"2405.02801","title":"Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models","created":"2024-05-05","cited_by_count":7},{"id":"2409.11904","title":"Finding the Subjective Truth: Collecting 2 Million Votes for Comprehensive Gen-AI Model Evaluation","created":"2024-09-18","cited_by_count":7},{"id":"2412.09428","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","created":"2024-12-12","cited_by_count":6},{"id":"2503.08147","title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips","created":"2025-03-11","cited_by_count":5},{"id":"2211.05543","title":"Vis2Mus: Exploring Multimodal Representation Mapping for Controllable Music Generation","created":"2022-11-10","cited_by_count":4},{"id":"1708.05851","title":"Image2song: Song Retrieval via Bridging Image Content and Lyric Words","created":"2017-08-19","cited_by_count":3},{"id":"2411.07539","title":"Harmonizing Pixels and Melodies: Maestro-Guided Film Score Generation and Composition Style Transfer","created":"2024-11-12","cited_by_count":2}],"next_cursor":null}