{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1708.01692","title":"Video Frame Interpolation via Adaptive Separable Convolution","created":"2017-08-05","cited_by_count":213},{"id":"2011.06294","title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation","created":"2020-11-12","cited_by_count":213},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1711.07837","title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","created":"2017-11-21","cited_by_count":202},{"id":"1703.07514","title":"Video Frame Interpolation via Adaptive Convolution","created":"2017-03-22","cited_by_count":158},{"id":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"2202.04901","title":"FILM: Frame Interpolation for Large Motion","created":"2022-02-10","cited_by_count":153},{"id":"2106.07286","title":"TimeLens: Event-based Video Frame Interpolation","created":"2021-06-14","cited_by_count":151},{"id":"1911.00627","title":"Quadratic video interpolation","created":"2019-11-02","cited_by_count":145},{"id":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"1907.10244","title":"AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation","created":"2019-07-24","cited_by_count":134},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126},{"id":"2111.13817","title":"Video Frame Interpolation Transformer","created":"2021-11-27","cited_by_count":123},{"id":"1810.08768","title":"MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement","created":"2018-10-20","cited_by_count":112},{"id":"2203.17191","title":"Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion","created":"2022-03-31","cited_by_count":111},{"id":"2205.14620","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","created":"2022-05-29","cited_by_count":109},{"id":"2108.06815","title":"Asymmetric Bilateral Motion Estimation for Video Frame Interpolation","created":"2021-08-15","cited_by_count":101},{"id":"2206.04647","title":"VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution","created":"2022-06-09","cited_by_count":101},{"id":"2012.08512","title":"FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation","created":"2020-12-15","cited_by_count":98},{"id":"2303.00440","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","created":"2023-03-01","cited_by_count":98},{"id":"2104.02495","title":"Deep Animation Video Interpolation in the Wild","created":"2021-04-06","cited_by_count":65},{"id":"2006.08070","title":"Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution","created":"2020-06-15","cited_by_count":63},{"id":"1804.00884","title":"PhaseNet for Video Frame Interpolation","created":"2018-04-03","cited_by_count":61},{"id":"1906.05928","title":"Unsupervised Video Interpolation Using Cycle Consistency","created":"2019-06-13","cited_by_count":44},{"id":"2007.11762","title":"All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling","created":"2020-07-23","cited_by_count":42},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42},{"id":"2204.03513","title":"Many-to-many Splatting for Efficient Video Frame Interpolation","created":"2022-04-07","cited_by_count":42},{"id":"2211.03456","title":"A Unified Pyramid Recurrent Network for Video Frame Interpolation","created":"2022-11-07","cited_by_count":39},{"id":"2203.13859","title":"TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation","created":"2022-03-25","cited_by_count":37},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32},{"id":"1910.11667","title":"Learning Multi-Human Optical Flow","created":"2019-10-24","cited_by_count":26},{"id":"2105.01237","title":"COMISR: Compression-Informed Video Super-Resolution","created":"2021-05-04","cited_by_count":26},{"id":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","cited_by_count":22},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19},{"id":"2206.08572","title":"Enhanced Bi-directional Motion Estimation for Video Frame Interpolation","created":"2022-06-17","cited_by_count":17},{"id":"2307.12558","title":"Revisiting Event-based Video Frame Interpolation","created":"2023-07-24","cited_by_count":3}],"next_cursor":null}