{"list":"other","total":65,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"1703.10960","title":"Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders","created":"2017-03-31","cited_by_count":222},{"id":"1910.07677","title":"Cross Attention Network for Few-shot Classification","created":"2019-10-17","cited_by_count":219},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2102.01987","title":"Learning Graph Embeddings for Compositional Zero-shot Learning","created":"2021-02-03","cited_by_count":112},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"1712.01381","title":"A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts","created":"2017-12-04","cited_by_count":96},{"id":"1412.4729","title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks","created":"2014-12-15","cited_by_count":95},{"id":"2109.05739","title":"CEM: Commonsense-aware Empathetic Response Generation","created":"2021-09-13","cited_by_count":89},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1905.07841","title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","created":"2019-05-20","cited_by_count":86},{"id":"1902.07816","title":"Mixture Models for Diverse Machine Translation: Tricks of the Trade","created":"2019-02-20","cited_by_count":77},{"id":"1902.10322","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","created":"2019-02-27","cited_by_count":60},{"id":"2005.05635","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","created":"2020-05-12","cited_by_count":54},{"id":"1510.01431","title":"SentiCap: Generating Image Descriptions with Sentiments","created":"2015-10-06","cited_by_count":48},{"id":"1903.07137","title":"Topic-Guided Variational Autoencoders for Text Generation","created":"2019-03-17","cited_by_count":44},{"id":"1803.08314","title":"Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data","created":"2018-03-22","cited_by_count":37},{"id":"2112.11202","title":"Contrast and Generation Make BART a Good Dialogue Emotion Recognizer","created":"2021-12-21","cited_by_count":35},{"id":"1804.08069","title":"Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation","created":"2018-04-22","cited_by_count":34},{"id":"1711.07068","title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","created":"2017-11-19","cited_by_count":33},{"id":"2203.01522","title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","created":"2022-03-03","cited_by_count":29},{"id":"1807.03871","title":"\"Factual\" or \"Emotional\": Stylized Image Captioning with Adaptive Learning and Attention","created":"2018-07-10","cited_by_count":26},{"id":"2004.12585","title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","created":"2020-04-27","cited_by_count":20},{"id":"2007.09049","title":"Learning to Discretely Compose Reasoning Module Networks for Video Captioning","created":"2020-07-17","cited_by_count":20},{"id":"2106.03518","title":"Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction","created":"2021-06-07","cited_by_count":17},{"id":"1705.10229","title":"Latent Intention Dialogue Models","created":"2017-05-29","cited_by_count":15},{"id":"1809.04938","title":"LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts","created":"2018-09-13","cited_by_count":14},{"id":"1902.06022","title":"A Fully Differentiable Beam Search Decoder","created":"2019-02-16","cited_by_count":14},{"id":"1806.00186","title":"Video Description: A Survey of Methods, Datasets and Evaluation Metrics","created":"2018-06-01","cited_by_count":13},{"id":"1904.06861","title":"Self-critical n-step Training for Image Captioning","created":"2019-04-15","cited_by_count":12},{"id":"2205.03112","title":"Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances","created":"2022-05-06","cited_by_count":11},{"id":"1509.07225","title":"Automatic Concept Discovery from Parallel Text and Visual Corpora","created":"2015-09-24","cited_by_count":10},{"id":"1706.08474","title":"Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention","created":"2017-06-26","cited_by_count":10},{"id":"1704.01691","title":"Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction","created":"2017-04-06","cited_by_count":9},{"id":"1907.10371","title":"Automatic Generation of Personalized Comment Based on User Profile","created":"2019-07-24","cited_by_count":9},{"id":"1911.02739","title":"DCA: Diversified Co-Attention towards Informative Live Video Commenting","created":"2019-11-07","cited_by_count":8},{"id":"1805.03668","title":"Automatic Article Commenting: the Task and Dataset","created":"2018-05-09","cited_by_count":7},{"id":"1906.01231","title":"Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model","created":"2019-06-04","cited_by_count":7},{"id":"2009.09758","title":"Target Conditioning for One-to-Many Generation","created":"2020-09-21","cited_by_count":6},{"id":"2103.15099","title":"BA^2M: A Batch Aware Attention Module for Image Classification","created":"2021-03-28","cited_by_count":5},{"id":"1810.12264","title":"Learning Comment Generation by Leveraging User-Generated Data","created":"2018-10-29","cited_by_count":3},{"id":"1905.01053","title":"Time-sync Video Tag Extraction Using Semantic Association Graph","created":"2019-05-03","cited_by_count":3},{"id":"1906.00246","title":"Personalized Multimedia Item and Key Frame Recommendation","created":"2019-06-01","cited_by_count":3},{"id":"1811.07485","title":"Visual-Texual Emotion Analysis with Deep Coupled Video and Danmu Neural Networks","created":"2018-11-19","cited_by_count":2},{"id":"2002.02649","title":"Multimodal Matching Transformer for Live Commenting","created":"2020-02-07","cited_by_count":2},{"id":"1905.00579","title":"Herding Effect based Attention for Personalized Time-Sync Video Recommendation","created":"2019-05-02","cited_by_count":1}],"next_cursor":null}