{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"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":"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":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"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":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"2207.09666","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","created":"2022-07-20","cited_by_count":56},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33},{"id":"2001.05876","title":"Show, Recall, and Tell: Image Captioning with Recall Mechanism","created":"2020-01-15","cited_by_count":27},{"id":"2110.08743","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","created":"2021-10-17","cited_by_count":27},{"id":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25},{"id":"2109.12487","title":"Parallel Refinements for Lexically Constrained Text Generation with BART","created":"2021-09-26","cited_by_count":24},{"id":"1711.04323","title":"High-Order Attention Models for Visual Question Answering","created":"2017-11-12","cited_by_count":22},{"id":"2202.06574","title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","created":"2022-02-14","cited_by_count":16},{"id":"1612.07086","title":"An Empirical Study of Language CNN for Image Captioning","created":"2016-12-21","cited_by_count":15},{"id":"1909.09060","title":"Adaptively Aligned Image Captioning via Adaptive Attention Time","created":"2019-09-19","cited_by_count":15},{"id":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5}],"next_cursor":null}