{"list":"other","total":86,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1710.10916","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2017-10-19","cited_by_count":229},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"2002.08565","title":"Captioning Images Taken by People Who Are Blind","created":"2020-02-20","cited_by_count":110},{"id":"1803.11404","title":"Cross-modal Deep Variational Hand Pose Estimation","created":"2018-03-30","cited_by_count":89},{"id":"2102.13219","title":"Learning with invariances in random features and kernel models","created":"2021-02-25","cited_by_count":89},{"id":"1611.01891","title":"Joint Multimodal Learning with Deep Generative Models","created":"2016-11-07","cited_by_count":87},{"id":"1904.03451","title":"Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval","created":"2019-04-06","cited_by_count":79},{"id":"1807.11724","title":"A Zero-Shot Framework for Sketch-based Image Retrieval","created":"2018-07-31","cited_by_count":71},{"id":"2003.02683","title":"SketchyCOCO: Image Generation from Freehand Scene Sketches","created":"2020-03-05","cited_by_count":67},{"id":"2106.13488","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","created":"2021-06-25","cited_by_count":67},{"id":"2001.02600","title":"Deep Learning for Free-Hand Sketch: A Survey","created":"2020-01-08","cited_by_count":59},{"id":"2002.10310","title":"Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval","created":"2020-02-24","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":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51},{"id":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"id":"2103.15706","title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval","created":"2021-03-29","cited_by_count":50},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49},{"id":"2005.09159","title":"Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt","created":"2020-05-19","cited_by_count":42},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41},{"id":"2103.13716","title":"Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting","created":"2021-03-25","cited_by_count":38},{"id":"2103.13990","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","created":"2021-03-25","cited_by_count":38},{"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":"2001.02890","title":"Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches","created":"2020-01-09","cited_by_count":37},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1607.07295","title":"Learning Aligned Cross-Modal Representations from Weakly Aligned Data","created":"2016-07-25","cited_by_count":34},{"id":"1904.06611","title":"LiveSketch: Query Perturbations for Guided Sketch-based Visual Search","created":"2019-04-14","cited_by_count":34},{"id":"2203.14691","title":"Sketch3T: Test-Time Training for Zero-Shot SBIR","created":"2022-03-28","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":"1706.00932","title":"See, Hear, and Read: Deep Aligned Representations","created":"2017-06-03","cited_by_count":32},{"id":"1808.02473","title":"SketchyScene: Richly-Annotated Scene Sketches","created":"2018-08-07","cited_by_count":32},{"id":"2007.15103","title":"Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval","created":"2020-07-29","cited_by_count":32},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30},{"id":"1805.11730","title":"Learn to Combine Modalities in Multimodal Deep Learning","created":"2018-05-29","cited_by_count":29},{"id":"2203.14817","title":"Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval","created":"2022-03-28","cited_by_count":27},{"id":"1802.03761","title":"On the Latent Space of Wasserstein Auto-Encoders","created":"2018-02-11","cited_by_count":22},{"id":"2011.00966","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","created":"2020-11-02","cited_by_count":22},{"id":"1707.05612","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","created":"2017-07-18","cited_by_count":21},{"id":"2008.06551","title":"Sketch-Guided Object Localization in Natural Images","created":"2020-08-14","cited_by_count":21},{"id":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","cited_by_count":20},{"id":"1805.11264","title":"Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data","created":"2018-05-29","cited_by_count":19},{"id":"1610.09003","title":"Cross-Modal Scene Networks","created":"2016-10-27","cited_by_count":16},{"id":"2002.06661","title":"Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings","created":"2020-02-16","cited_by_count":16},{"id":"1608.07973","title":"Linking Image and Text with 2-Way Nets","created":"2016-08-29","cited_by_count":14},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13},{"id":"1807.09064","title":"CaricatureShop: Personalized and Photorealistic Caricature Sketching","created":"2018-07-24","cited_by_count":12},{"id":"1808.09044","title":"Single Shot Scene Text Retrieval","created":"2018-08-27","cited_by_count":11},{"id":"2202.11948","title":"Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval","created":"2022-02-24","cited_by_count":10},{"id":"1711.09825","title":"Separating Self-Expression and Visual Content in Hashtag Supervision","created":"2017-11-27","cited_by_count":9},{"id":"2112.10838","title":"One Sketch for All: One-Shot Personalized Sketch Segmentation","created":"2021-12-20","cited_by_count":9},{"id":"1909.02097","title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering","created":"2019-09-04","cited_by_count":7},{"id":"1811.08170","title":"Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition","created":"2018-11-20","cited_by_count":6},{"id":"2108.07353","title":"Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch","created":"2021-08-16","cited_by_count":3}],"next_cursor":null}