{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"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":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"2008.03673","title":"Feature Space Augmentation for Long-Tailed Data","created":"2020-08-09","cited_by_count":136},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"2002.10826","title":"Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective","created":"2020-02-25","cited_by_count":120},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"2010.16219","title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","created":"2020-10-30","cited_by_count":81},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"2104.07256","title":"A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation","created":"2021-04-15","cited_by_count":79},{"id":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"2005.11643","title":"Robust Object Detection under Occlusion with Context-Aware CompositionalNets","created":"2020-05-24","cited_by_count":54},{"id":"1605.03688","title":"Going Deeper into First-Person Activity Recognition","created":"2016-05-12","cited_by_count":48},{"id":"2003.04490","title":"Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion","created":"2020-03-10","cited_by_count":47},{"id":"1902.09811","title":"LaSO: Label-Set Operations networks for multi-label few-shot learning","created":"2019-02-26","cited_by_count":38},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35},{"id":"2211.15393","title":"Video Test-Time Adaptation for Action Recognition","created":"2022-11-24","cited_by_count":35},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"1511.04196","title":"Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition","created":"2015-11-13","cited_by_count":27},{"id":"2002.03137","title":"Symbiotic Attention with Privileged Information for Egocentric Action Recognition","created":"2020-02-08","cited_by_count":27},{"id":"2206.06931","title":"Stand-Alone Inter-Frame Attention in Video Models","created":"2022-06-14","cited_by_count":19},{"id":"2203.09694","title":"Group Contextualization for Video Recognition","created":"2022-03-18","cited_by_count":18},{"id":"2203.03145","title":"End-to-end video instance segmentation via spatial-temporal graph neural networks","created":"2022-03-07","cited_by_count":16},{"id":"2007.05756","title":"Generative Compositional Augmentations for Scene Graph Prediction","created":"2020-07-11","cited_by_count":14},{"id":"1412.6505","title":"Pooled Motion Features for First-Person Videos","created":"2014-12-19","cited_by_count":10},{"id":"2003.14065","title":"Long Short-Term Relation Networks for Video Action Detection","created":"2020-03-31","cited_by_count":10},{"id":"1504.07469","title":"Compact CNN for Indexing Egocentric Videos","created":"2015-04-28","cited_by_count":9},{"id":"1909.04743","title":"Reasoning About Human-Object Interactions Through Dual Attention Networks","created":"2019-09-10","cited_by_count":9},{"id":"2202.12116","title":"Motion-driven Visual Tempo Learning for Video-based Action Recognition","created":"2022-02-24","cited_by_count":9},{"id":"2201.04027","title":"Representing Videos as Discriminative Sub-graphs for Action Recognition","created":"2022-01-11","cited_by_count":8},{"id":"2204.04796","title":"SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition","created":"2022-04-10","cited_by_count":8},{"id":"2010.01007","title":"DecAug: Augmenting HOI Detection via Decomposition","created":"2020-10-02","cited_by_count":6},{"id":"2210.11387","title":"Transformer-based Action recognition in hand-object interacting scenarios","created":"2022-10-20","cited_by_count":2}],"next_cursor":null}