{"list":"other","total":92,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1808.02559","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","created":"2018-08-07","cited_by_count":208},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2205.14141","title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","created":"2022-05-27","cited_by_count":93},{"id":"2203.05175","title":"MVP: Multimodality-guided Visual Pre-training","created":"2022-03-10","cited_by_count":92},{"id":"2212.04500","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","created":"2022-12-08","cited_by_count":90},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"2206.01204","title":"Siamese Image Modeling for Self-Supervised Vision Representation Learning","created":"2022-06-02","cited_by_count":78},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41},{"id":"2210.10615","title":"A Unified View of Masked Image Modeling","created":"2022-10-19","cited_by_count":36},{"id":"2212.06138","title":"CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet","created":"2022-12-12","cited_by_count":35},{"id":"2211.08887","title":"Stare at What You See: Masked Image Modeling without Reconstruction","created":"2022-11-16","cited_by_count":30},{"id":"2212.00986","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","created":"2022-12-02","cited_by_count":11}],"next_cursor":null}