{"list":"other","total":54,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"1912.04573","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","created":"2019-12-10","cited_by_count":125},{"id":"2003.08429","title":"STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos","created":"2020-03-18","cited_by_count":121},{"id":"2007.14772","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","created":"2020-07-29","cited_by_count":108},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83},{"id":"1908.09511","title":"Relation Distillation Networks for Video Object Detection","created":"2019-08-26","cited_by_count":77},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","cited_by_count":60},{"id":"2003.13042","title":"Omni-sourced Webly-supervised Learning for Video Recognition","created":"2020-03-29","cited_by_count":48},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37},{"id":"1903.09126","title":"Progressive Sparse Local Attention for Video object detection","created":"2019-03-21","cited_by_count":30},{"id":"2401.09923","title":"MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection","created":"2024-01-18","cited_by_count":13}],"next_cursor":null}