{"list":"other","total":60,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1909.02729","title":"A Baseline for Few-Shot Image Classification","created":"2019-09-06","cited_by_count":298},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"1812.01866","title":"Few-shot Object Detection via Feature Reweighting","created":"2018-12-05","cited_by_count":265},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"1706.03466","title":"Few-Shot Image Recognition by Predicting Parameters from Activations","created":"2017-06-12","cited_by_count":122},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"2003.10658","title":"CRNet: Cross-Reference Networks for Few-Shot Segmentation","created":"2020-03-24","cited_by_count":101},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"id":"2108.09666","title":"Relational Embedding for Few-Shot Classification","created":"2021-08-22","cited_by_count":74},{"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":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"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":"2004.00163","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","created":"2020-03-31","cited_by_count":48},{"id":"1909.07945","title":"ProtoGAN: Towards Few Shot Learning for Action Recognition","created":"2019-09-17","cited_by_count":41},{"id":"2103.13582","title":"Learning Dynamic Alignment via Meta-filter for Few-shot Learning","created":"2021-03-25","cited_by_count":41},{"id":"1801.09086","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","created":"2018-01-27","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":"2101.00562","title":"Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier","created":"2021-01-03","cited_by_count":32},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28},{"id":"1805.04288","title":"Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples","created":"2018-05-11","cited_by_count":27},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27},{"id":"2105.02439","title":"Weakly Supervised Action Selection Learning in Video","created":"2021-05-06","cited_by_count":21},{"id":"2010.06215","title":"Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization","created":"2020-10-13","cited_by_count":18},{"id":"2110.12358","title":"A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark","created":"2021-10-24","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":"2007.04755","title":"Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation","created":"2020-07-09","cited_by_count":6},{"id":"2112.01034","title":"Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data","created":"2021-12-02","cited_by_count":5},{"id":"2112.01038","title":"Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips","created":"2021-12-02","cited_by_count":4}],"next_cursor":null}