{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"1703.08448","title":"Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach","created":"2017-03-24","cited_by_count":201},{"id":"1603.06098","title":"Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation","created":"2016-03-19","cited_by_count":198},{"id":"1502.02734","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","created":"2015-02-09","cited_by_count":189},{"id":"2005.08104","title":"Single-Stage Semantic Segmentation from Image Labels","created":"2020-05-16","cited_by_count":167},{"id":"1805.04574","title":"Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation","created":"2018-05-11","cited_by_count":145},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"2105.08965","title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","created":"2021-05-19","cited_by_count":127},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"1410.5926","title":"Salient Object Detection: A Discriminative Regional Feature Integration Approach","created":"2014-10-22","cited_by_count":89},{"id":"1909.04161","title":"Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentation","created":"2019-09-09","cited_by_count":57},{"id":"2103.07246","title":"Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation","created":"2021-03-12","cited_by_count":50},{"id":"1407.1208","title":"Weakly Supervised Action Labeling in Videos Under Ordering Constraints","created":"2014-07-04","cited_by_count":48},{"id":"1705.01371","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","created":"2017-05-03","cited_by_count":40},{"id":"1609.04331","title":"ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization","created":"2016-09-14","cited_by_count":39},{"id":"1908.10568","title":"Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding","created":"2019-08-28","cited_by_count":37},{"id":"2103.12989","title":"Relation-aware Instance Refinement for Weakly Supervised Visual Grounding","created":"2021-03-24","cited_by_count":35},{"id":"1803.03879","title":"Knowledge Aided Consistency for Weakly Supervised Phrase Grounding","created":"2018-03-11","cited_by_count":32},{"id":"2112.03185","title":"Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples","created":"2021-12-06","cited_by_count":24},{"id":"1711.07618","title":"S4Net: Single Stage Salient-Instance Segmentation","created":"2017-11-21","cited_by_count":23},{"id":"1908.04501","title":"Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation","created":"2019-08-13","cited_by_count":18}],"next_cursor":null}