{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2201.06503","title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","created":"2022-01-17","cited_by_count":334},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"2112.07068","title":"Score-Based Generative Modeling with Critically-Damped Langevin Diffusion","created":"2021-12-14","cited_by_count":233},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1609.07093","title":"Neural Photo Editing with Introspective Adversarial Networks","created":"2016-09-22","cited_by_count":109},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"1804.06055","title":"Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation","created":"2018-04-17","cited_by_count":106},{"id":"2104.14466","title":"3D Human Action Representation Learning via Cross-View Consistency Pursuit","created":"2021-04-29","cited_by_count":106},{"id":"1910.13321","title":"Semantic Object Accuracy for Generative Text-to-Image Synthesis","created":"2019-10-29","cited_by_count":89},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","cited_by_count":87},{"id":"2008.08171","title":"Learning to Generate Diverse Dance Motions with Transformer","created":"2020-08-18","cited_by_count":85},{"id":"1711.08682","title":"Deep Video Generation, Prediction and Completion of Human Action Sequences","created":"2017-11-23","cited_by_count":52},{"id":"1910.02212","title":"Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction","created":"2019-10-05","cited_by_count":50},{"id":"1704.02581","title":"Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks","created":"2017-04-09","cited_by_count":49},{"id":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2003.13042","title":"Omni-sourced Webly-supervised Learning for Video Recognition","created":"2020-03-29","cited_by_count":48},{"id":"1804.10652","title":"Human Motion Modeling using DVGANs","created":"2018-04-27","cited_by_count":45},{"id":"1907.13025","title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","created":"2019-07-30","cited_by_count":43},{"id":"1804.08254","title":"Memory Attention Networks for Skeleton-based Action Recognition","created":"2018-04-23","cited_by_count":36},{"id":"2007.14638","title":"COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network","created":"2020-07-29","cited_by_count":29},{"id":"2007.09268","title":"3D Human Shape Reconstruction from a Polarization Image","created":"2020-07-17","cited_by_count":28},{"id":"2203.04705","title":"FlexIT: Towards Flexible Semantic Image Translation","created":"2022-03-09","cited_by_count":28},{"id":"1704.05645","title":"Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn","created":"2017-04-19","cited_by_count":26},{"id":"2106.01603","title":"CT-Net: Channel Tensorization Network for Video Classification","created":"2021-06-03","cited_by_count":26},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24},{"id":"2011.11900","title":"CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature","created":"2020-11-24","cited_by_count":20},{"id":"1804.01194","title":"Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks","created":"2018-03-17","cited_by_count":19},{"id":"2203.15375","title":"A Style-aware Discriminator for Controllable Image Translation","created":"2022-03-29","cited_by_count":16},{"id":"2011.08652","title":"3D CNNs with Adaptive Temporal Feature Resolutions","created":"2020-11-17","cited_by_count":15},{"id":"2006.07743","title":"3DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Information","created":"2020-06-13","cited_by_count":13},{"id":"2004.14899","title":"Polarization Human Shape and Pose Dataset","created":"2020-04-30","cited_by_count":10},{"id":"2004.08352","title":"Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging","created":"2020-04-17","cited_by_count":7},{"id":"2011.11242","title":"Unsupervised domain adaptation based COVID-19 CT infection segmentation network","created":"2020-11-23","cited_by_count":5}],"next_cursor":null}