{"list":"other","total":56,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80},{"id":"1608.07017","title":"Ambient Sound Provides Supervision for Visual Learning","created":"2016-08-25","cited_by_count":78},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"1902.07473","title":"Dual-modality seq2seq network for audio-visual event localization","created":"2019-02-20","cited_by_count":72},{"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":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"1908.11602","title":"Recursive Visual Sound Separation Using Minus-Plus Net","created":"2019-08-30","cited_by_count":53},{"id":"2305.01836","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","created":"2023-05-03","cited_by_count":53},{"id":"2303.17056","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","created":"2023-03-29","cited_by_count":52},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32},{"id":"2403.07938","title":"Text-to-Audio Generation Synchronized with Videos","created":"2024-03-08","cited_by_count":28},{"id":"2312.01017","title":"Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling","created":"2023-12-02","cited_by_count":24},{"id":"2309.05281","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","created":"2023-09-11","cited_by_count":22},{"id":"2305.19458","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition","created":"2023-05-30","cited_by_count":21},{"id":"2305.12903","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","created":"2023-05-22","cited_by_count":19},{"id":"2311.15080","title":"Weakly-Supervised Audio-Visual Segmentation","created":"2023-11-25","cited_by_count":19},{"id":"2403.07952","title":"AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production","created":"2024-03-12","cited_by_count":13},{"id":"2406.04930","title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers","created":"2024-06-07","cited_by_count":11},{"id":"2407.13095","title":"Audio-visual Generalized Zero-shot Learning the Easy Way","created":"2024-07-18","cited_by_count":7},{"id":"2407.03736","title":"Semantic Grouping Network for Audio Source Separation","created":"2024-07-04","cited_by_count":5},{"id":"2409.00486","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","created":"2024-08-31","cited_by_count":3},{"id":"2405.07202","title":"Unified Video-Language Pre-training with Synchronized Audio","created":"2024-05-12","cited_by_count":2}],"next_cursor":null}