{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179},{"id":"1811.11389","title":"Image Generation from Layout","created":"2018-11-28","cited_by_count":105},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"1908.07500","title":"Image Synthesis From Reconfigurable Layout and Style","created":"2019-08-20","cited_by_count":85},{"id":"2203.17260","title":"Generating High Fidelity Data from Low-density Regions using Diffusion Models","created":"2022-03-31","cited_by_count":78},{"id":"2304.12308","title":"Segment Anything in 3D with Radiance Fields","created":"2023-04-24","cited_by_count":62},{"id":"1905.10346","title":"Mask-Guided Portrait Editing with Conditional GANs","created":"2019-05-24","cited_by_count":61},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"2102.01645","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","created":"2021-02-02","cited_by_count":57},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35},{"id":"2303.11162","title":"Picture that Sketch: Photorealistic Image Generation from Abstract Sketches","created":"2023-03-20","cited_by_count":34},{"id":"2103.11597","title":"Human De-occlusion: Invisible Perception and Recovery for Humans","created":"2021-03-22","cited_by_count":31},{"id":"2003.11690","title":"BachGAN: High-Resolution Image Synthesis from Salient Object Layout","created":"2020-03-26","cited_by_count":22},{"id":"2112.01695","title":"Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation","created":"2021-12-03","cited_by_count":13},{"id":"2110.10599","title":"Video Instance Segmentation by Instance Flow Assembly","created":"2021-10-20","cited_by_count":12},{"id":"2211.14419","title":"Panoramic Video Salient Object Detection with Ambisonic Audio Guidance","created":"2022-11-26","cited_by_count":9},{"id":"2305.19406","title":"PaintSeg: Training-free Segmentation via Painting","created":"2023-05-30","cited_by_count":7},{"id":"2307.13948","title":"Rethinking Voice-Face Correlation: A Geometry View","created":"2023-07-26","cited_by_count":3}],"next_cursor":null}