{"list":"other","total":71,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"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":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"1910.07677","title":"Cross Attention Network for Few-shot Classification","created":"2019-10-17","cited_by_count":219},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"1709.01643","title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","created":"2017-09-06","cited_by_count":91},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"1906.00562","title":"Learning to Self-Train for Semi-Supervised Few-Shot Classification","created":"2019-06-03","cited_by_count":83},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"1810.02334","title":"Unsupervised Learning via Meta-Learning","created":"2018-10-04","cited_by_count":82},{"id":"2103.17263","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","created":"2021-03-31","cited_by_count":81},{"id":"1811.11819","title":"Unsupervised Meta-Learning For Few-Shot Image Classification","created":"2018-11-28","cited_by_count":75},{"id":"1811.11387","title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","created":"2018-11-28","cited_by_count":71},{"id":"1907.09021","title":"TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition","created":"2019-07-21","cited_by_count":71},{"id":"1804.05298","title":"Multi-level Semantic Feature Augmentation for One-shot Learning","created":"2018-04-15","cited_by_count":62},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53},{"id":"2010.09982","title":"Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition","created":"2020-10-20","cited_by_count":50},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48},{"id":"1412.6056","title":"Unsupervised Learning of Spatiotemporally Coherent Metrics","created":"2014-12-18","cited_by_count":46},{"id":"1809.04440","title":"Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching","created":"2018-09-10","cited_by_count":46},{"id":"2008.02531","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","created":"2020-08-06","cited_by_count":46},{"id":"1908.05257","title":"Few-Shot Learning with Global Class Representations","created":"2019-08-14","cited_by_count":44},{"id":"1909.07945","title":"ProtoGAN: Towards Few Shot Learning for Action Recognition","created":"2019-09-17","cited_by_count":41},{"id":"2012.07962","title":"Iterative label cleaning for transductive and semi-supervised few-shot learning","created":"2020-12-14","cited_by_count":40},{"id":"1912.09033","title":"TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning","created":"2019-12-19","cited_by_count":39},{"id":"2104.03214","title":"Self-Supervised Learning for Semi-Supervised Temporal Action Proposal","created":"2021-04-07","cited_by_count":39},{"id":"2107.04782","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","created":"2021-07-10","cited_by_count":35},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35},{"id":"1906.11888","title":"Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks","created":"2019-06-09","cited_by_count":32},{"id":"2002.05873","title":"Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention","created":"2020-02-14","cited_by_count":28},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27},{"id":"1902.09884","title":"Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation","created":"2019-02-26","cited_by_count":24},{"id":"2105.08149","title":"Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments","created":"2021-05-17","cited_by_count":23},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23},{"id":"2109.13227","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","created":"2021-09-27","cited_by_count":17},{"id":"2107.00197","title":"Few-Shot Learning with a Strong Teacher","created":"2021-07-01","cited_by_count":16},{"id":"2109.15317","title":"Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation","created":"2021-09-30","cited_by_count":11},{"id":"1907.09382","title":"Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition","created":"2019-07-22","cited_by_count":9},{"id":"2012.10844","title":"PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning","created":"2020-12-20","cited_by_count":9},{"id":"1810.10866","title":"Convolutional Set Matching for Graph Similarity","created":"2018-10-23","cited_by_count":7},{"id":"1912.12178","title":"Unsupervised Few-shot Learning via Self-supervised Training","created":"2019-12-20","cited_by_count":7},{"id":"2007.04755","title":"Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation","created":"2020-07-09","cited_by_count":6},{"id":"1905.12277","title":"Learning Task-specific Representation for Novel Words in Sequence Labeling","created":"2019-05-29","cited_by_count":5}],"next_cursor":null}