{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"1911.11445","title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","created":"2019-11-26","cited_by_count":176},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"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":"1501.02741","title":"Salient Object Detection: A Benchmark","created":"2015-01-05","cited_by_count":131},{"id":"2004.05763","title":"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders","created":"2020-04-13","cited_by_count":98},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","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":"2008.12134","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","created":"2020-08-26","cited_by_count":67},{"id":"1803.03391","title":"Review of Visual Saliency Detection with Comprehensive Information","created":"2018-03-09","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":"1905.06741","title":"RGB-T Image Saliency Detection via Collaborative Graph Learning","created":"2019-05-16","cited_by_count":58},{"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":"2103.11832","title":"Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion","created":"2021-03-22","cited_by_count":56},{"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":"2112.02363","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","created":"2021-12-04","cited_by_count":47},{"id":"2003.08608","title":"DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection","created":"2020-03-19","cited_by_count":45},{"id":"2108.03990","title":"TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network","created":"2021-08-09","cited_by_count":45},{"id":"2005.02315","title":"Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection","created":"2020-05-05","cited_by_count":44},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"2101.10241","title":"RGB-D Salient Object Detection via 3D Convolutional Neural Networks","created":"2021-01-25","cited_by_count":36},{"id":"1903.02120","title":"Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation","created":"2019-03-05","cited_by_count":34},{"id":"2108.01971","title":"Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection","created":"2021-08-04","cited_by_count":34},{"id":"2110.14223","title":"RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images","created":"2021-10-27","cited_by_count":34},{"id":"1710.05174","title":"Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion","created":"2017-10-14","cited_by_count":28},{"id":"1802.07957","title":"Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps","created":"2018-02-22","cited_by_count":26},{"id":"2110.00338","title":"Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection","created":"2021-10-01","cited_by_count":24},{"id":"2204.08917","title":"Global-and-Local Collaborative Learning for Co-Salient Object Detection","created":"2022-04-19","cited_by_count":24},{"id":"2102.09133","title":"Densely Nested Top-Down Flows for Salient Object Detection","created":"2021-02-18","cited_by_count":23},{"id":"2112.10992","title":"Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition","created":"2021-12-21","cited_by_count":23},{"id":"1912.10280","title":"\\emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks","created":"2019-12-21","cited_by_count":21},{"id":"2010.04968","title":"Light Field Salient Object Detection: A Review and Benchmark","created":"2020-10-10","cited_by_count":19},{"id":"2104.10127","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","created":"2021-04-20","cited_by_count":18},{"id":"1903.10152","title":"SAC-Net: Spatial Attenuation Context for Salient Object Detection","created":"2019-03-25","cited_by_count":15},{"id":"1711.01371","title":"An Iterative Co-Saliency Framework for RGBD Images","created":"2017-11-04","cited_by_count":14},{"id":"2109.01926","title":"Audio-Visual Transformer Based Crowd Counting","created":"2021-09-04","cited_by_count":12},{"id":"2109.03425","title":"RGB-D Salient Object Detection with Ubiquitous Target Awareness","created":"2021-09-08","cited_by_count":12},{"id":"2110.00698","title":"Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance","created":"2021-10-02","cited_by_count":12},{"id":"2108.02759","title":"Unifying Global-Local Representations in Salient Object Detection with Transformer","created":"2021-08-05","cited_by_count":11},{"id":"2104.14729","title":"CoSformer: Detecting Co-Salient Object with Transformers","created":"2021-04-30","cited_by_count":10},{"id":"2110.04904","title":"Modality-Guided Subnetwork for Salient Object Detection","created":"2021-10-10","cited_by_count":8},{"id":"1910.08071","title":"Context-Aware Saliency Detection for Image Retargeting Using Convolutional Neural Networks","created":"2019-10-17","cited_by_count":7},{"id":"2008.04158","title":"Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks","created":"2020-08-07","cited_by_count":6},{"id":"2104.13916","title":"Learning Synergistic Attention for Light Field Salient Object Detection","created":"2021-04-28","cited_by_count":6},{"id":"2107.01980","title":"Gaze Estimation with an Ensemble of Four Architectures","created":"2021-07-05","cited_by_count":6},{"id":"2103.04235","title":"Graph-based Pyramid Global Context Reasoning with a Saliency-aware Projection for COVID-19 Lung Infections Segmentation","created":"2021-03-07","cited_by_count":5},{"id":"2102.06882","title":"Saliency-Aware Class-Agnostic Food Image Segmentation","created":"2021-02-13","cited_by_count":4},{"id":"2111.00770","title":"Dense Prediction with Attentive Feature Aggregation","created":"2021-11-01","cited_by_count":4},{"id":"2112.00582","title":"Transformer-based Network for RGB-D Saliency Detection","created":"2021-12-01","cited_by_count":2}],"next_cursor":null}