{"list":"other","total":57,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"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":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"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":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"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":"2111.14821","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","created":"2021-11-29","cited_by_count":135},{"id":"2103.07941","title":"Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion","created":"2021-03-14","cited_by_count":129},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"2007.08270","title":"Kernelized Memory Network for Video Object Segmentation","created":"2020-07-16","cited_by_count":111},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"1802.01218","title":"Efficient Video Object Segmentation via Network Modulation","created":"2018-02-04","cited_by_count":98},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"1701.05384","title":"FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos","created":"2017-01-19","cited_by_count":77},{"id":"2004.01800","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","created":"2020-04-03","cited_by_count":77},{"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":"2109.11404","title":"Hierarchical Memory Matching Network for Video Object Segmentation","created":"2021-09-23","cited_by_count":72},{"id":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68},{"id":"2008.05789","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","created":"2020-08-13","cited_by_count":63},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63},{"id":"2307.09356","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","created":"2023-07-18","cited_by_count":62},{"id":"1804.00389","title":"Low-Latency Video Semantic Segmentation","created":"2018-04-02","cited_by_count":61},{"id":"2112.13528","title":"Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction","created":"2021-12-27","cited_by_count":57},{"id":"2008.11516","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","created":"2020-08-26","cited_by_count":56},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","cited_by_count":53},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2307.13537","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","created":"2023-07-25","cited_by_count":48},{"id":"2308.08288","title":"Improving Audio-Visual Segmentation with Bidirectional Generation","created":"2023-08-16","cited_by_count":37},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27},{"id":"2309.03473","title":"Temporal Collection and Distribution for Referring Video Object Segmentation","created":"2023-09-07","cited_by_count":27},{"id":"1912.11844","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","created":"2019-12-26","cited_by_count":18},{"id":"2306.13337","title":"Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning","created":"2023-06-23","cited_by_count":14},{"id":"2112.01695","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","created":"2021-12-03","cited_by_count":13},{"id":"2203.09093","title":"Semantic-aligned Fusion Transformer for One-shot Object Detection","created":"2022-03-17","cited_by_count":13},{"id":"2110.10599","title":"Video Instance Segmentation by Instance Flow Assembly","created":"2021-10-20","cited_by_count":12},{"id":"2210.00132","title":"Alignment-guided Temporal Attention for Video Action Recognition","created":"2022-09-30","cited_by_count":10},{"id":"2211.14419","title":"Panoramic Video Salient Object Detection with Ambisonic Audio Guidance","created":"2022-11-26","cited_by_count":9}],"next_cursor":null}