{"list":"other","total":133,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"1507.04808","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","created":"2015-07-17","cited_by_count":207},{"id":"2004.06871","title":"TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue","created":"2020-04-15","cited_by_count":185},{"id":"1506.08909","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","created":"2015-06-30","cited_by_count":172},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"1812.07809","title":"Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities","created":"2018-12-19","cited_by_count":149},{"id":"1905.05709","title":"Challenges in Building Intelligent Open-domain Dialog Systems","created":"2019-05-13","cited_by_count":147},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130},{"id":"1809.01984","title":"Training Millions of Personalized Dialogue Agents","created":"2018-09-06","cited_by_count":126},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1903.09588","title":"Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence","created":"2019-03-22","cited_by_count":122},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"1506.06714","title":"A Neural Network Approach to Context-Sensitive Generation of Conversational Responses","created":"2015-06-22","cited_by_count":98},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95},{"id":"1803.10859","title":"Features for Multi-Target Multi-Camera Tracking and Re-Identification","created":"2018-03-28","cited_by_count":88},{"id":"1904.03567","title":"Image and Video Compression with Neural Networks: A Review","created":"2019-04-07","cited_by_count":86},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85},{"id":"2002.07510","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","created":"2020-02-18","cited_by_count":82},{"id":"1811.00945","title":"Image Chat: Engaging Grounded Conversations","created":"2018-11-02","cited_by_count":77},{"id":"2106.06169","title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","created":"2021-06-11","cited_by_count":75},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"1708.09545","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","created":"2017-08-31","cited_by_count":63},{"id":"1607.06215","title":"A Comprehensive Survey on Cross-modal Retrieval","created":"2016-07-21","cited_by_count":62},{"id":"1912.02379","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","created":"2019-12-05","cited_by_count":61},{"id":"1812.02699","title":"Online Model Distillation for Efficient Video Inference","created":"2018-12-06","cited_by_count":60},{"id":"1907.09358","title":"Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods","created":"2019-07-22","cited_by_count":55},{"id":"2004.13278","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","created":"2020-04-28","cited_by_count":55},{"id":"1809.01816","title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","created":"2018-09-06","cited_by_count":54},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"1907.03141","title":"AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates","created":"2019-07-06","cited_by_count":49},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"1806.07243","title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","created":"2018-06-19","cited_by_count":45},{"id":"1911.03768","title":"The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents","created":"2019-11-09","cited_by_count":45},{"id":"1903.03166","title":"CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog","created":"2019-03-07","cited_by_count":44},{"id":"1902.00579","title":"Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog","created":"2019-02-01","cited_by_count":41},{"id":"1904.05880","title":"Factor Graph Attention","created":"2019-04-11","cited_by_count":41},{"id":"1806.08409","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","created":"2018-06-21","cited_by_count":37},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36},{"id":"2008.12918","title":"Zero-Resource Knowledge-Grounded Dialogue Generation","created":"2020-08-29","cited_by_count":35},{"id":"2103.02548","title":"NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation","created":"2021-03-03","cited_by_count":35},{"id":"1812.02664","title":"Recursive Visual Attention in Visual Dialog","created":"2018-12-06","cited_by_count":34},{"id":"1911.07251","title":"DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue","created":"2019-11-17","cited_by_count":30},{"id":"2009.10942","title":"Exploring global diverse attention via pairwise temporal relation for video summarization","created":"2020-09-23","cited_by_count":29},{"id":"1709.07992","title":"Visual Reference Resolution using Attention Memory for Visual Dialog","created":"2017-09-23","cited_by_count":28},{"id":"2012.15015","title":"OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts","created":"2020-12-30","cited_by_count":27}],"next_cursor":"100"}