{"list":"other","total":64,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"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":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2308.15070","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","created":"2023-08-29","cited_by_count":257},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"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":"1608.01041","title":"Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution","created":"2016-08-03","cited_by_count":158},{"id":"1801.02385","title":"Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification","created":"2018-01-08","cited_by_count":136},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2108.01775","title":"Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning","created":"2021-08-03","cited_by_count":116},{"id":"2304.07060","title":"DCFace: Synthetic Face Generation with Dual Condition Diffusion Model","created":"2023-04-14","cited_by_count":116},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2405.14705","title":"Learning Multi-dimensional Human Preference for Text-to-Image Generation","created":"2024-05-23","cited_by_count":106},{"id":"1908.05913","title":"Context-Aware Emotion Recognition Networks","created":"2019-08-16","cited_by_count":99},{"id":"2201.04684","title":"BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations","created":"2022-01-12","cited_by_count":99},{"id":"1907.11510","title":"AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition","created":"2019-07-10","cited_by_count":87},{"id":"2205.01782","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","created":"2022-05-02","cited_by_count":82},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82},{"id":"2309.04907","title":"Effective Real Image Editing with Accelerated Iterative Diffusion Inversion","created":"2023-09-10","cited_by_count":79},{"id":"2010.07734","title":"Self-training for Few-shot Transfer Across Extreme Task Differences","created":"2020-10-15","cited_by_count":76},{"id":"2308.04995","title":"IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models","created":"2023-08-09","cited_by_count":72},{"id":"2305.03382","title":"Guided Image Synthesis via Initial Image Editing in Diffusion Model","created":"2023-05-05","cited_by_count":63},{"id":"2307.16687","title":"DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation","created":"2023-07-31","cited_by_count":36},{"id":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36},{"id":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35},{"id":"2203.12341","title":"Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin","created":"2022-03-23","cited_by_count":32},{"id":"2203.15089","title":"Learning Optical Flow, Depth, and Scene Flow without Real-World Labels","created":"2022-03-28","cited_by_count":31},{"id":"2209.10448","title":"Uncertainty-aware Label Distribution Learning for Facial Expression Recognition","created":"2022-09-21","cited_by_count":30},{"id":"2407.02157","title":"FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs","created":"2024-07-02","cited_by_count":30},{"id":"2405.19100","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","created":"2024-05-29","cited_by_count":18},{"id":"2211.13490","title":"Pose-disentangled Contrastive Learning for Self-supervised Facial Representation","created":"2022-11-24","cited_by_count":17},{"id":"2310.19636","title":"Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition","created":"2023-10-30","cited_by_count":17},{"id":"2403.02138","title":"Self-Supervised Facial Representation Learning with Facial Region Awareness","created":"2024-03-04","cited_by_count":17},{"id":"2407.20175","title":"Towards Localized Fine-Grained Control for Facial Expression Generation","created":"2024-07-25","cited_by_count":13},{"id":"2212.07144","title":"Uncertain Facial Expression Recognition via Multi-task Assisted Correction","created":"2022-12-14","cited_by_count":10},{"id":"2309.03575","title":"Toward High Quality Facial Representation Learning","created":"2023-09-07","cited_by_count":10},{"id":"2406.17100","title":"FaceScore: Benchmarking and Enhancing Face Quality in Human Generation","created":"2024-06-24","cited_by_count":8},{"id":"2303.10583","title":"Toward Artificial Empathy for Human-Centered Design: A Framework","created":"2023-03-19","cited_by_count":6},{"id":"2207.07973","title":"Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition","created":"2022-07-16","cited_by_count":5},{"id":"2303.08617","title":"Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognition","created":"2023-03-15","cited_by_count":4}],"next_cursor":null}