{"list":"other","total":54,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"1811.06152","title":"Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos","created":"2018-11-15","cited_by_count":155},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"1810.06125","title":"Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding","created":"2018-10-14","cited_by_count":101},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"1901.03360","title":"Unsupervised Moving Object Detection via Contextual Information Separation","created":"2019-01-10","cited_by_count":72},{"id":"1604.00136","title":"It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos","created":"2016-04-01","cited_by_count":71},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2207.02206","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","created":"2022-07-05","cited_by_count":63},{"id":"2011.11630","title":"Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation","created":"2020-11-23","cited_by_count":62},{"id":"2102.02629","title":"Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency","created":"2021-02-04","cited_by_count":58},{"id":"2010.12152","title":"Generative Neurosymbolic Machines","created":"2020-10-23","cited_by_count":57},{"id":"1612.07217","title":"Learning Motion Patterns in Videos","created":"2016-12-21","cited_by_count":53},{"id":"1902.03715","title":"Towards Segmenting Anything That Moves","created":"2019-02-11","cited_by_count":51},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50},{"id":"2111.06394","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","created":"2021-11-11","cited_by_count":45},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42},{"id":"1712.01127","title":"Learning to Segment Moving Objects","created":"2017-12-01","cited_by_count":39},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"2103.15346","title":"Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection","created":"2021-03-29","cited_by_count":28},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19},{"id":"2112.01502","title":"Dimensions of Motion: Monocular Prediction through Flow Subspaces","created":"2021-12-02","cited_by_count":10},{"id":"2110.11275","title":"Self-Supervised Monocular Scene Decomposition and Depth Estimation","created":"2021-10-21","cited_by_count":8},{"id":"2004.09197","title":"LSM: Learning Subspace Minimization for Low-level Vision","created":"2020-04-20","cited_by_count":6}],"next_cursor":null}