{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2103.02406","title":"Multi-attentional Deepfake Detection","created":"2021-03-03","cited_by_count":341},{"id":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338},{"id":"2103.12376","title":"Generalizing Face Forgery Detection with High-frequency Features","created":"2021-03-23","cited_by_count":262},{"id":"2004.11138","title":"The Creation and Detection of Deepfakes: A Survey","created":"2020-04-23","cited_by_count":247},{"id":"2103.01856","title":"Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain","created":"2021-03-02","cited_by_count":244},{"id":"1711.10678","title":"AttGAN: Facial Attribute Editing by Only Changing What You Want","created":"2017-11-29","cited_by_count":242},{"id":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"2105.06070","title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","created":"2021-05-13","cited_by_count":197},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2012.09311","title":"Learning Self-Consistency for Deepfake Detection","created":"2020-12-16","cited_by_count":179},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"id":"2005.05535","title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","created":"2020-05-12","cited_by_count":131},{"id":"1611.06355","title":"Invertible Conditional GANs for image editing","created":"2016-11-19","cited_by_count":118},{"id":"1706.00409","title":"Fader Networks: Manipulating Images by Sliding Attributes","created":"2017-06-01","cited_by_count":118},{"id":"2103.09460","title":"You Only Look One-level Feature","created":"2021-03-17","cited_by_count":116},{"id":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2104.14754","title":"Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing","created":"2021-04-30","cited_by_count":91},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"2005.05005","title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","created":"2020-05-11","cited_by_count":70},{"id":"2003.08897","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","created":"2020-03-19","cited_by_count":63},{"id":"2106.14490","title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","created":"2021-06-28","cited_by_count":63},{"id":"1906.05856","title":"Detecting Photoshopped Faces by Scripting Photoshop","created":"2019-06-13","cited_by_count":55},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"1803.06414","title":"Learning to Segment via Cut-and-Paste","created":"2018-03-16","cited_by_count":42},{"id":"2203.07319","title":"GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors","created":"2022-03-14","cited_by_count":39},{"id":"2207.02204","title":"Detecting and Recovering Sequential DeepFake Manipulation","created":"2022-07-05","cited_by_count":34},{"id":"1907.13106","title":"Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks","created":"2019-07-30","cited_by_count":24},{"id":"1904.08608","title":"Learning to Collocate Neural Modules for Image Captioning","created":"2019-04-18","cited_by_count":22},{"id":"2001.06822","title":"Exploiting Semantics for Face Image Deblurring","created":"2020-01-19","cited_by_count":18},{"id":"2211.02831","title":"Deep Face Restoration: A Survey","created":"2022-11-05","cited_by_count":17},{"id":"1803.11439","title":"Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present","created":"2018-03-30","cited_by_count":15},{"id":"1807.09958","title":"Rethinking the Form of Latent States in Image Captioning","created":"2018-07-26","cited_by_count":5}],"next_cursor":null}