{"list":"other","total":79,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1908.06066","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training","created":"2019-08-16","cited_by_count":451},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"1812.03299","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding","created":"2018-12-08","cited_by_count":140},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"1812.05252","title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","created":"2018-12-13","cited_by_count":114},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"1612.09542","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","created":"2016-12-30","cited_by_count":74},{"id":"1908.05054","title":"Fusion of Detected Objects in Text for Visual Question Answering","created":"2019-08-14","cited_by_count":74},{"id":"1902.00038","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","created":"2019-01-31","cited_by_count":62},{"id":"1905.04405","title":"Language-Conditioned Graph Networks for Relational Reasoning","created":"2019-05-10","cited_by_count":55},{"id":"1805.03508","title":"Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding","created":"2018-05-09","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":"1909.03918","title":"Hierarchy Parsing for Image Captioning","created":"2019-09-09","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":"2004.12070","title":"Deep Multimodal Neural Architecture Search","created":"2020-04-25","cited_by_count":34},{"id":"1912.03478","title":"A Real-time Global Inference Network for One-stage Referring Expression Comprehension","created":"2019-12-07","cited_by_count":32},{"id":"1908.04289","title":"Multi-modality Latent Interaction Network for Visual Question Answering","created":"2019-08-10","cited_by_count":23},{"id":"2101.11562","title":"Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network","created":"2021-01-27","cited_by_count":17},{"id":"1908.04107","title":"Multimodal Unified Attention Networks for Vision-and-Language Interactions","created":"2019-08-12","cited_by_count":9},{"id":"1912.06638","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","created":"2019-12-13","cited_by_count":1}],"next_cursor":null}