{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"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":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"1404.1100","title":"A Tutorial on Principal Component Analysis","created":"2014-04-03","cited_by_count":141},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","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":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","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":"2305.17011","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","created":"2023-05-26","cited_by_count":57},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","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":"2404.08767","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","created":"2024-04-12","cited_by_count":52},{"id":"2307.12616","title":"CTVIS: Consistent Training for Online Video Instance Segmentation","created":"2023-07-24","cited_by_count":51},{"id":"2403.02969","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","created":"2024-03-05","cited_by_count":39},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38},{"id":"2308.08288","title":"Improving Audio-Visual Segmentation with Bidirectional Generation","created":"2023-08-16","cited_by_count":37},{"id":"2307.13236","title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation","created":"2023-07-25","cited_by_count":33},{"id":"2308.10175","title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","created":"2023-08-20","cited_by_count":32},{"id":"2307.16579","title":"Contrastive Conditional Latent Diffusion for Audio-visual Segmentation","created":"2023-07-31","cited_by_count":31},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31},{"id":"2309.09501","title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","created":"2023-09-18","cited_by_count":29},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20},{"id":"2311.15080","title":"Weakly-Supervised Audio-Visual Segmentation","created":"2023-11-25","cited_by_count":19},{"id":"2104.08506","title":"Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations","created":"2021-04-17","cited_by_count":18},{"id":"1807.00983","title":"Long Activity Video Understanding using Functional Object-Oriented Network","created":"2018-07-03","cited_by_count":8},{"id":"2210.05242","title":"Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization","created":"2022-10-11","cited_by_count":7},{"id":"2402.02327","title":"Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues","created":"2024-02-04","cited_by_count":7},{"id":"2307.00536","title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","created":"2023-07-02","cited_by_count":5},{"id":"1808.03413","title":"Inverse Augmented Reality: A Virtual Agent's Perspective","created":"2018-08-10","cited_by_count":3}],"next_cursor":null}