{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"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":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"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":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"2005.08104","title":"Single-Stage Semantic Segmentation from Image Labels","created":"2020-05-16","cited_by_count":167},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2203.16768","title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","created":"2022-03-31","cited_by_count":112},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"2010.00515","title":"Linguistic Structure Guided Context Modeling for Referring Image Segmentation","created":"2020-10-01","cited_by_count":102},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98},{"id":"2003.07685","title":"Weakly-Supervised Salient Object Detection via Scribble Annotations","created":"2020-03-17","cited_by_count":96},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"1708.02750","title":"Extreme clicking for efficient object annotation","created":"2017-08-09","cited_by_count":81},{"id":"2203.02668","title":"Cross Language Image Matching for Weakly Supervised Semantic Segmentation","created":"2022-03-05","cited_by_count":72},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67},{"id":"2012.04404","title":"Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence","created":"2020-12-08","cited_by_count":55},{"id":"1711.06288","title":"Language-Based Image Editing with Recurrent Attentive Models","created":"2017-11-16","cited_by_count":53},{"id":"1903.11649","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","created":"2019-03-27","cited_by_count":51},{"id":"2007.01951","title":"Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation","created":"2020-07-03","cited_by_count":51},{"id":"1910.04748","title":"Referring Expression Object Segmentation with Caption-Aware Consistency","created":"2019-10-10","cited_by_count":46},{"id":"1412.7144","title":"Fully Convolutional Multi-Class Multiple Instance Learning","created":"2014-12-22","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":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33},{"id":"1811.11683","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","created":"2018-11-28","cited_by_count":32},{"id":"2112.08996","title":"Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation","created":"2021-12-16","cited_by_count":29},{"id":"2112.01732","title":"MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection","created":"2021-12-03","cited_by_count":27},{"id":"2203.11652","title":"Weakly-Supervised Salient Object Detection Using Point Supervision","created":"2022-03-22","cited_by_count":25},{"id":"1908.07553","title":"Phrase Localization Without Paired Training Examples","created":"2019-08-20","cited_by_count":24},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16},{"id":"2111.10137","title":"Learning to Detect Instance-level Salient Objects Using Complementary Image Labels","created":"2021-11-19","cited_by_count":14},{"id":"2009.13898","title":"Weakly-supervised Salient Instance Detection","created":"2020-09-29","cited_by_count":12},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11},{"id":"2301.12646","title":"MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search","created":"2023-01-30","cited_by_count":9}],"next_cursor":null}