{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2003.02320","title":"Knowledge Graphs","created":"2020-03-04","cited_by_count":621},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2003.01251","title":"Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud","created":"2020-03-02","cited_by_count":335},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2202.04579","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","created":"2022-02-09","cited_by_count":214},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"2002.08277","title":"When Radiology Report Generation Meets Knowledge Graph","created":"2020-02-19","cited_by_count":145},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95},{"id":"2209.15486","title":"Graph Neural Networks for Link Prediction with Subgraph Sketching","created":"2022-09-30","cited_by_count":81},{"id":"2007.05655","title":"Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation","created":"2020-07-11","cited_by_count":71},{"id":"2206.08702","title":"Sheaf Neural Networks with Connection Laplacians","created":"2022-06-17","cited_by_count":65},{"id":"1802.01572","title":"MotifNet: a motif-based Graph Convolutional Network for directed graphs","created":"2018-02-04","cited_by_count":64},{"id":"2208.00005","title":"Testing Relational Understanding in Text-Guided Image Generation","created":"2022-07-29","cited_by_count":59},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"2006.09073","title":"Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering","created":"2020-06-16","cited_by_count":51},{"id":"2003.13962","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","created":"2020-03-31","cited_by_count":46},{"id":"2012.01981","title":"Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery","created":"2020-12-02","cited_by_count":46},{"id":"1909.03918","title":"Hierarchy Parsing for Image Captioning","created":"2019-09-09","cited_by_count":44},{"id":"2205.08148","title":"Gender and Racial Bias in Visual Question Answering Datasets","created":"2022-05-17","cited_by_count":39},{"id":"1605.07869","title":"Variational Neural Machine Translation","created":"2016-05-25","cited_by_count":35},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34},{"id":"2009.00145","title":"Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering","created":"2020-08-31","cited_by_count":32},{"id":"2004.14231","title":"Image Captioning through Image Transformer","created":"2020-04-29","cited_by_count":29},{"id":"2108.02366","title":"Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning","created":"2021-08-05","cited_by_count":27},{"id":"1908.02127","title":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","created":"2019-08-06","cited_by_count":25},{"id":"2012.07620","title":"Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective","created":"2020-12-14","cited_by_count":24},{"id":"2206.01988","title":"Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation","created":"2022-06-04","cited_by_count":24},{"id":"2012.14700","title":"Image-to-Image Retrieval by Learning Similarity between Scene Graphs","created":"2020-12-29","cited_by_count":23},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22},{"id":"1907.12133","title":"An Empirical Study on Leveraging Scene Graphs for Visual Question Answering","created":"2019-07-28","cited_by_count":21},{"id":"2112.08587","title":"SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning","created":"2021-12-16","cited_by_count":16},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11},{"id":"2210.04559","title":"CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning","created":"2022-10-10","cited_by_count":11},{"id":"2012.03476","title":"NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification","created":"2020-12-07","cited_by_count":9},{"id":"2212.12249","title":"Do DALL-E and Flamingo Understand Each Other?","created":"2022-12-23","cited_by_count":7},{"id":"2010.01666","title":"Multi-Modal Retrieval using Graph Neural Networks","created":"2020-10-04","cited_by_count":4},{"id":"2201.01190","title":"Two-level Graph Neural Network","created":"2022-01-03","cited_by_count":4},{"id":"2105.02391","title":"Exploring Explicit and Implicit Visual Relationships for Image Captioning","created":"2021-05-06","cited_by_count":2},{"id":"2007.06624","title":"A new approach to descriptors generation for image retrieval by analyzing activations of deep neural network layers","created":"2020-07-13","cited_by_count":1}],"next_cursor":null}