{"list":"other","total":106,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"1511.01844","title":"A note on the evaluation of generative models","created":"2015-11-05","cited_by_count":292},{"id":"1904.00370","title":"Variational Adversarial Active Learning","created":"2019-03-31","cited_by_count":284},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1911.00650","title":"Automatic Detection of Generated Text is Easiest when Humans are Fooled","created":"2019-11-02","cited_by_count":261},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"1705.08584","title":"MMD GAN: Towards Deeper Understanding of Moment Matching Network","created":"2017-05-24","cited_by_count":254},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"1802.03446","title":"Pros and Cons of GAN Evaluation Measures","created":"2018-02-09","cited_by_count":224},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"1912.11078","title":"Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview","created":"2019-11-09","cited_by_count":137},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"1911.08460","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","created":"2019-11-19","cited_by_count":120},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90},{"id":"1901.09024","title":"Diversity-Sensitive Conditional Generative Adversarial Networks","created":"2019-01-25","cited_by_count":77},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"2007.15188","title":"Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability","created":"2020-07-30","cited_by_count":63},{"id":"1812.08249","title":"D3D: Distilled 3D Networks for Video Action Recognition","created":"2018-12-19","cited_by_count":60},{"id":"2005.08575","title":"Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation","created":"2020-05-18","cited_by_count":59},{"id":"1909.02050","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","created":"2019-09-04","cited_by_count":58},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"2006.08315","title":"Mitigating Gender Bias in Captioning Systems","created":"2020-06-15","cited_by_count":50},{"id":"1907.10568","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","created":"2019-07-24","cited_by_count":48},{"id":"2101.00828","title":"Transformer-based Conditional Variational Autoencoder for Controllable Story Generation","created":"2021-01-04","cited_by_count":44},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"2005.10430","title":"Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation","created":"2020-05-21","cited_by_count":37},{"id":"1912.00578","title":"Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models","created":"2019-12-02","cited_by_count":36},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"2104.12807","title":"Multimodal Self-Supervised Learning of General Audio Representations","created":"2021-04-26","cited_by_count":32},{"id":"2010.13588","title":"Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale","created":"2020-10-26","cited_by_count":28},{"id":"2005.03271","title":"RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions","created":"2020-05-07","cited_by_count":26},{"id":"1612.03226","title":"Active Learning for Speech Recognition: the Power of Gradients","created":"2016-12-10","cited_by_count":25},{"id":"2004.02644","title":"Sparse Text Generation","created":"2020-04-06","cited_by_count":24},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21}],"next_cursor":"100"}