{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2309.11497","title":"FreeU: Free Lunch in Diffusion U-Net","created":"2023-09-20","cited_by_count":196},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2111.03600","title":"Hybrid Spectrogram and Waveform Source Separation","created":"2021-11-05","cited_by_count":91},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"1704.08292","title":"Deep Cross-Modal Audio-Visual Generation","created":"2017-04-26","cited_by_count":63},{"id":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","cited_by_count":49},{"id":"2402.10294","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","created":"2024-02-15","cited_by_count":47},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46},{"id":"1902.06634","title":"Contextual Encoder-Decoder Network for Visual Saliency Prediction","created":"2019-02-18","cited_by_count":44},{"id":"2012.06170","title":"ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction","created":"2020-12-11","cited_by_count":43},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29},{"id":"2309.15977","title":"Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields","created":"2023-09-27","cited_by_count":23},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"2301.12688","title":"Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production","created":"2023-01-30","cited_by_count":21},{"id":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21},{"id":"2308.06979","title":"The Sound Demixing Challenge 2023 $\\unicode{x2013}$ Music Demixing Track","created":"2023-08-14","cited_by_count":20},{"id":"2410.07463","title":"Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation","created":"2024-10-09","cited_by_count":19},{"id":"2207.08759","title":"Style Transfer of Audio Effects with Differentiable Signal Processing","created":"2022-07-18","cited_by_count":18},{"id":"2211.02247","title":"Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects","created":"2022-11-04","cited_by_count":18},{"id":"2406.05983","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","created":"2024-06-10","cited_by_count":14},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12},{"id":"1811.12214","title":"Play as You Like: Timbre-enhanced Multi-modal Music Style Transfer","created":"2018-11-28","cited_by_count":11},{"id":"2204.10125","title":"Physical Modeling using Recurrent Neural Networks with Fast Convolutional Layers","created":"2022-04-21","cited_by_count":9},{"id":"2410.24151","title":"Scaling Concept With Text-Guided Diffusion Models","created":"2024-10-31","cited_by_count":8},{"id":"2010.14151","title":"Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators","created":"2020-10-27","cited_by_count":7},{"id":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6},{"id":"2407.08889","title":"Diff-MST: Differentiable Mixing Style Transfer","created":"2024-07-11","cited_by_count":6},{"id":"1810.06603","title":"Modeling of nonlinear audio effects with end-to-end deep neural networks","created":"2018-10-15","cited_by_count":5},{"id":"2107.13634","title":"Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization","created":"2021-07-28","cited_by_count":5},{"id":"2407.07275","title":"Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support","created":"2024-07-09","cited_by_count":5}],"next_cursor":null}