{"list":"other","total":58,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"1910.00033","title":"Hidden Trigger Backdoor Attacks","created":"2019-09-30","cited_by_count":371},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"1805.10917","title":"Deep Anomaly Detection Using Geometric Transformations","created":"2018-05-28","cited_by_count":269},{"id":"2003.06054","title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","created":"2020-03-12","cited_by_count":231},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2005.02359","title":"Classification-Based Anomaly Detection for General Data","created":"2020-05-05","cited_by_count":211},{"id":"1507.00448","title":"Cross Modal Distillation for Supervision Transfer","created":"2015-07-02","cited_by_count":175},{"id":"1703.04044","title":"Colorization as a Proxy Task for Visual Understanding","created":"2017-03-11","cited_by_count":175},{"id":"1804.10427","title":"Open Set Domain Adaptation by Backpropagation","created":"2018-04-27","cited_by_count":150},{"id":"2003.12815","title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","created":"2020-03-28","cited_by_count":134},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"2104.03620","title":"Open Domain Generalization with Domain-Augmented Meta-Learning","created":"2021-04-08","cited_by_count":115},{"id":"2007.12360","title":"On the Effectiveness of Image Rotation for Open Set Domain Adaptation","created":"2020-07-24","cited_by_count":72},{"id":"2310.19795","title":"SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization","created":"2023-10-30","cited_by_count":48},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"2302.02615","title":"Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need","created":"2023-02-06","cited_by_count":46},{"id":"2211.15656","title":"SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation","created":"2022-11-28","cited_by_count":39},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35},{"id":"2209.07027","title":"Out-of-Distribution Representation Learning for Time Series Classification","created":"2022-09-15","cited_by_count":31},{"id":"2405.17419","title":"MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities","created":"2024-05-27","cited_by_count":28},{"id":"2308.09391","title":"Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization","created":"2023-08-18","cited_by_count":24},{"id":"2208.07364","title":"Online Pole Segmentation on Range Images for Long-term LiDAR Localization in Urban Environments","created":"2022-08-15","cited_by_count":12}],"next_cursor":null}