{"list":"other","total":87,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"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":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"2003.13045","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","created":"2020-03-29","cited_by_count":120},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","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":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"1903.05612","title":"RVOS: End-to-End Recurrent Network for Video Object Segmentation","created":"2019-03-13","cited_by_count":88},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86},{"id":"1909.11895","title":"Joint-task Self-supervised Learning for Temporal Correspondence","created":"2019-09-26","cited_by_count":80},{"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":"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":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"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":"2204.07151","title":"Deformable Sprites for Unsupervised Video Decomposition","created":"2022-04-14","cited_by_count":61},{"id":"2203.12614","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","created":"2022-03-23","cited_by_count":56},{"id":"1612.07217","title":"Learning Motion Patterns in Videos","created":"2016-12-21","cited_by_count":53},{"id":"2307.15958","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","created":"2023-07-29","cited_by_count":53},{"id":"1902.03715","title":"Towards Segmenting Anything That Moves","created":"2019-02-11","cited_by_count":51},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51},{"id":"1910.10895","title":"Anchor Diffusion for Unsupervised Video Object Segmentation","created":"2019-10-24","cited_by_count":50},{"id":"2006.12373","title":"Learning Physical Graph Representations from Visual Scenes","created":"2020-06-22","cited_by_count":50},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49},{"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":"2307.05014","title":"Test-Time Training on Video Streams","created":"2023-07-11","cited_by_count":37},{"id":"2308.14710","title":"VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation","created":"2023-08-28","cited_by_count":37},{"id":"2209.03138","title":"Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation","created":"2022-09-04","cited_by_count":35},{"id":"2001.05425","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","created":"2020-01-15","cited_by_count":34},{"id":"2201.02074","title":"EM-driven unsupervised learning for efficient motion segmentation","created":"2022-01-06","cited_by_count":33},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"2209.03712","title":"Unsupervised Video Object Segmentation via Prototype Memory Network","created":"2022-09-08","cited_by_count":30},{"id":"2006.07034","title":"Benchmarking Unsupervised Object Representations for Video Sequences","created":"2020-06-12","cited_by_count":27},{"id":"1809.03137","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","created":"2018-09-10","cited_by_count":22},{"id":"1801.00908","title":"Instance Embedding Transfer to Unsupervised Video Object Segmentation","created":"2018-01-03","cited_by_count":19},{"id":"2311.04414","title":"Learning the What and How of Annotation in Video Object Segmentation","created":"2023-11-08","cited_by_count":19},{"id":"1703.10667","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","created":"2017-03-30","cited_by_count":18},{"id":"2103.10391","title":"Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild","created":"2021-03-18","cited_by_count":18},{"id":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","cited_by_count":16},{"id":"2209.09341","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","created":"2022-09-19","cited_by_count":15},{"id":"1903.11779","title":"BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames","created":"2019-03-28","cited_by_count":14},{"id":"2208.01159","title":"BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation","created":"2022-08-01","cited_by_count":14},{"id":"2210.00221","title":"Motion-inductive Self-supervised Object Discovery in Videos","created":"2022-10-01","cited_by_count":14},{"id":"2211.12036","title":"Dual Prototype Attention for Unsupervised Video Object Segmentation","created":"2022-11-22","cited_by_count":14},{"id":"2309.09858","title":"Unsupervised Open-Vocabulary Object Localization in Videos","created":"2023-09-18","cited_by_count":13},{"id":"2107.12569","title":"Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation","created":"2021-07-27","cited_by_count":11},{"id":"2012.12554","title":"Efficient video annotation with visual interpolation and frame selection guidance","created":"2020-12-23","cited_by_count":10},{"id":"2308.11239","title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","created":"2023-08-22","cited_by_count":8},{"id":"1906.07851","title":"Key Instance Selection for Unsupervised Video Object Segmentation","created":"2019-06-18","cited_by_count":5},{"id":"2011.12372","title":"Play Fair: Frame Attributions in Video Models","created":"2020-11-24","cited_by_count":4},{"id":"2303.08132","title":"InstMove: Instance Motion for Object-centric Video Segmentation","created":"2023-03-14","cited_by_count":3},{"id":"2307.04392","title":"FODVid: Flow-guided Object Discovery in Videos","created":"2023-07-10","cited_by_count":3}],"next_cursor":null}