{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"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":"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":"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":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"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":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"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":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"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":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"1808.02559","title":"A Joint Sequence Fusion Model for Video Question Answering and Retrieval","created":"2018-08-07","cited_by_count":208},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2006.09199","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","created":"2020-06-16","cited_by_count":111},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59},{"id":"2206.01201","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering","created":"2022-06-02","cited_by_count":59},{"id":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36},{"id":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33},{"id":"2108.08426","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","created":"2021-08-19","cited_by_count":28}],"next_cursor":null}