{"list":"other","total":58,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2106.01226","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","created":"2021-06-02","cited_by_count":463},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2003.09005","title":"Semi-Supervised Semantic Segmentation with Cross-Consistency Training","created":"2020-03-19","cited_by_count":376},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2102.09480","title":"Unbiased Teacher for Semi-Supervised Object Detection","created":"2021-02-18","cited_by_count":306},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"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":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2203.03884","title":"Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels","created":"2022-03-08","cited_by_count":218},{"id":"2010.09713","title":"PseudoSeg: Designing Pseudo Labels for Semantic Segmentation","created":"2020-10-19","cited_by_count":180},{"id":"2208.09910","title":"Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation","created":"2022-08-21","cited_by_count":178},{"id":"2109.00650","title":"Dash: Semi-Supervised Learning with Dynamic Thresholding","created":"2021-09-01","cited_by_count":148},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"2301.10921","title":"SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning","created":"2023-01-26","cited_by_count":133},{"id":"2010.00514","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","created":"2020-10-01","cited_by_count":131},{"id":"2010.00515","title":"Linguistic Structure Guided Context Modeling for Referring Image Segmentation","created":"2020-10-01","cited_by_count":102},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2104.04465","title":"Bootstrapping Semantic Segmentation with Regional Contrast","created":"2021-04-09","cited_by_count":80},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68},{"id":"2212.04976","title":"Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation","created":"2022-12-09","cited_by_count":64},{"id":"2204.02078","title":"Semi-supervised Semantic Segmentation with Error Localization Network","created":"2022-04-05","cited_by_count":57},{"id":"2104.04386","title":"Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding","created":"2021-04-09","cited_by_count":52},{"id":"2304.12637","title":"Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation","created":"2023-04-25","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":"2204.12109","title":"Instance-Specific Feature Propagation for Referring Segmentation","created":"2022-04-26","cited_by_count":45},{"id":"1606.04596","title":"Semi-Supervised Learning for Neural Machine Translation","created":"2016-06-15","cited_by_count":36},{"id":"1708.01676","title":"Query-guided Regression Network with Context Policy for Phrase Grounding","created":"2017-08-04","cited_by_count":34},{"id":"1611.06641","title":"Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues","created":"2016-11-21","cited_by_count":33},{"id":"2304.14006","title":"Edit Everything: A Text-Guided Generative System for Images Editing","created":"2023-04-27","cited_by_count":33},{"id":"2308.15512","title":"Shatter and Gather: Learning Referring Image Segmentation with Text Supervision","created":"2023-08-29","cited_by_count":25},{"id":"2303.15062","title":"The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation","created":"2023-03-27","cited_by_count":21},{"id":"1903.07669","title":"Neural Sequential Phrase Grounding (SeqGROUND)","created":"2019-03-18","cited_by_count":20},{"id":"2310.14583","title":"JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification","created":"2023-10-23","cited_by_count":15},{"id":"2209.12611","title":"MaxMatch: Semi-Supervised Learning with Worst-Case Consistency","created":"2022-09-26","cited_by_count":9},{"id":"2305.03289","title":"BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks","created":"2023-05-05","cited_by_count":7},{"id":"2310.18142","title":"Semi-Supervised Panoptic Narrative Grounding","created":"2023-10-27","cited_by_count":4}],"next_cursor":null}