{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"2401.14398","title":"pix2gestalt: Amodal Segmentation by Synthesizing Wholes","created":"2024-01-25","cited_by_count":70},{"id":"1604.08202","title":"Amodal Instance Segmentation","created":"2016-04-27","cited_by_count":63},{"id":"1804.08864","title":"Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation","created":"2018-04-24","cited_by_count":62},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"2012.05598","title":"Amodal Segmentation Based on Visible Region Segmentation and Shape Prior","created":"2020-12-10","cited_by_count":43},{"id":"2109.11103","title":"Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling","created":"2021-09-23","cited_by_count":43},{"id":"2202.11542","title":"Amodal Panoptic Segmentation","created":"2022-02-23","cited_by_count":38},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35},{"id":"2010.13175","title":"Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model","created":"2020-10-25","cited_by_count":29},{"id":"2308.16825","title":"Coarse-to-Fine Amodal Segmentation with Shape Prior","created":"2023-08-31","cited_by_count":29},{"id":"2108.09897","title":"A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation","created":"2021-08-23","cited_by_count":21},{"id":"2411.13019","title":"Open-World Amodal Appearance Completion","created":"2024-11-20","cited_by_count":19},{"id":"1905.12898","title":"Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation","created":"2019-05-30","cited_by_count":16},{"id":"2412.04623","title":"Using Diffusion Priors for Video Amodal Segmentation","created":"2024-12-05","cited_by_count":16},{"id":"2301.08898","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","created":"2023-01-21","cited_by_count":9},{"id":"2401.01642","title":"BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion","created":"2024-01-03","cited_by_count":9},{"id":"2503.06261","title":"Segment Anything, Even Occluded","created":"2025-03-08","cited_by_count":7},{"id":"2403.11376","title":"ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation","created":"2024-03-18","cited_by_count":6},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5},{"id":"2409.18256","title":"Amodal Instance Segmentation with Diffusion Shape Prior Estimation","created":"2024-09-26","cited_by_count":5}],"next_cursor":null}