{"list":"other","total":74,"rows":[{"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":"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","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":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1905.13211","title":"What Can Neural Networks Reason About?","created":"2019-05-30","cited_by_count":159},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"1902.03748","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","created":"2019-02-11","cited_by_count":114},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1703.06189","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","created":"2017-03-17","cited_by_count":113},{"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":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"2003.12424","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","created":"2020-03-27","cited_by_count":59},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"1802.05451","title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","created":"2018-02-15","cited_by_count":44},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"1708.02349","title":"Temporal Context Network for Activity Localization in Videos","created":"2017-08-08","cited_by_count":37},{"id":"2006.15327","title":"Compositional Video Synthesis with Action Graphs","created":"2020-06-27","cited_by_count":34},{"id":"1803.10362","title":"Referring Relationships","created":"2018-03-28","cited_by_count":29},{"id":"1704.04671","title":"Temporal Action Localization by Structured Maximal Sums","created":"2017-04-15","cited_by_count":28},{"id":"1905.08586","title":"Marginalized Average Attentional Network for Weakly-Supervised Learning","created":"2019-05-21","cited_by_count":24},{"id":"1902.10200","title":"Differentiable Scene Graphs","created":"2019-02-26","cited_by_count":16},{"id":"2009.14558","title":"Learning Object Detection from Captions via Textual Scene Attributes","created":"2020-09-30","cited_by_count":14}],"next_cursor":null}