{"list":"other","total":91,"rows":[{"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":"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"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":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"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":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1912.07726","title":"Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy","created":"2019-12-16","cited_by_count":156},{"id":"1711.05535","title":"Dual-Path Convolutional Image-Text Embeddings with Instance Loss","created":"2017-11-15","cited_by_count":145},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","cited_by_count":125},{"id":"2010.05607","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","created":"2020-10-12","cited_by_count":122},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"1903.05485","title":"MMKG: Multi-Modal Knowledge Graphs","created":"2019-03-13","cited_by_count":105},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"id":"1511.02570","title":"Explicit Knowledge-based Reasoning for Visual Question Answering","created":"2015-11-09","cited_by_count":85},{"id":"2002.00819","title":"Knowledge Graph Embedding for Link Prediction: A Comparative Analysis","created":"2020-02-03","cited_by_count":85},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"1609.07028","title":"Image-embodied Knowledge Representation Learning","created":"2016-09-22","cited_by_count":68},{"id":"1904.01475","title":"Good News, Everyone! Context driven entity-aware captioning for news images","created":"2019-04-02","cited_by_count":66},{"id":"1910.05134","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","created":"2019-10-11","cited_by_count":66},{"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":"1712.02036","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","created":"2017-12-06","cited_by_count":62},{"id":"1707.09423","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","created":"2017-07-28","cited_by_count":61},{"id":"2005.02472","title":"Cross-media Structured Common Space for Multimedia Event Extraction","created":"2020-05-05","cited_by_count":61},{"id":"2007.08883","title":"Consensus-Aware Visual-Semantic Embedding for Image-Text Matching","created":"2020-07-17","cited_by_count":59},{"id":"1506.00379","title":"Modeling Relation Paths for Representation Learning of Knowledge Bases","created":"2015-06-01","cited_by_count":56},{"id":"2004.08070","title":"Transform and Tell: Entity-Aware News Image Captioning","created":"2020-04-17","cited_by_count":52},{"id":"2009.07162","title":"Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product","created":"2020-09-15","cited_by_count":39},{"id":"1804.11146","title":"Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings","created":"2018-04-30","cited_by_count":35},{"id":"1505.01197","title":"Contextual Action Recognition with R*CNN","created":"2015-05-05","cited_by_count":34},{"id":"1809.01341","title":"Embedding Multimodal Relational Data for Knowledge Base Completion","created":"2018-09-05","cited_by_count":34},{"id":"1804.10660","title":"Large-Scale Visual Relationship Understanding","created":"2018-04-27","cited_by_count":33},{"id":"1803.03879","title":"Knowledge Aided Consistency for Weakly Supervised Phrase Grounding","created":"2018-03-11","cited_by_count":32},{"id":"1811.11683","title":"Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding","created":"2018-11-28","cited_by_count":32},{"id":"1904.06539","title":"HAKE: Human Activity Knowledge Engine","created":"2019-04-13","cited_by_count":32},{"id":"2009.00145","title":"Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering","created":"2020-08-31","cited_by_count":32},{"id":"2107.11970","title":"Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph","created":"2021-07-26","cited_by_count":31},{"id":"2108.07073","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","created":"2021-08-16","cited_by_count":31},{"id":"2008.09150","title":"VisualSem: A High-quality Knowledge Graph for Vision and Language","created":"2020-08-20","cited_by_count":30},{"id":"2104.03236","title":"Multimodal Entity Linking for Tweets","created":"2021-04-07","cited_by_count":28},{"id":"1709.04676","title":"KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features","created":"2017-09-14","cited_by_count":26},{"id":"1912.01496","title":"Knowledge-Enriched Visual Storytelling","created":"2019-12-03","cited_by_count":26},{"id":"1504.06063","title":"Multimodal Convolutional Neural Networks for Matching Image and Sentence","created":"2015-04-23","cited_by_count":25},{"id":"1612.07360","title":"Top-down Visual Saliency Guided by Captions","created":"2016-12-21","cited_by_count":22},{"id":"2106.03619","title":"Multi-modal Entity Alignment in Hyperbolic Space","created":"2021-06-07","cited_by_count":19},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19},{"id":"2003.12383","title":"End-to-End Entity Classification on Multimodal Knowledge Graphs","created":"2020-03-25","cited_by_count":12},{"id":"2006.07510","title":"Do Dogs have Whiskers? A New Knowledge Base of hasPart Relations","created":"2020-06-12","cited_by_count":10},{"id":"2109.07411","title":"AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commerce","created":"2021-09-13","cited_by_count":8},{"id":"1906.01290","title":"Relational Reasoning using Prior Knowledge for Visual Captioning","created":"2019-06-04","cited_by_count":7},{"id":"1511.04891","title":"Sherlock: Scalable Fact Learning in Images","created":"2015-11-16","cited_by_count":4},{"id":"1710.06303","title":"Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance","created":"2017-10-17","cited_by_count":1}],"next_cursor":null}