{"list":"other","total":76,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1610.08336","title":"The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM","created":"2016-10-26","cited_by_count":203},{"id":"2003.08111","title":"Transformer Networks for Trajectory Forecasting","created":"2020-03-18","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":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2007.03639","title":"Human Trajectory Forecasting in Crowds: A Deep Learning Perspective","created":"2020-07-07","cited_by_count":129},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2010.05654","title":"The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain","created":"2020-10-12","cited_by_count":79},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2002.08945","title":"Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction","created":"2020-02-20","cited_by_count":71},{"id":"2006.03340","title":"MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction","created":"2020-06-05","cited_by_count":69},{"id":"2003.06845","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","created":"2020-03-15","cited_by_count":62},{"id":"1711.11217","title":"Future Person Localization in First-Person Videos","created":"2017-11-30","cited_by_count":58},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"1605.03688","title":"Going Deeper into First-Person Activity Recognition","created":"2016-05-12","cited_by_count":48},{"id":"1812.02501","title":"Zero-Shot Anticipation for Instructional Activities","created":"2018-12-06","cited_by_count":43},{"id":"1809.07408","title":"Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems","created":"2018-09-19","cited_by_count":42},{"id":"1903.00445","title":"A Behavioral Approach to Visual Navigation with Graph Localization Networks","created":"2019-03-01","cited_by_count":40},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"1703.07023","title":"Encouraging LSTMs to Anticipate Actions Very Early","created":"2017-03-21","cited_by_count":37},{"id":"1707.05733","title":"Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments","created":"2017-07-18","cited_by_count":34},{"id":"1912.10867","title":"Analysis of the hands in egocentric vision: A survey","created":"2019-12-23","cited_by_count":25},{"id":"1909.06761","title":"Multitask Learning to Improve Egocentric Action Recognition","created":"2019-09-15","cited_by_count":23},{"id":"1909.09272","title":"Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks","created":"2019-09-20","cited_by_count":22},{"id":"2004.07711","title":"Knowledge Distillation for Action Anticipation via Label Smoothing","created":"2020-04-16","cited_by_count":21},{"id":"1409.1484","title":"The Evolution of First Person Vision Methods: A Survey","created":"2014-09-04","cited_by_count":19},{"id":"2006.09220","title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2020-06-16","cited_by_count":19},{"id":"2007.00095","title":"Deep Learning for Vision-based Prediction: A Survey","created":"2020-06-30","cited_by_count":19},{"id":"1808.00141","title":"Action Anticipation By Predicting Future Dynamic Images","created":"2018-08-01","cited_by_count":18},{"id":"1904.06250","title":"Generative Hybrid Representations for Activity Forecasting with No-Regret Learning","created":"2019-04-12","cited_by_count":18},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2006.03201","title":"Egocentric Object Manipulation Graphs","created":"2020-06-05","cited_by_count":17},{"id":"1911.10967","title":"Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video","created":"2019-11-25","cited_by_count":14},{"id":"1804.04118","title":"Personalized Dynamics Models for Adaptive Assistive Navigation Systems","created":"2018-04-11","cited_by_count":13},{"id":"1905.00742","title":"Egocentric Hand Track and Object-based Human Action Recognition","created":"2019-05-02","cited_by_count":12},{"id":"1802.08722","title":"A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos","created":"2018-02-23","cited_by_count":11},{"id":"1904.06090","title":"Digging Deeper into Egocentric Gaze Prediction","created":"2019-04-12","cited_by_count":11},{"id":"1812.00104","title":"From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval","created":"2018-12-01","cited_by_count":10},{"id":"1611.05335","title":"Unsupervised Learning of Important Objects from First-Person Videos","created":"2016-11-16","cited_by_count":9},{"id":"2002.00899","title":"EGO-CH: Dataset and Fundamental Tasks for Visitors BehavioralUnderstanding using Egocentric Vision","created":"2020-02-03","cited_by_count":9},{"id":"1710.07477","title":"Anticipating Daily Intention using On-Wrist Motion Triggered Sensing","created":"2017-10-20","cited_by_count":8},{"id":"1803.01413","title":"Egocentric Basketball Motion Planning from a Single First-Person Image","created":"2018-03-04","cited_by_count":8},{"id":"1811.00233","title":"Survey on Vision-based Path Prediction","created":"2018-11-01","cited_by_count":8},{"id":"2003.03530","title":"TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation","created":"2020-03-07","cited_by_count":6},{"id":"2001.11580","title":"Unsupervised Gaze Prediction in Egocentric Videos by Energy-based Surprise Modeling","created":"2020-01-30","cited_by_count":5},{"id":"2006.00830","title":"Temporal Aggregate Representations for Long-Range Video Understanding","created":"2020-06-01","cited_by_count":5},{"id":"1909.08150","title":"NEMO: Future Object Localization Using Noisy Ego Priors","created":"2019-09-17","cited_by_count":4},{"id":"1704.02163","title":"Egocentric Video Description based on Temporally-Linked Sequences","created":"2017-04-07","cited_by_count":2},{"id":"1808.02289","title":"Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-streams","created":"2018-08-07","cited_by_count":2},{"id":"2005.10420","title":"Towards Streaming Perception","created":"2020-05-21","cited_by_count":2}],"next_cursor":null}