{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"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":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"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":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"1808.01900","title":"DeepTAM: Deep Tracking and Mapping","created":"2018-08-06","cited_by_count":87},{"id":"2105.07014","title":"SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping","created":"2021-05-14","cited_by_count":74},{"id":"1906.06565","title":"Deep Set Prediction Networks","created":"2019-06-15","cited_by_count":71},{"id":"2204.08442","title":"Deep Equilibrium Optical Flow Estimation","created":"2022-04-18","cited_by_count":64},{"id":"2002.11433","title":"Efficient Semantic Video Segmentation with Per-frame Inference","created":"2020-02-26","cited_by_count":63},{"id":"2010.12152","title":"Generative Neurosymbolic Machines","created":"2020-10-23","cited_by_count":57},{"id":"2001.01102","title":"MushroomRL: Simplifying Reinforcement Learning Research","created":"2020-01-04","cited_by_count":50},{"id":"2012.00212","title":"UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning","created":"2020-12-01","cited_by_count":49},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"1911.09033","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","created":"2019-11-20","cited_by_count":40},{"id":"2204.00330","title":"DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow","created":"2022-04-01","cited_by_count":40},{"id":"2109.09904","title":"Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems","created":"2021-09-21","cited_by_count":36},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29},{"id":"1512.01286","title":"Adjusting for Chance Clustering Comparison Measures","created":"2015-12-03","cited_by_count":27},{"id":"2007.12348","title":"Unsupervised Discovery of 3D Physical Objects from Video","created":"2020-07-24","cited_by_count":27},{"id":"2204.07262","title":"Imposing Consistency for Optical Flow Estimation","created":"2022-04-14","cited_by_count":24},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23},{"id":"2104.04782","title":"Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation","created":"2021-04-10","cited_by_count":21},{"id":"1812.09533","title":"Temporal Hockey Action Recognition via Pose and Optical Flows","created":"2018-12-22","cited_by_count":13},{"id":"2004.02853","title":"Optical Flow Estimation in the Deep Learning Age","created":"2020-04-06","cited_by_count":13},{"id":"1805.07780","title":"Unsupervised Video Object Segmentation for Deep Reinforcement Learning","created":"2018-05-20","cited_by_count":11},{"id":"1902.09937","title":"Semantic Relational Object Tracking","created":"2019-02-26","cited_by_count":8},{"id":"1811.04407","title":"An initial attempt of combining visual selective attention with deep reinforcement learning","created":"2018-11-11","cited_by_count":4}],"next_cursor":null}