{"list":"other","total":56,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"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":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"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":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1904.05255","title":"Simple BERT Models for Relation Extraction and Semantic Role Labeling","created":"2019-04-10","cited_by_count":154},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"1803.04376","title":"Discriminability objective for training descriptive captions","created":"2018-03-12","cited_by_count":67},{"id":"1811.10652","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","created":"2018-11-26","cited_by_count":65},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"1805.12589","title":"Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech","created":"2018-05-31","cited_by_count":55},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"1812.02347","title":"Counterfactual Critic Multi-Agent Training for Scene Graph Generation","created":"2018-12-06","cited_by_count":53},{"id":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"1510.01431","title":"SentiCap: Generating Image Descriptions with Sentiments","created":"2015-10-06","cited_by_count":48},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"1701.02870","title":"Context-aware Captions from Context-agnostic Supervision","created":"2017-01-11","cited_by_count":43},{"id":"1807.09986","title":"Recurrent Fusion Network for Image Captioning","created":"2018-07-26","cited_by_count":43},{"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":"2007.09580","title":"Length-Controllable Image Captioning","created":"2020-07-19","cited_by_count":36},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1903.05942","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","created":"2019-03-14","cited_by_count":35},{"id":"1708.04320","title":"Situation Recognition with Graph Neural Networks","created":"2017-08-14","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":"1805.07030","title":"SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text","created":"2018-05-18","cited_by_count":27},{"id":"2007.06877","title":"Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets","created":"2020-07-14","cited_by_count":27},{"id":"1807.03871","title":"\"Factual\" or \"Emotional\": Stylized Image Captioning with Adaptive Learning and Attention","created":"2018-07-10","cited_by_count":26},{"id":"2009.03949","title":"Towards Unique and Informative Captioning of Images","created":"2020-09-08","cited_by_count":25},{"id":"2005.00908","title":"Clue: Cross-modal Coherence Modeling for Caption Generation","created":"2020-05-02","cited_by_count":24},{"id":"1904.08608","title":"Learning to Collocate Neural Modules for Image Captioning","created":"2019-04-18","cited_by_count":22},{"id":"1908.08529","title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning","created":"2019-08-22","cited_by_count":21},{"id":"1811.07662","title":"Intention Oriented Image Captions with Guiding Objects","created":"2018-11-19","cited_by_count":20},{"id":"1803.11439","title":"Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present","created":"2018-03-30","cited_by_count":15},{"id":"1612.00901","title":"Commonly Uncommon: Semantic Sparsity in Situation Recognition","created":"2016-12-03","cited_by_count":13},{"id":"1703.06233","title":"Recurrent Models for Situation Recognition","created":"2017-03-18","cited_by_count":13},{"id":"1804.00861","title":"Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning","created":"2018-04-03","cited_by_count":7},{"id":"2011.14901","title":"Language-Driven Region Pointer Advancement for Controllable Image Captioning","created":"2020-11-30","cited_by_count":5},{"id":"2101.08000","title":"Macroscopic Control of Text Generation for Image Captioning","created":"2021-01-20","cited_by_count":1}],"next_cursor":null}