{"list":"other","total":59,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"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":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1807.03247","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","created":"2018-07-09","cited_by_count":307},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"id":"2010.11304","title":"Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling","created":"2020-10-21","cited_by_count":115},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"id":"2005.06312","title":"Reasoning with Latent Structure Refinement for Document-Level Relation Extraction","created":"2020-05-13","cited_by_count":97},{"id":"2010.01923","title":"Learning from Context or Names? An Empirical Study on Neural Relation Extraction","created":"2020-10-05","cited_by_count":75},{"id":"1908.02660","title":"SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition","created":"2019-08-07","cited_by_count":55},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"2006.09623","title":"Learning Visual Commonsense for Robust Scene Graph Generation","created":"2020-06-17","cited_by_count":47},{"id":"2003.12754","title":"HIN: Hierarchical Inference Network for Document-Level Relation Extraction","created":"2020-03-28","cited_by_count":42},{"id":"2203.10900","title":"Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation","created":"2022-03-21","cited_by_count":39},{"id":"2012.01634","title":"Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D","created":"2020-12-03","cited_by_count":30},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28},{"id":"1708.01956","title":"PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN","created":"2017-08-07","cited_by_count":25},{"id":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25},{"id":"1902.01030","title":"Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers","created":"2019-02-04","cited_by_count":19},{"id":"2205.07993","title":"Generalizable Task Planning through Representation Pretraining","created":"2022-05-16","cited_by_count":19},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15},{"id":"2207.09705","title":"Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction","created":"2022-07-20","cited_by_count":14},{"id":"2208.03763","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","created":"2022-08-07","cited_by_count":14},{"id":"2009.07938","title":"Type-augmented Relation Prediction in Knowledge Graphs","created":"2020-09-16","cited_by_count":12},{"id":"2111.05251","title":"Learning Perceptual Concepts by Bootstrapping from Human Queries","created":"2021-11-09","cited_by_count":12},{"id":"2310.09943","title":"Evaluating Robustness of Visual Representations for Object Assembly Task Requiring Spatio-Geometrical Reasoning","created":"2023-10-15","cited_by_count":3}],"next_cursor":null}