{"list":"other","total":67,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"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":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"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":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"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":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"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":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"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":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"1703.05884","title":"Need for Speed: A Benchmark for Higher Frame Rate Object Tracking","created":"2017-03-17","cited_by_count":137},{"id":"2207.09603","title":"AiATrack: Attention in Attention for Transformer Visual Tracking","created":"2022-07-20","cited_by_count":137},{"id":"2009.03465","title":"LaSOT: A High-quality Large-scale Single Object Tracking Benchmark","created":"2020-09-08","cited_by_count":132},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126},{"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":"2004.00070","title":"Conditional Channel Gated Networks for Task-Aware Continual Learning","created":"2020-03-31","cited_by_count":115},{"id":"2303.16580","title":"Generalized Relation Modeling for Transformer Tracking","created":"2023-03-29","cited_by_count":93},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75},{"id":"2203.01666","title":"Correlation-Aware Deep Tracking","created":"2022-03-03","cited_by_count":62},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57},{"id":"2308.06904","title":"Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking","created":"2023-08-14","cited_by_count":53},{"id":"2301.10938","title":"Compact Transformer Tracker with Correlative Masked Modeling","created":"2023-01-26","cited_by_count":50},{"id":"2112.09686","title":"Efficient Visual Tracking with Exemplar Transformers","created":"2021-12-17","cited_by_count":48},{"id":"2106.05409","title":"Zero Time Waste: Recycling Predictions in Early Exit Neural Networks","created":"2021-06-09","cited_by_count":39},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38},{"id":"2203.13537","title":"Efficient Visual Tracking via Hierarchical Cross-Attention Transformer","created":"2022-03-25","cited_by_count":24},{"id":"1708.02973","title":"Learning Policies for Adaptive Tracking with Deep Feature Cascades","created":"2017-08-09","cited_by_count":19},{"id":"2105.13792","title":"Early Exiting with Ensemble Internal Classifiers","created":"2021-05-28","cited_by_count":19},{"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":"2004.07109","title":"Fully Convolutional Online Tracking","created":"2020-04-15","cited_by_count":15},{"id":"2203.13533","title":"High-Performance Transformer Tracking","created":"2022-03-25","cited_by_count":14},{"id":"2106.10900","title":"Self-Supervised Tracking via Target-Aware Data Synthesis","created":"2021-06-21","cited_by_count":10},{"id":"2007.11404","title":"A Hybrid Neuromorphic Object Tracking and Classification Framework for Real-time Systems","created":"2020-07-21","cited_by_count":4},{"id":"2111.11625","title":"Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking","created":"2021-11-23","cited_by_count":2},{"id":"2207.04438","title":"SRRT: Exploring Search Region Regulation for Visual Object Tracking","created":"2022-07-10","cited_by_count":2},{"id":"1612.06053","title":"Dual Deep Network for Visual Tracking","created":"2016-12-19","cited_by_count":1}],"next_cursor":null}