{"list":"other","total":58,"rows":[{"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"1812.07003","title":"3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans","created":"2018-12-17","cited_by_count":217},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2203.01509","title":"SoftGroup for 3D Instance Segmentation on Point Clouds","created":"2022-03-03","cited_by_count":200},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2301.02238","title":"HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling","created":"2023-01-05","cited_by_count":174},{"id":"2005.02551","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","created":"2020-05-06","cited_by_count":113},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88},{"id":"1912.06218","title":"YOLACT++: Better Real-time Instance Segmentation","created":"2019-12-03","cited_by_count":84},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"1812.03904","title":"Attention-guided Unified Network for Panoptic Segmentation","created":"2018-12-10","cited_by_count":71},{"id":"2306.04633","title":"Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion","created":"2023-06-07","cited_by_count":64},{"id":"2212.13545","title":"Interactive Segmentation of Radiance Fields","created":"2022-12-27","cited_by_count":60},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46},{"id":"2305.16233","title":"Interactive Segment Anything NeRF with Feature Imitation","created":"2023-05-25","cited_by_count":24},{"id":"2310.15712","title":"GNeSF: Generalizable Neural Semantic Fields","created":"2023-10-24","cited_by_count":9},{"id":"1809.02110","title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","created":"2018-09-06","cited_by_count":8}],"next_cursor":null}