{"list":"other","total":70,"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"1707.06875","title":"Why We Need New Evaluation Metrics for NLG","created":"2017-07-21","cited_by_count":233},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"1712.09405","title":"Advances in Pre-Training Distributed Word Representations","created":"2017-12-26","cited_by_count":207},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2005.08271","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","created":"2020-05-17","cited_by_count":76},{"id":"1807.09840","title":"A multi-device dataset for urban acoustic scene classification","created":"2018-07-25","cited_by_count":75},{"id":"2112.09418","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","created":"2021-12-17","cited_by_count":61},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55},{"id":"2107.05463","title":"Sound Event Detection: A Tutorial","created":"2021-07-12","cited_by_count":51},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45},{"id":"1706.10006","title":"Automated Audio Captioning with Recurrent Neural Networks","created":"2017-06-30","cited_by_count":40},{"id":"1911.09655","title":"Temporal Reasoning via Audio Question Answering","created":"2019-11-21","cited_by_count":39},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33},{"id":"2203.15537","title":"On Metric Learning for Audio-Text Cross-Modal Retrieval","created":"2022-03-29","cited_by_count":30},{"id":"1912.04761","title":"Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization","created":"2019-12-10","cited_by_count":29},{"id":"2012.07331","title":"Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval","created":"2020-12-14","cited_by_count":27},{"id":"1411.3715","title":"Acoustic Scene Classification","created":"2014-11-13","cited_by_count":26},{"id":"2102.11457","title":"Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning","created":"2021-02-23","cited_by_count":26},{"id":"2007.00222","title":"A Transformer-based Audio Captioning Model with Keyword Estimation","created":"2020-07-01","cited_by_count":24},{"id":"2107.09998","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","created":"2021-07-21","cited_by_count":24},{"id":"2108.02752","title":"An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning","created":"2021-08-05","cited_by_count":23},{"id":"1906.00717","title":"Masked Non-Autoregressive Image Captioning","created":"2019-06-03","cited_by_count":22},{"id":"1902.09254","title":"Audio Caption: Listen and Tell","created":"2019-02-25","cited_by_count":20},{"id":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18},{"id":"1903.00765","title":"Weakly Labelled AudioSet Tagging with Attention Neural Networks","created":"2019-03-02","cited_by_count":17},{"id":"2107.09990","title":"CL4AC: A Contrastive Loss for Audio Captioning","created":"2021-07-21","cited_by_count":16},{"id":"2203.15526","title":"Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning","created":"2022-03-29","cited_by_count":15},{"id":"2110.06691","title":"Diverse Audio Captioning via Adversarial Training","created":"2021-10-13","cited_by_count":14},{"id":"2009.11436","title":"Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning","created":"2020-09-24","cited_by_count":12},{"id":"2103.16858","title":"SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification","created":"2021-03-31","cited_by_count":12},{"id":"2108.04692","title":"Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization","created":"2021-08-10","cited_by_count":12},{"id":"1812.02872","title":"An Attempt towards Interpretable Audio-Visual Video Captioning","created":"2018-12-07","cited_by_count":11},{"id":"2110.06100","title":"Improving the Performance of Automated Audio Captioning via Integrating the Acoustic and Semantic Information","created":"2021-10-12","cited_by_count":11},{"id":"1804.04715","title":"Sound Event Detection and Time-Frequency Segmentation from Weakly Labelled Data","created":"2018-04-12","cited_by_count":10},{"id":"2010.11098","title":"WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","created":"2020-10-21","cited_by_count":8},{"id":"2010.03644","title":"Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations","created":"2020-10-07","cited_by_count":6},{"id":"1607.03681","title":"Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging","created":"2016-07-13","cited_by_count":5},{"id":"2007.02676","title":"Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning","created":"2020-07-06","cited_by_count":5},{"id":"2007.04660","title":"Multi-task Regularization Based on Infrequent Classes for Audio Captioning","created":"2020-07-09","cited_by_count":5},{"id":"2110.07410","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","created":"2021-10-14","cited_by_count":5},{"id":"2201.03217","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","created":"2022-01-10","cited_by_count":5},{"id":"2202.01405","title":"Joint Speech Recognition and Audio Captioning","created":"2022-02-03","cited_by_count":5},{"id":"2006.15406","title":"Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation","created":"2020-06-27","cited_by_count":4},{"id":"1702.07787","title":"Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging","created":"2017-02-24","cited_by_count":3},{"id":"2107.08028","title":"Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach","created":"2021-07-16","cited_by_count":3}],"next_cursor":null}