{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1803.11365","title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","created":"2018-03-30","cited_by_count":218},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"id":"2104.03176","title":"On Self-Contact and Human Pose","created":"2021-04-07","cited_by_count":89},{"id":"2011.11534","title":"Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation","created":"2020-11-23","cited_by_count":81},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"1810.09617","title":"How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval","created":"2018-10-23","cited_by_count":74},{"id":"1311.3715","title":"Recognizing Image Style","created":"2013-11-15","cited_by_count":64},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64},{"id":"2206.11404","title":"The ArtBench Dataset: Benchmarking Generative Models with Artworks","created":"2022-06-22","cited_by_count":64},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"1910.12032","title":"HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation","created":"2019-10-26","cited_by_count":50},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50},{"id":"2302.01593","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","created":"2023-02-03","cited_by_count":48},{"id":"1704.08614","title":"BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography","created":"2017-04-27","cited_by_count":43},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"2103.06175","title":"Regressive Domain Adaptation for Unsupervised Keypoint Detection","created":"2021-03-10","cited_by_count":34},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34},{"id":"2203.08713","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","created":"2022-03-16","cited_by_count":29},{"id":"1810.02569","title":"Weakly Supervised Object Detection in Artworks","created":"2018-10-05","cited_by_count":27},{"id":"2110.06901","title":"A Survey on Deep Learning for Skeleton-Based Human Animation","created":"2021-10-13","cited_by_count":27},{"id":"1610.08871","title":"Detecting People in Artwork with CNNs","created":"2016-10-27","cited_by_count":25},{"id":"2111.12792","title":"Improving the Perceptual Quality of 2D Animation Interpolation","created":"2021-11-24","cited_by_count":20},{"id":"2209.11224","title":"VToonify: Controllable High-Resolution Portrait Video Style Transfer","created":"2022-09-22","cited_by_count":20},{"id":"2102.06529","title":"Improving Object Detection in Art Images Using Only Style Transfer","created":"2021-02-12","cited_by_count":15},{"id":"2012.05616","title":"Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning","created":"2020-12-10","cited_by_count":13},{"id":"2111.07640","title":"AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment","created":"2021-11-15","cited_by_count":11},{"id":"2207.05378","title":"Collaborative Neural Rendering using Anime Character Sheets","created":"2022-07-12","cited_by_count":8},{"id":"2002.11812","title":"Learning to Shadow Hand-drawn Sketches","created":"2020-02-26","cited_by_count":6},{"id":"1410.3756","title":"Crowd Saliency Detection via Global Similarity Structure","created":"2014-10-14","cited_by_count":4}],"next_cursor":null}