{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"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":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1411.7923","title":"Learning Face Representation from Scratch","created":"2014-11-28","cited_by_count":453},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2204.00964","title":"AdaFace: Quality Adaptive Margin for Face Recognition","created":"2022-04-03","cited_by_count":391},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"1512.00596","title":"The MegaFace Benchmark: 1 Million Faces for Recognition at Scale","created":"2015-12-02","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":"2109.09416","title":"ElasticFace: Elastic Margin Loss for Deep Face Recognition","created":"2021-09-20","cited_by_count":144},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116},{"id":"2111.15490","title":"FENeRF: Face Editing in Neural Radiance Fields","created":"2021-11-30","cited_by_count":112},{"id":"1902.06838","title":"SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color","created":"2019-02-18","cited_by_count":106},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2002.10310","title":"Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval","created":"2020-02-24","cited_by_count":59},{"id":"2309.08480","title":"PoseFix: Correcting 3D Human Poses with Natural Language","created":"2023-09-15","cited_by_count":40},{"id":"2203.14691","title":"Sketch3T: Test-Time Training for Zero-Shot SBIR","created":"2022-03-28","cited_by_count":34},{"id":"2203.14448","title":"Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing","created":"2022-03-28","cited_by_count":26},{"id":"2102.02717","title":"RoI Tanh-polar Transformer Network for Face Parsing in the Wild","created":"2021-02-04","cited_by_count":23},{"id":"2207.10180","title":"Controllable and Guided Face Synthesis for Unconstrained Face Recognition","created":"2022-07-20","cited_by_count":22},{"id":"2303.13779","title":"Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR","created":"2023-03-24","cited_by_count":14},{"id":"2112.15439","title":"Facial-Sketch Synthesis: A New Challenge","created":"2021-12-31","cited_by_count":13},{"id":"1907.02157","title":"Slim-CNN: A Light-Weight CNN for Face Attribute Prediction","created":"2019-07-03","cited_by_count":11},{"id":"2311.03714","title":"Loss Balancing for Fair Supervised Learning","created":"2023-11-07","cited_by_count":11},{"id":"1908.08433","title":"Scoot: A Perceptual Metric for Facial Sketches","created":"2019-08-21","cited_by_count":10},{"id":"2201.06570","title":"BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR","created":"2022-01-17","cited_by_count":8},{"id":"1812.04929","title":"Semi-Supervised Learning for Face Sketch Synthesis in the Wild","created":"2018-12-12","cited_by_count":7},{"id":"2006.11739","title":"Achieving Better Kinship Recognition Through Better Baseline","created":"2020-06-21","cited_by_count":6},{"id":"2302.05576","title":"Sketch Less Face Image Retrieval: A New Challenge","created":"2023-02-11","cited_by_count":4},{"id":"2109.01745","title":"A realistic approach to generate masked faces applied on two novel masked face recognition data sets","created":"2021-09-03","cited_by_count":3},{"id":"2301.02807","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","created":"2023-01-07","cited_by_count":3},{"id":"2107.00327","title":"Orthonormal Product Quantization Network for Scalable Face Image Retrieval","created":"2021-07-01","cited_by_count":1},{"id":"2301.01922","title":"Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning","created":"2023-01-05","cited_by_count":1}],"next_cursor":null}