{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"1908.08297","title":"EGNet:Edge Guidance Network for Salient Object Detection","created":"2019-08-22","cited_by_count":237},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"1904.08739","title":"Cascaded Partial Decoder for Fast and Accurate Salient Object Detection","created":"2019-04-18","cited_by_count":216},{"id":"2007.09062","title":"Multi-scale Interactive Network for Salient Object Detection","created":"2020-07-17","cited_by_count":212},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1406.2807","title":"The Secrets of Salient Object Segmentation","created":"2014-06-11","cited_by_count":200},{"id":"1503.08663","title":"Visual Saliency Based on Multiscale Deep Features","created":"2015-03-30","cited_by_count":185},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"id":"1907.06781","title":"Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks","created":"2019-07-15","cited_by_count":133},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133},{"id":"2011.04233","title":"End-to-end Lane Shape Prediction with Transformers","created":"2020-11-09","cited_by_count":111},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"2004.08515","title":"JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection","created":"2020-04-18","cited_by_count":79},{"id":"2008.00230","title":"RGB-D Salient Object Detection: A Survey","created":"2020-08-01","cited_by_count":73},{"id":"2108.08162","title":"Specificity-preserving RGB-D Saliency Detection","created":"2021-08-18","cited_by_count":70},{"id":"2007.03262","title":"RGBT Salient Object Detection: A Large-scale Dataset and Benchmark","created":"2020-07-07","cited_by_count":69},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2007.06811","title":"A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection","created":"2020-07-14","cited_by_count":67},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60},{"id":"2204.05585","title":"SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection","created":"2022-04-12","cited_by_count":59},{"id":"2112.13528","title":"Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction","created":"2021-12-27","cited_by_count":57},{"id":"2007.11782","title":"Accurate RGB-D Salient Object Detection via Collaborative Learning","created":"2020-07-23","cited_by_count":52},{"id":"1701.02829","title":"A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach","created":"2017-01-11","cited_by_count":51},{"id":"2007.07051","title":"RGB-D Salient Object Detection with Cross-Modality Modulation and Selection","created":"2020-07-14","cited_by_count":50},{"id":"2109.07246","title":"RGB-D Saliency Detection via Cascaded Mutual Information Minimization","created":"2021-09-15","cited_by_count":50},{"id":"2005.02315","title":"Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection","created":"2020-05-05","cited_by_count":44},{"id":"2008.07064","title":"Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection","created":"2020-08-17","cited_by_count":40},{"id":"2303.07336","title":"MP-Former: Mask-Piloted Transformer for Image Segmentation","created":"2023-03-13","cited_by_count":39},{"id":"2010.05537","title":"Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection","created":"2020-10-12","cited_by_count":38},{"id":"2008.03087","title":"Cascade Graph Neural Networks for RGB-D Salient Object Detection","created":"2020-08-07","cited_by_count":36},{"id":"2303.08594","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","created":"2023-03-15","cited_by_count":32},{"id":"2301.03036","title":"HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection","created":"2023-01-08","cited_by_count":27},{"id":"2207.07898","title":"SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection","created":"2022-07-16","cited_by_count":26},{"id":"2010.04968","title":"Light Field Salient Object Detection: A Review and Benchmark","created":"2020-10-10","cited_by_count":19}],"next_cursor":null}