{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"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":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"2111.13998","title":"Targeted Supervised Contrastive Learning for Long-Tailed Recognition","created":"2021-11-27","cited_by_count":132},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"1907.11879","title":"Multi-task Self-Supervised Learning for Human Activity Detection","created":"2019-07-27","cited_by_count":102},{"id":"2005.03572","title":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation","created":"2020-05-07","cited_by_count":98},{"id":"1909.08494","title":"Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity","created":"2019-09-18","cited_by_count":86},{"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":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68},{"id":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53},{"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},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","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":"2304.02970","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","created":"2023-04-06","cited_by_count":34},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31},{"id":"2104.00315","title":"Unsupervised Sound Localization via Iterative Contrastive Learning","created":"2021-04-01","cited_by_count":28},{"id":"2104.02215","title":"When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes","created":"2021-04-06","cited_by_count":23},{"id":"1901.01189","title":"Learning Sound Event Classifiers from Web Audio with Noisy Labels","created":"2019-01-04","cited_by_count":22},{"id":"2312.02428","title":"FreestyleRet: Retrieving Images from Style-Diversified Queries","created":"2023-12-05","cited_by_count":20},{"id":"2302.07702","title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision","created":"2023-02-15","cited_by_count":18},{"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":"2206.01948","title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","created":"2022-06-04","cited_by_count":16},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13},{"id":"2104.09946","title":"A cappella: Audio-visual Singing Voice Separation","created":"2021-04-20","cited_by_count":12},{"id":"2407.16638","title":"Unveiling and Mitigating Bias in Audio Visual Segmentation","created":"2024-07-23","cited_by_count":11},{"id":"2111.05526","title":"Space-Time Memory Network for Sounding Object Localization in Videos","created":"2021-11-10","cited_by_count":10},{"id":"2202.10372","title":"L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment","created":"2022-02-21","cited_by_count":10},{"id":"2408.05057","title":"SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation","created":"2024-08-09","cited_by_count":6},{"id":"2012.08282","title":"Robots Understanding Contextual Information in Human-Centered Environments using Weakly Supervised Mask Data Distillation","created":"2020-12-15","cited_by_count":5},{"id":"2210.05917","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","created":"2022-10-12","cited_by_count":3}],"next_cursor":null}