{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"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":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"1911.02972","title":"Blockwise Self-Attention for Long Document Understanding","created":"2019-11-07","cited_by_count":159},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2110.13711","title":"Hierarchical Transformers Are More Efficient Language Models","created":"2021-10-26","cited_by_count":102},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91},{"id":"2007.06866","title":"Alleviating Over-segmentation Errors by Detecting Action Boundaries","created":"2020-07-14","cited_by_count":87},{"id":"1602.02995","title":"Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation","created":"2016-02-09","cited_by_count":78},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"1509.01947","title":"An end-to-end generative framework for video segmentation and recognition","created":"2015-09-07","cited_by_count":61},{"id":"2106.07631","title":"Improved Transformer for High-Resolution GANs","created":"2021-06-14","cited_by_count":59},{"id":"2209.00638","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","created":"2022-09-01","cited_by_count":55},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50},{"id":"2101.00910","title":"Global2Local: Efficient Structure Search for Video Action Segmentation","created":"2021-01-04","cited_by_count":42},{"id":"1904.03116","title":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency","created":"2019-04-05","cited_by_count":30},{"id":"2012.07508","title":"Temporal Relational Modeling with Self-Supervision for Action Segmentation","created":"2020-12-14","cited_by_count":29},{"id":"2105.10859","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","created":"2021-05-23","cited_by_count":28},{"id":"2106.09650","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","created":"2021-06-17","cited_by_count":16},{"id":"2108.03894","title":"FIFA: Fast Inference Approximation for Action Segmentation","created":"2021-08-09","cited_by_count":16},{"id":"1909.09269","title":"Fine-grained Action Segmentation using the Semi-Supervised Action GAN","created":"2019-09-20","cited_by_count":12},{"id":"2302.13074","title":"Temporal Segment Transformer for Action Segmentation","created":"2023-02-25","cited_by_count":3}],"next_cursor":null}