{"list":"other","total":68,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"1711.09349","title":"Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)","created":"2017-11-26","cited_by_count":473},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1904.07223","title":"Joint Discriminative and Generative Learning for Person Re-identification","created":"2019-04-15","cited_by_count":213},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1704.01719","title":"Beyond triplet loss: a deep quadruplet network for person re-identification","created":"2017-04-06","cited_by_count":172},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1908.01114","title":"ABD-Net: Attentive but Diverse Person Re-Identification","created":"2019-08-03","cited_by_count":126},{"id":"2007.13467","title":"Identity-Guided Human Semantic Parsing for Person Re-Identification","created":"2020-07-27","cited_by_count":118},{"id":"1703.05446","title":"Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing","created":"2017-03-16","cited_by_count":109},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2204.08680","title":"Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer","created":"2022-04-19","cited_by_count":101},{"id":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"1804.07094","title":"Part-Aligned Bilinear Representations for Person Re-identification","created":"2018-04-19","cited_by_count":90},{"id":"1709.09930","title":"HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis","created":"2017-09-28","cited_by_count":89},{"id":"1804.01984","title":"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark","created":"2018-04-05","cited_by_count":79},{"id":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"id":"1711.07752","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","created":"2017-11-21","cited_by_count":62},{"id":"1711.08184","title":"AlignedReID: Surpassing Human-Level Performance in Person Re-Identification","created":"2017-11-22","cited_by_count":61},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"1905.13143","title":"Semantics-Aligned Representation Learning for Person Re-identification","created":"2019-05-30","cited_by_count":51},{"id":"1901.07474","title":"Pedestrian Attribute Recognition: A Survey","created":"2019-01-22","cited_by_count":50},{"id":"1910.04562","title":"Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization","created":"2019-10-10","cited_by_count":46},{"id":"2103.11617","title":"Anchor-Free Person Search","created":"2021-03-22","cited_by_count":42},{"id":"2203.16533","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","created":"2022-03-30","cited_by_count":41},{"id":"2103.10148","title":"Sequential End-to-end Network for Efficient Person Search","created":"2021-03-18","cited_by_count":38},{"id":"2111.12084","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","created":"2021-11-23","cited_by_count":36},{"id":"1603.07054","title":"A Richly Annotated Dataset for Pedestrian Attribute Recognition","created":"2016-03-23","cited_by_count":33},{"id":"2107.03576","title":"Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting","created":"2021-07-08","cited_by_count":27},{"id":"2108.03439","title":"Towards Discriminative Representation Learning for Unsupervised Person Re-identification","created":"2021-08-07","cited_by_count":20},{"id":"2105.06623","title":"City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones","created":"2021-05-14","cited_by_count":18},{"id":"2112.00317","title":"Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification","created":"2021-12-01","cited_by_count":12},{"id":"2210.13440","title":"Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval","created":"2022-10-24","cited_by_count":12},{"id":"2108.09977","title":"Exploring the Quality of GAN Generated Images for Person Re-Identification","created":"2021-08-23","cited_by_count":10},{"id":"1607.05369","title":"A Multi-task Deep Network for Person Re-identification","created":"2016-07-19","cited_by_count":9},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8},{"id":"2203.03931","title":"PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification","created":"2022-03-08","cited_by_count":8},{"id":"2106.02426","title":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","created":"2021-06-04","cited_by_count":7},{"id":"2107.02220","title":"Graph Convolution for Re-ranking in Person Re-identification","created":"2021-07-05","cited_by_count":6},{"id":"2002.09053","title":"Adapted Center and Scale Prediction: More Stable and More Accurate","created":"2020-02-20","cited_by_count":5},{"id":"2012.13498","title":"1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification","created":"2020-12-25","cited_by_count":4},{"id":"2201.09594","title":"Describe me if you can! Characterized Instance-level Human Parsing","created":"2022-01-24","cited_by_count":3},{"id":"2207.05658","title":"Dynamic Gradient Reactivation for Backward Compatible Person Re-identification","created":"2022-07-12","cited_by_count":3},{"id":"1502.03532","title":"An equalised global graphical model-based approach for multi-camera object tracking","created":"2015-02-12","cited_by_count":2},{"id":"2112.14239","title":"TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification","created":"2021-12-28","cited_by_count":2}],"next_cursor":null}