{"list":"other","total":64,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"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":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2010.05953","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","created":"2020-10-12","cited_by_count":254},{"id":"1806.02847","title":"A Simple Method for Commonsense Reasoning","created":"2018-06-07","cited_by_count":223},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"2004.05483","title":"Unsupervised Commonsense Question Answering with Self-Talk","created":"2020-04-11","cited_by_count":161},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"id":"1511.03745","title":"Grounding of Textual Phrases in Images by Reconstruction","created":"2015-11-12","cited_by_count":112},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"2005.05402","title":"MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning","created":"2020-05-11","cited_by_count":79},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"2005.08271","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","created":"2020-05-17","cited_by_count":76},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"1904.03870","title":"Streamlined Dense Video Captioning","created":"2019-04-08","cited_by_count":57},{"id":"2010.03205","title":"Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions","created":"2020-10-07","cited_by_count":49},{"id":"1711.11135","title":"Video Captioning via Hierarchical Reinforcement Learning","created":"2017-11-29","cited_by_count":47},{"id":"2011.07956","title":"Pre-training Text-to-Text Transformers for Concept-centric Common Sense","created":"2020-10-24","cited_by_count":42},{"id":"1705.01371","title":"Weakly-supervised Visual Grounding of Phrases with Linguistic Structures","created":"2017-05-03","cited_by_count":40},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39},{"id":"1909.09944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","created":"2019-09-22","cited_by_count":38},{"id":"1807.10018","title":"Move Forward and Tell: A Progressive Generator of Video Descriptions","created":"2018-07-26","cited_by_count":35},{"id":"1812.05634","title":"Adversarial Inference for Multi-Sentence Video Description","created":"2018-12-13","cited_by_count":31},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22},{"id":"2109.05097","title":"HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge","created":"2021-09-10","cited_by_count":22},{"id":"1804.05448","title":"Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning","created":"2018-04-15","cited_by_count":21},{"id":"2011.07735","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","created":"2020-11-16","cited_by_count":20},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20},{"id":"2211.15076","title":"Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning","created":"2022-11-28","cited_by_count":18},{"id":"2207.08625","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","created":"2022-07-18","cited_by_count":17},{"id":"1802.10250","title":"Joint Event Detection and Description in Continuous Video Streams","created":"2018-02-28","cited_by_count":9},{"id":"2112.08583","title":"Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge","created":"2021-12-16","cited_by_count":8},{"id":"1810.11735","title":"Middle-Out Decoding","created":"2018-10-28","cited_by_count":5}],"next_cursor":null}