{"list":"other","total":64,"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"2002.09291","title":"Transformer Hawkes Process","created":"2020-02-21","cited_by_count":235},{"id":"1907.05321","title":"Time2Vec: Learning a Vector Representation of Time","created":"2019-07-11","cited_by_count":213},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104},{"id":"2102.09109","title":"Understanding and Creating Art with AI: Review and Outlook","created":"2021-02-18","cited_by_count":60},{"id":"2010.04903","title":"What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding","created":"2020-10-10","cited_by_count":52},{"id":"2202.01747","title":"The Met Dataset: Instance-level Recognition for Artworks","created":"2022-02-03","cited_by_count":40},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"2204.07660","title":"It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection","created":"2022-04-15","cited_by_count":36},{"id":"1801.07729","title":"The Shape of Art History in the Eyes of the Machine","created":"2018-01-23","cited_by_count":33},{"id":"2010.14563","title":"Adversarial Dueling Bandits","created":"2020-10-27","cited_by_count":33},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30},{"id":"2408.00491","title":"GalleryGPT: Analyzing Paintings with Large Multimodal Models","created":"2024-08-01","cited_by_count":28},{"id":"1904.01962","title":"Rep the Set: Neural Networks for Learning Set Representations","created":"2019-04-03","cited_by_count":22},{"id":"2001.00056","title":"Deep Attentive Ranking Networks for Learning to Order Sentences","created":"2019-12-31","cited_by_count":22},{"id":"2306.05144","title":"Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean","created":"2023-06-08","cited_by_count":19},{"id":"2206.11925","title":"Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets","created":"2022-06-23","cited_by_count":17},{"id":"1905.07689","title":"DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases","created":"2019-05-19","cited_by_count":16},{"id":"2006.11483","title":"Predicting Temporal Sets with Deep Neural Networks","created":"2020-06-20","cited_by_count":16},{"id":"2104.07064","title":"Is Everything in Order? A Simple Way to Order Sentences","created":"2021-04-14","cited_by_count":15},{"id":"2109.14233","title":"A Next Basket Recommendation Reality Check","created":"2021-09-29","cited_by_count":15},{"id":"2304.00414","title":"Learning Dynamic Style Kernels for Artistic Style Transfer","created":"2023-04-02","cited_by_count":12},{"id":"2405.03140","title":"TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning","created":"2024-05-06","cited_by_count":12},{"id":"1802.07535","title":"BRUNO: A Deep Recurrent Model for Exchangeable Data","created":"2018-02-21","cited_by_count":11},{"id":"1908.01174","title":"Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition","created":"2019-08-03","cited_by_count":10},{"id":"2105.08190","title":"Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings","created":"2021-05-17","cited_by_count":9},{"id":"2204.05490","title":"Continuous-Time User Preference Modelling for Temporal Sets Prediction","created":"2022-04-12","cited_by_count":7},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6},{"id":"2407.17689","title":"SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification","created":"2024-07-25","cited_by_count":6},{"id":"2203.07390","title":"What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction","created":"2022-03-14","cited_by_count":4},{"id":"2312.16477","title":"Group Multi-View Transformer for 3D Shape Analysis with Spatial Encoding","created":"2023-12-27","cited_by_count":4},{"id":"1903.02939","title":"ViTOR: Learning to Rank Webpages Based on Visual Features","created":"2019-03-07","cited_by_count":2},{"id":"2206.03720","title":"Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction","created":"2022-06-08","cited_by_count":2},{"id":"2306.08650","title":"Learning to Rank when Grades Matter","created":"2023-06-14","cited_by_count":2}],"next_cursor":null}