{"list":"other","total":57,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"1711.08189","title":"An Analysis of Scale Invariance in Object Detection - SNIP","created":"2017-11-22","cited_by_count":120},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1911.06644","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","created":"2019-11-15","cited_by_count":59},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"2007.14937","title":"Learning Video Representations from Textual Web Supervision","created":"2020-07-29","cited_by_count":40},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"2006.09116","title":"1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020","created":"2020-06-16","cited_by_count":2}],"next_cursor":null}