{"list":"other","total":61,"rows":[{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"1511.02680","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","created":"2015-11-09","cited_by_count":218},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"1512.05287","title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks","created":"2015-12-16","cited_by_count":161},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"2003.00504","title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","created":"2020-03-01","cited_by_count":153},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2003.09373","title":"SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness","created":"2020-03-20","cited_by_count":112},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1904.04620","title":"Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving","created":"2019-04-09","cited_by_count":105},{"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":"1804.05132","title":"Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection","created":"2018-04-13","cited_by_count":82},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81},{"id":"1811.07253","title":"Quantifying Uncertainties in Natural Language Processing Tasks","created":"2018-11-18","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":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"1709.01907","title":"Deep and Confident Prediction for Time Series at Uber","created":"2017-09-06","cited_by_count":50},{"id":"2104.09952","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","created":"2021-04-20","cited_by_count":49},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46},{"id":"2312.00589","title":"Merlin:Empowering Multimodal LLMs with Foresight Minds","created":"2023-11-30","cited_by_count":46},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","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":"1908.09540","title":"Uncertainty-Aware Anticipation of Activities","created":"2019-08-26","cited_by_count":39},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39},{"id":"1703.07023","title":"Encouraging LSTMs to Anticipate Actions Very Early","created":"2017-03-21","cited_by_count":37},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36},{"id":"1908.10700","title":"Explainable Video Action Reasoning via Prior Knowledge and State Transitions","created":"2019-08-28","cited_by_count":33},{"id":"2111.11631","title":"Self-Regulated Learning for Egocentric Video Activity Anticipation","created":"2021-11-23","cited_by_count":32},{"id":"2008.13426","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","created":"2020-08-31","cited_by_count":29},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2305.16703","title":"Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' View","created":"2023-05-26","cited_by_count":28},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23},{"id":"1708.00945","title":"Predicting Human Activities Using Stochastic Grammar","created":"2017-08-02","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":"2308.08303","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","created":"2023-08-16","cited_by_count":16},{"id":"2010.06647","title":"Video Action Understanding","created":"2020-10-13","cited_by_count":13},{"id":"2106.08856","title":"X-MAN: Explaining multiple sources of anomalies in video","created":"2021-06-16","cited_by_count":10},{"id":"2311.15991","title":"DiffAnt: Diffusion Models for Action Anticipation","created":"2023-11-27","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":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6},{"id":"2204.00942","title":"A-ACT: Action Anticipation through Cycle Transformations","created":"2022-04-02","cited_by_count":6},{"id":"2111.11653","title":"Modeling Temporal Concept Receptive Field Dynamically for Untrimmed Video Analysis","created":"2021-11-23","cited_by_count":3}],"next_cursor":null}