{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2101.02388","title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","created":"2021-01-07","cited_by_count":348},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2112.07068","title":"Score-Based Generative Modeling with Critically-Damped Langevin Diffusion","created":"2021-12-14","cited_by_count":233},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2103.10428","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","created":"2021-03-18","cited_by_count":220},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2202.05830","title":"Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality","created":"2022-02-11","cited_by_count":182},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"1901.00212","title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","created":"2019-01-01","cited_by_count":163},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2005.09704","title":"Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting","created":"2020-05-19","cited_by_count":124},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2008.04899","title":"Visual Imitation Made Easy","created":"2020-08-11","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"1912.04344","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","created":"2019-12-09","cited_by_count":107},{"id":"2008.03737","title":"Recurrent Feature Reasoning for Image Inpainting","created":"2020-08-09","cited_by_count":107},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"1912.04443","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","created":"2019-12-10","cited_by_count":105},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"2209.03954","title":"Learning to Generate Realistic LiDAR Point Clouds","created":"2022-09-08","cited_by_count":93},{"id":"1901.05945","title":"Foreground-aware Image Inpainting","created":"2019-01-17","cited_by_count":90},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"2011.06507","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","created":"2020-11-12","cited_by_count":82},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2008.08324","title":"FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration","created":"2020-08-19","cited_by_count":73},{"id":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"1805.03356","title":"SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting","created":"2018-05-09","cited_by_count":58},{"id":"1806.08482","title":"Video Inpainting by Jointly Learning Temporal Structure and Spatial Details","created":"2018-06-22","cited_by_count":58},{"id":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2110.09936","title":"NeuralDiff: Segmenting 3D objects that move in egocentric videos","created":"2021-10-19","cited_by_count":57},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"1503.05528","title":"Video Inpainting of Complex Scenes","created":"2015-03-18","cited_by_count":41},{"id":"2009.05721","title":"Short-Term and Long-Term Context Aggregation Network for Video Inpainting","created":"2020-09-12","cited_by_count":35},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"1909.12507","title":"Region-wise Generative Adversarial ImageInpainting for Large Missing Areas","created":"2019-09-27","cited_by_count":18},{"id":"2305.03036","title":"3D Reconstruction of Objects in Hands without Real World 3D Supervision","created":"2023-05-04","cited_by_count":12},{"id":"2204.12458","title":"Learning Value Functions from Undirected State-only Experience","created":"2022-04-26","cited_by_count":8},{"id":"2208.06807","title":"Semi-Supervised Video Inpainting with Cycle Consistency Constraints","created":"2022-08-14","cited_by_count":8}],"next_cursor":null}