{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"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":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"2303.17056","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","created":"2023-03-29","cited_by_count":52},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"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":"2303.11302","title":"Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning","created":"2023-03-20","cited_by_count":47},{"id":"2206.12772","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","created":"2022-06-26","cited_by_count":44},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41},{"id":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32},{"id":"1911.09649","title":"Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications","created":"2019-11-20","cited_by_count":31},{"id":"2202.06406","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","created":"2022-02-13","cited_by_count":19},{"id":"2404.01751","title":"T-VSL: Text-Guided Visual Sound Source Localization in Mixtures","created":"2024-04-02","cited_by_count":19},{"id":"2406.05629","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","created":"2024-06-09","cited_by_count":17},{"id":"2211.01966","title":"MarginNCE: Robust Sound Localization with a Negative Margin","created":"2022-11-03","cited_by_count":16},{"id":"2007.05722","title":"Do We Need Sound for Sound Source Localization?","created":"2020-07-11","cited_by_count":15},{"id":"2203.04099","title":"VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer","created":"2022-03-08","cited_by_count":14},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14},{"id":"2403.17420","title":"Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge","created":"2024-03-26","cited_by_count":14},{"id":"2310.15676","title":"Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation","created":"2023-10-24","cited_by_count":12},{"id":"2108.00443","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","created":"2021-08-01","cited_by_count":8},{"id":"2407.13676","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","created":"2024-07-18","cited_by_count":8},{"id":"2502.00358","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","created":"2025-02-01","cited_by_count":6},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5},{"id":"2204.05156","title":"How to Listen? Rethinking Visual Sound Localization","created":"2022-04-11","cited_by_count":4},{"id":"2306.00489","title":"Speech inpainting: Context-based speech synthesis guided by video","created":"2023-06-01","cited_by_count":4},{"id":"2410.01020","title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio","created":"2024-10-01","cited_by_count":4},{"id":"2408.16448","title":"Enhancing Sound Source Localization via False Negative Elimination","created":"2024-08-29","cited_by_count":3},{"id":"2106.15909","title":"Effect of acoustic scene complexity and visual scene representation on auditory perception in virtual audio-visual environments","created":"2021-06-30","cited_by_count":2},{"id":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","cited_by_count":2},{"id":"2407.01774","title":"Audio-Visual Approach For Multimodal Concurrent Speaker Detection","created":"2024-07-01","cited_by_count":1}],"next_cursor":null}