{"list":"other","total":180,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"1611.04558","title":"Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation","created":"2016-11-14","cited_by_count":469},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2305.08845","title":"Large Language Models are Zero-Shot Rankers for Recommender Systems","created":"2023-05-15","cited_by_count":309},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"1409.8403","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","created":"2014-09-30","cited_by_count":166},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"2011.08641","title":"A Review of Generalized Zero-Shot Learning Methods","created":"2020-11-17","cited_by_count":159},{"id":"2308.06038","title":"Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning","created":"2023-08-11","cited_by_count":154},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"2109.02748","title":"Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP","created":"2021-09-06","cited_by_count":152},{"id":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"id":"2403.18293","title":"Efficient Test-Time Adaptation of Vision-Language Models","created":"2024-03-27","cited_by_count":141},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","cited_by_count":130},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"1805.03438","title":"Robust Classification with Convolutional Prototype Learning","created":"2018-05-09","cited_by_count":123},{"id":"1905.05908","title":"Task-Driven Modular Networks for Zero-Shot Compositional Learning","created":"2019-05-15","cited_by_count":121},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"1712.03878","title":"Generalized Zero-Shot Learning via Synthesized Examples","created":"2017-12-11","cited_by_count":114},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112},{"id":"1809.00287","title":"Learning to Navigate for Fine-grained Classification","created":"2018-09-02","cited_by_count":103},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103},{"id":"2101.12609","title":"Open World Compositional Zero-Shot Learning","created":"2021-01-29","cited_by_count":101},{"id":"2311.01459","title":"Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization","created":"2023-11-02","cited_by_count":101},{"id":"1712.01381","title":"A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts","created":"2017-12-04","cited_by_count":96},{"id":"2008.06893","title":"Context-aware Feature Generation for Zero-shot Semantic Segmentation","created":"2020-08-16","cited_by_count":94},{"id":"2004.00587","title":"Symmetry and Group in Attribute-Object Compositions","created":"2020-04-01","cited_by_count":89},{"id":"2111.12698","title":"Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling","created":"2021-11-24","cited_by_count":84},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79},{"id":"2303.10598","title":"StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields","created":"2023-03-19","cited_by_count":79},{"id":"2303.13440","title":"CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not","created":"2023-03-23","cited_by_count":79},{"id":"2006.14610","title":"A causal view of compositional zero-shot recognition","created":"2020-06-25","cited_by_count":78},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"2103.03433","title":"Goal-Oriented Gaze Estimation for Zero-Shot Learning","created":"2021-03-05","cited_by_count":68},{"id":"2405.02266","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","created":"2024-05-03","cited_by_count":67},{"id":"1908.05832","title":"Transferable Contrastive Network for Generalized Zero-Shot Learning","created":"2019-08-16","cited_by_count":64},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62},{"id":"1903.00502","title":"Semantic-Guided Multi-Attention Localization for Zero-Shot Learning","created":"2019-03-01","cited_by_count":58},{"id":"2101.07978","title":"Semantics Disentangling for Generalized Zero-Shot Learning","created":"2021-01-20","cited_by_count":56},{"id":"2205.08536","title":"Disentangling Visual Embeddings for Attributes and Objects","created":"2022-05-17","cited_by_count":55},{"id":"2206.14475","title":"Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning","created":"2022-06-29","cited_by_count":55},{"id":"2112.01683","title":"TransZero: Attribute-guided Transformer for Zero-Shot Learning","created":"2021-12-03","cited_by_count":54},{"id":"1501.04560","title":"Transductive Multi-view Zero-Shot Learning","created":"2015-01-19","cited_by_count":53},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52},{"id":"1803.06049","title":"Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts","created":"2018-03-16","cited_by_count":48},{"id":"2203.03137","title":"MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning","created":"2022-03-07","cited_by_count":48},{"id":"1709.01148","title":"Link the head to the \"beak\": Zero Shot Learning from Noisy Text Description at Part Precision","created":"2017-09-04","cited_by_count":46},{"id":"1603.02814","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","created":"2016-03-09","cited_by_count":44},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42},{"id":"2205.06784","title":"KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning","created":"2022-05-13","cited_by_count":41},{"id":"2306.02245","title":"SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model","created":"2023-06-04","cited_by_count":40},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40},{"id":"2104.04980","title":"Zero-Shot Learning on 3D Point Cloud Objects and Beyond","created":"2021-04-11","cited_by_count":38},{"id":"2211.10681","title":"Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning","created":"2022-11-19","cited_by_count":37},{"id":"1902.10272","title":"Zero-shot Learning of 3D Point Cloud Objects","created":"2019-02-27","cited_by_count":34},{"id":"2207.01328","title":"DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning","created":"2022-07-04","cited_by_count":33}],"next_cursor":"100"}