{"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":"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"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":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"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":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"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":"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":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"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":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2010.02824","title":"Support-set bottlenecks for video-text representation learning","created":"2020-10-06","cited_by_count":170},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95},{"id":"2010.10864","title":"A Short Note on the Kinetics-700-2020 Human Action Dataset","created":"2020-10-21","cited_by_count":92},{"id":"1809.01337","title":"Localizing Moments in Video with Temporal Language","created":"2018-09-05","cited_by_count":83},{"id":"2010.07999","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","created":"2020-10-15","cited_by_count":62},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24},{"id":"2104.09052","title":"Metadata Normalization","created":"2021-04-19","cited_by_count":14},{"id":"2103.14517","title":"On the hidden treasure of dialog in video question answering","created":"2021-03-26","cited_by_count":7}],"next_cursor":null}