{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"2011.08641","title":"A Review of Generalized Zero-Shot Learning Methods","created":"2020-11-17","cited_by_count":159},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1703.02507","title":"Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features","created":"2017-03-07","cited_by_count":104},{"id":"2003.01455","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","created":"2020-03-03","cited_by_count":80},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"1907.09021","title":"TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition","created":"2019-07-21","cited_by_count":71},{"id":"1904.08703","title":"Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition","created":"2019-04-18","cited_by_count":54},{"id":"1507.00825","title":"Ridge Regression, Hubness, and Zero-Shot Learning","created":"2015-07-03","cited_by_count":44},{"id":"1803.08460","title":"Towards Universal Representation for Unseen Action Recognition","created":"2018-03-22","cited_by_count":44},{"id":"1511.04512","title":"Zero-Shot Learning via Joint Latent Similarity Embedding","created":"2015-11-14","cited_by_count":39},{"id":"1801.09086","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","created":"2018-01-27","cited_by_count":39},{"id":"1511.04458","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","created":"2015-11-13","cited_by_count":31},{"id":"2009.13682","title":"VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning","created":"2020-09-28","cited_by_count":30},{"id":"1912.12179","title":"Locality and compositionality in zero-shot learning","created":"2019-12-20","cited_by_count":29},{"id":"2008.08072","title":"AssembleNet++: Assembling Modality Representations via Attention Connections","created":"2020-08-18","cited_by_count":28},{"id":"1607.02104","title":"Zero-Shot Visual Recognition via Bidirectional Latent Embedding","created":"2016-07-07","cited_by_count":27},{"id":"1611.08663","title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","created":"2016-11-26","cited_by_count":27},{"id":"1706.09317","title":"Alternative Semantic Representations for Zero-Shot Human Action Recognition","created":"2017-06-28","cited_by_count":27},{"id":"1502.01540","title":"Semantic Embedding Space for Zero-Shot Action Recognition","created":"2015-02-05","cited_by_count":19},{"id":"1901.00484","title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","created":"2019-01-02","cited_by_count":19},{"id":"1909.06423","title":"Zero-Shot Action Recognition in Videos: A Survey","created":"2019-09-13","cited_by_count":19},{"id":"2008.12432","title":"All About Knowledge Graphs for Actions","created":"2020-08-28","cited_by_count":16},{"id":"1804.10073","title":"Visual Data Synthesis via GAN for Zero-Shot Video Classification","created":"2018-04-26","cited_by_count":10},{"id":"1602.07119","title":"The ImageNet Shuffle: Reorganized Pre-training for Video Event Detection","created":"2016-02-23","cited_by_count":5}],"next_cursor":null}