{"list":"other","total":85,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1701.08398","title":"Re-ranking Person Re-identification with k-reciprocal Encoding","created":"2017-01-29","cited_by_count":262},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"2003.06297","title":"Harmonizing Transferability and Discriminability for Adapting Object Detectors","created":"2020-03-13","cited_by_count":126},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"1803.11438","title":"Reconstruction Network for Video Captioning","created":"2018-03-30","cited_by_count":98},{"id":"1412.4729","title":"Translating Videos to Natural Language Using Deep Recurrent Neural Networks","created":"2014-12-15","cited_by_count":95},{"id":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"1804.07094","title":"Part-Aligned Bilinear Representations for Person Re-identification","created":"2018-04-19","cited_by_count":90},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"1505.01257","title":"A Deeper Look at Dataset Bias","created":"2015-05-06","cited_by_count":87},{"id":"1709.08325","title":"Pose-driven Deep Convolutional Model for Person Re-identification","created":"2017-09-25","cited_by_count":86},{"id":"1611.05666","title":"A Discriminatively Learned CNN Embedding for Person Re-identification","created":"2016-11-17","cited_by_count":78},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"2006.03204","title":"Black-box Explanation of Object Detectors via Saliency Maps","created":"2020-06-05","cited_by_count":76},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"1804.05275","title":"Horizontal Pyramid Matching for Person Re-identification","created":"2018-04-14","cited_by_count":70},{"id":"1905.03966","title":"Memory-Attended Recurrent Network for Video Captioning","created":"2019-05-10","cited_by_count":65},{"id":"1803.09882","title":"Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification","created":"2018-03-27","cited_by_count":55},{"id":"1505.01861","title":"Jointly Modeling Embedding and Translation to Bridge Video and Language","created":"2015-05-07","cited_by_count":53},{"id":"1710.06555","title":"Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification","created":"2017-10-18","cited_by_count":52},{"id":"1803.01457","title":"Less Is More: Picking Informative Frames for Video Captioning","created":"2018-03-05","cited_by_count":52},{"id":"2006.08315","title":"Mitigating Gender Bias in Captioning Systems","created":"2020-06-15","cited_by_count":50},{"id":"1908.10072","title":"Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network","created":"2019-08-27","cited_by_count":48},{"id":"1906.04375","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","created":"2019-06-11","cited_by_count":42},{"id":"1708.02286","title":"Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification","created":"2017-08-03","cited_by_count":39},{"id":"1711.06330","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","created":"2017-11-16","cited_by_count":37},{"id":"1704.03373","title":"Quality Aware Network for Set to Set Recognition","created":"2017-04-11","cited_by_count":36},{"id":"1804.06423","title":"Deep Object Co-Segmentation","created":"2018-04-17","cited_by_count":35},{"id":"1711.08766","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","created":"2017-11-23","cited_by_count":33},{"id":"1711.08200","title":"Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification","created":"2017-11-22","cited_by_count":27},{"id":"1805.02104","title":"Revisiting Temporal Modeling for Video-based Person ReID","created":"2018-05-05","cited_by_count":26},{"id":"1512.03622","title":"Deep Feature Learning with Relative Distance Comparison for Person Re-identification","created":"2015-12-11","cited_by_count":25},{"id":"2109.03229","title":"Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets","created":"2021-09-07","cited_by_count":22},{"id":"1504.01561","title":"Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification","created":"2015-04-07","cited_by_count":21},{"id":"1611.05592","title":"Multimodal Memory Modelling for Video Captioning","created":"2016-11-17","cited_by_count":20},{"id":"1601.06260","title":"Person Re-Identification by Discriminative Selection in Video Ranking","created":"2016-01-23","cited_by_count":16},{"id":"1701.00193","title":"Video-based Person Re-identification with Accumulative Motion Context","created":"2017-01-01","cited_by_count":16},{"id":"1810.06859","title":"Semantic Aware Attention Based Deep Object Co-segmentation","created":"2018-10-16","cited_by_count":15},{"id":"1604.08683","title":"Top-push Video-based Person Re-identification","created":"2016-04-29","cited_by_count":9},{"id":"1610.04997","title":"Spatio-Temporal Attention Models for Grounded Video Captioning","created":"2016-10-17","cited_by_count":8},{"id":"1804.03864","title":"MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification","created":"2018-04-11","cited_by_count":8},{"id":"1712.09662","title":"CNN Is All You Need","created":"2017-12-27","cited_by_count":2}],"next_cursor":null}