{"list":"other","total":84,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"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":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"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":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1901.07042","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","created":"2019-01-21","cited_by_count":597},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2004.00849","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","created":"2020-04-02","cited_by_count":288},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"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":"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":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"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":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117},{"id":"1609.06647","title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge","created":"2016-09-21","cited_by_count":116},{"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":"2002.08565","title":"Captioning Images Taken by People Who Are Blind","created":"2020-02-20","cited_by_count":110},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"2105.11333","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","created":"2021-05-24","cited_by_count":96},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"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":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69},{"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":"2003.08897","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","created":"2020-03-19","cited_by_count":63},{"id":"1907.09085","title":"Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment","created":"2019-07-22","cited_by_count":60},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"1903.11649","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","created":"2019-03-27","cited_by_count":51},{"id":"1510.01431","title":"SentiCap: Generating Image Descriptions with Sentiments","created":"2015-10-06","cited_by_count":48},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43},{"id":"2307.08347","title":"M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization","created":"2023-07-17","cited_by_count":43},{"id":"1506.01144","title":"What value do explicit high level concepts have in vision to language problems?","created":"2015-06-03","cited_by_count":31},{"id":"1612.01033","title":"Areas of Attention for Image Captioning","created":"2016-12-03","cited_by_count":24},{"id":"2209.13983","title":"Medical Image Captioning via Generative Pretrained Transformers","created":"2022-09-28","cited_by_count":20},{"id":"1505.04467","title":"Exploring Nearest Neighbor Approaches for Image Captioning","created":"2015-05-17","cited_by_count":19},{"id":"1806.06004","title":"Partially-Supervised Image Captioning","created":"2018-06-15","cited_by_count":11},{"id":"2010.03855","title":"Dense Relational Image Captioning via Multi-task Triple-Stream Networks","created":"2020-10-08","cited_by_count":11},{"id":"2111.15015","title":"Neural Attention for Image Captioning: Review of Outstanding Methods","created":"2021-11-29","cited_by_count":11},{"id":"1911.10115","title":"TPsgtR: Neural-Symbolic Tensor Product Scene-Graph-Triplet Representation for Image Captioning","created":"2019-11-22","cited_by_count":4},{"id":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4},{"id":"2306.15111","title":"Self-Supervised Image Captioning with CLIP","created":"2023-06-26","cited_by_count":3}],"next_cursor":null}