{"list":"other","total":57,"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"1909.02729","title":"A Baseline for Few-Shot Image Classification","created":"2019-09-06","cited_by_count":298},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"1811.09751","title":"Characterizing and Avoiding Negative Transfer","created":"2018-11-24","cited_by_count":229},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88},{"id":"2108.06227","title":"SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation","created":"2021-08-13","cited_by_count":86},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"2105.07059","title":"Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentation","created":"2021-05-14","cited_by_count":49},{"id":"2302.01735","title":"Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective","created":"2023-02-03","cited_by_count":43},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41},{"id":"1905.06139","title":"Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations","created":"2019-05-15","cited_by_count":36},{"id":"2007.04239","title":"A Survey on Transfer Learning in Natural Language Processing","created":"2020-05-31","cited_by_count":33},{"id":"2201.10737","title":"Class-Aware Adversarial Transformers for Medical Image Segmentation","created":"2022-01-26","cited_by_count":33},{"id":"1903.12457","title":"Towards Knowledge-Based Personalized Product Description Generation in E-commerce","created":"2019-03-29","cited_by_count":32},{"id":"2209.13476","title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","created":"2022-09-27","cited_by_count":30},{"id":"2206.02307","title":"Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation","created":"2022-06-06","cited_by_count":27},{"id":"2203.14987","title":"Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment","created":"2022-03-28","cited_by_count":24},{"id":"2105.07205","title":"Rethinking Skip Connection with Layer Normalization in Transformers and ResNets","created":"2021-05-15","cited_by_count":22},{"id":"2210.08654","title":"Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs","created":"2022-10-16","cited_by_count":21},{"id":"2210.15461","title":"LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation","created":"2022-10-19","cited_by_count":21},{"id":"2103.01594","title":"Probing Product Description Generation via Posterior Distillation","created":"2021-03-02","cited_by_count":15},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14},{"id":"2108.08468","title":"QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction","created":"2021-08-19","cited_by_count":13},{"id":"1904.01735","title":"Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce","created":"2019-04-03","cited_by_count":11},{"id":"2202.06129","title":"RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph","created":"2022-02-12","cited_by_count":11},{"id":"2211.04023","title":"A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding","created":"2022-11-08","cited_by_count":9},{"id":"1803.11359","title":"Automatic Generation of Chinese Short Product Titles for Mobile Display","created":"2018-03-30","cited_by_count":7},{"id":"2211.04861","title":"ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation","created":"2022-11-09","cited_by_count":7},{"id":"2007.11768","title":"Product Title Generation for Conversational Systems using BERT","created":"2020-07-23","cited_by_count":2},{"id":"2008.12258","title":"Learning to Profile: User Meta-Profile Network for Few-Shot Learning","created":"2020-08-21","cited_by_count":2},{"id":"2211.08588","title":"Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering","created":"2022-11-16","cited_by_count":2}],"next_cursor":null}