{"list":"other","total":81,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1803.10794","title":"TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild","created":"2018-03-28","cited_by_count":343},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"2006.10721","title":"Ocean: Object-aware Anchor-free Tracking","created":"2020-06-18","cited_by_count":212},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2003.06761","title":"Siamese Box Adaptive Network for Visual Tracking","created":"2020-03-15","cited_by_count":189},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"id":"2308.05140","title":"Robust Object Modeling for Visual Tracking","created":"2023-08-09","cited_by_count":80},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2108.00202","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","created":"2021-07-31","cited_by_count":72},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71},{"id":"1805.11761","title":"Collaborative Learning for Deep Neural Networks","created":"2018-05-30","cited_by_count":69},{"id":"2203.01885","title":"TCTrack: Temporal Contexts for Aerial Tracking","created":"2022-03-03","cited_by_count":69},{"id":"2108.00803","title":"Learn to Match: Automatic Matching Network Design for Visual Tracking","created":"2021-08-02","cited_by_count":67},{"id":"1608.05571","title":"Learning Spatially Regularized Correlation Filters for Visual Tracking","created":"2016-08-19","cited_by_count":66},{"id":"1703.04590","title":"Learning Background-Aware Correlation Filters for Visual Tracking","created":"2017-03-14","cited_by_count":65},{"id":"1803.08679","title":"Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking","created":"2018-03-23","cited_by_count":63},{"id":"2012.06048","title":"Reinforced Multi-Teacher Selection for Knowledge Distillation","created":"2020-12-11","cited_by_count":63},{"id":"2003.12949","title":"AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization","created":"2020-03-29","cited_by_count":62},{"id":"2203.01666","title":"Correlation-Aware Deep Tracking","created":"2022-03-03","cited_by_count":62},{"id":"2308.06904","title":"Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking","created":"2023-08-14","cited_by_count":53},{"id":"2401.03142","title":"Explicit Visual Prompts for Visual Object Tracking","created":"2024-01-06","cited_by_count":50},{"id":"1908.02231","title":"Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking","created":"2019-08-06","cited_by_count":47},{"id":"1609.06141","title":"Discriminative Scale Space Tracking","created":"2016-09-20","cited_by_count":46},{"id":"2205.03776","title":"SparseTT: Visual Tracking with Sparse Transformers","created":"2022-05-08","cited_by_count":36},{"id":"2308.10658","title":"Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification","created":"2023-08-21","cited_by_count":34},{"id":"2309.03979","title":"Separable Self and Mixed Attention Transformers for Efficient Object Tracking","created":"2023-09-07","cited_by_count":31},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26},{"id":"2308.10330","title":"Towards Real-World Visual Tracking with Temporal Contexts","created":"2023-08-20","cited_by_count":26},{"id":"2310.10071","title":"ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking","created":"2023-10-16","cited_by_count":25},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24},{"id":"2012.10706","title":"Siamese Anchor Proposal Network for High-Speed Aerial Tracking","created":"2020-12-19","cited_by_count":22},{"id":"2303.04378","title":"SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking","created":"2023-03-08","cited_by_count":20},{"id":"2211.12501","title":"AeDet: Azimuth-invariant Multi-view 3D Object Detection","created":"2022-11-22","cited_by_count":19},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18},{"id":"2404.09571","title":"MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution","created":"2024-04-15","cited_by_count":17},{"id":"2309.09249","title":"LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking","created":"2023-09-17","cited_by_count":16},{"id":"2309.10491","title":"DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs","created":"2023-09-19","cited_by_count":16},{"id":"2112.02571","title":"Learning Tracking Representations via Dual-Branch Fully Transformer Networks","created":"2021-12-05","cited_by_count":15},{"id":"2407.18041","title":"How to Train the Teacher Model for Effective Knowledge Distillation","created":"2024-07-25","cited_by_count":13},{"id":"2104.03114","title":"Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking","created":"2021-04-07","cited_by_count":9},{"id":"2308.11450","title":"Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking","created":"2023-08-22","cited_by_count":9},{"id":"2401.12743","title":"Correlation-Embedded Transformer Tracking: A Single-Branch Framework","created":"2024-01-23","cited_by_count":9},{"id":"2409.16652","title":"Progressive Representation Learning for Real-Time UAV Tracking","created":"2024-09-25","cited_by_count":9},{"id":"2207.01768","title":"Rank-Based Filter Pruning for Real-Time UAV Tracking","created":"2022-07-05","cited_by_count":8},{"id":"2310.05392","title":"Lightweight Full-Convolutional Siamese Tracker","created":"2023-10-09","cited_by_count":8},{"id":"2312.09716","title":"Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval","created":"2023-12-15","cited_by_count":7},{"id":"2304.00858","title":"Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition","created":"2023-04-03","cited_by_count":6},{"id":"1709.05087","title":"Viewpoint Invariant Action Recognition using RGB-D Videos","created":"2017-09-15","cited_by_count":5},{"id":"2308.10262","title":"Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking","created":"2023-08-20","cited_by_count":5},{"id":"2312.06136","title":"BACTrack: Building Appearance Collection for Aerial Tracking","created":"2023-12-11","cited_by_count":4},{"id":"2403.04363","title":"Multi-step Temporal Modeling for UAV Tracking","created":"2024-03-07","cited_by_count":3},{"id":"2306.05582","title":"A newborn embodied Turing test for view-invariant object recognition","created":"2023-06-08","cited_by_count":2}],"next_cursor":null}