{"list":"other","total":52,"rows":[{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2012.04012","title":"Learning an Animatable Detailed 3D Face Model from In-The-Wild Images","created":"2020-12-07","cited_by_count":477},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255},{"id":"2009.09960","title":"Towards Fast, Accurate and Stable 3D Dense Face Alignment","created":"2020-09-21","cited_by_count":219},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"1905.06817","title":"Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision","created":"2019-05-16","cited_by_count":176},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2004.00060","title":"HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation","created":"2020-03-31","cited_by_count":112},{"id":"2311.08526","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","created":"2023-11-14","cited_by_count":88},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83},{"id":"1803.07737","title":"PyramidBox: A Context-assisted Single Shot Face Detector","created":"2018-03-21","cited_by_count":58},{"id":"2012.07791","title":"img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation","created":"2020-12-14","cited_by_count":58},{"id":"2005.10353","title":"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose","created":"2020-05-20","cited_by_count":47},{"id":"2204.03688","title":"DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image","created":"2022-04-07","cited_by_count":31},{"id":"2110.09772","title":"Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry","created":"2021-10-19","cited_by_count":27},{"id":"1902.04943","title":"3D Face Modeling From Diverse Raw Scan Data","created":"2019-02-13","cited_by_count":25},{"id":"2202.02299","title":"Multi-task head pose estimation in-the-wild","created":"2022-02-04","cited_by_count":23},{"id":"2406.08249","title":"Dataset Enhancement with Instance-Level Augmentations","created":"2024-06-12","cited_by_count":23},{"id":"2212.01593","title":"Make RepVGG Greater Again: A Quantization-aware Approach","created":"2022-12-03","cited_by_count":22},{"id":"2309.07654","title":"Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation","created":"2023-09-14","cited_by_count":20},{"id":"1803.09256","title":"Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture","created":"2018-03-25","cited_by_count":18},{"id":"2210.13835","title":"Synthetic Data Supervised Salient Object Detection","created":"2022-10-25","cited_by_count":15},{"id":"1511.07917","title":"Context-aware CNNs for person head detection","created":"2015-11-24","cited_by_count":9},{"id":"1708.00370","title":"Hand2Face: Automatic Synthesis and Recognition of Hand Over Face Occlusions","created":"2017-08-01","cited_by_count":8},{"id":"1802.02142","title":"Face Detection Using Improved Faster RCNN","created":"2018-02-06","cited_by_count":7}],"next_cursor":null}