{"list":"other","total":159,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"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":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"1701.08398","title":"Re-ranking Person Re-identification with k-reciprocal Encoding","created":"2017-01-29","cited_by_count":262},{"id":"2006.02713","title":"Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID","created":"2020-06-04","cited_by_count":212},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1610.02984","title":"Person Re-identification: Past, Present and Future","created":"2016-10-10","cited_by_count":181},{"id":"2211.13977","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","created":"2022-11-25","cited_by_count":181},{"id":"1711.07027","title":"Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification","created":"2017-11-19","cited_by_count":168},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"1906.08332","title":"A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification","created":"2019-06-19","cited_by_count":155},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"2005.11037","title":"Style Normalization and Restitution for Generalizable Person Re-identification","created":"2020-05-22","cited_by_count":136},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132},{"id":"1904.02998","title":"Relation-Aware Global Attention for Person Re-identification","created":"2019-04-05","cited_by_count":124},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120},{"id":"1903.09254","title":"CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification","created":"2019-03-21","cited_by_count":119},{"id":"2012.00417","title":"Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification","created":"2020-12-01","cited_by_count":110},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110},{"id":"2004.09228","title":"Unsupervised Person Re-identification via Multi-label Classification","created":"2020-04-20","cited_by_count":107},{"id":"2003.08177","title":"High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification","created":"2020-03-18","cited_by_count":106},{"id":"1910.05839","title":"RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment","created":"2019-10-13","cited_by_count":102},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102},{"id":"1804.00216","title":"Human Semantic Parsing for Person Re-identification","created":"2018-03-31","cited_by_count":100},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96},{"id":"2012.03753","title":"Unsupervised Pre-training for Person Re-identification","created":"2020-12-07","cited_by_count":95},{"id":"2002.02295","title":"Person Re-identification by Contour Sketch under Moderate Clothing Change","created":"2020-02-06","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":"2103.11568","title":"Cluster Contrast for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":89},{"id":"1709.08325","title":"Pose-driven Deep Convolutional Model for Person Re-identification","created":"2017-09-25","cited_by_count":86},{"id":"2005.12633","title":"Long-Term Cloth-Changing Person Re-identification","created":"2020-05-26","cited_by_count":85},{"id":"1812.02162","title":"Dissecting Person Re-identification from the Viewpoint of Viewpoint","created":"2018-12-05","cited_by_count":83},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"1611.05666","title":"A Discriminatively Learned CNN Embedding for Person Re-identification","created":"2016-11-17","cited_by_count":78},{"id":"2005.07327","title":"ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language","created":"2020-05-15","cited_by_count":78},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78},{"id":"2011.14670","title":"Meta Batch-Instance Normalization for Generalizable Person Re-Identification","created":"2020-11-30","cited_by_count":77},{"id":"2004.03547","title":"Unsupervised Person Re-identification via Softened Similarity Learning","created":"2020-04-07","cited_by_count":75},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75},{"id":"1804.02792","title":"Occluded Person Re-identification","created":"2018-04-09","cited_by_count":72},{"id":"2002.04114","title":"Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification","created":"2020-02-10","cited_by_count":71},{"id":"2103.15537","title":"Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization","created":"2021-03-29","cited_by_count":69},{"id":"2103.16364","title":"ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification","created":"2021-03-30","cited_by_count":69},{"id":"2112.02466","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","created":"2021-12-05","cited_by_count":68},{"id":"1908.05819","title":"Mixed High-Order Attention Network for Person Re-Identification","created":"2019-08-16","cited_by_count":65},{"id":"1908.10534","title":"Adversarial Representation Learning for Text-to-Image Matching","created":"2019-08-28","cited_by_count":65},{"id":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65},{"id":"1906.09610","title":"Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments","created":"2019-06-23","cited_by_count":64},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62},{"id":"2203.14675","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","created":"2022-03-28","cited_by_count":59},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2103.12366","title":"Group-aware Label Transfer for Domain Adaptive Person Re-identification","created":"2021-03-23","cited_by_count":58},{"id":"2204.09331","title":"NFormer: Robust Person Re-identification with Neighbor Transformer","created":"2022-04-20","cited_by_count":57},{"id":"1903.00535","title":"Unsupervised Tracklet Person Re-Identification","created":"2019-03-01","cited_by_count":55},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54},{"id":"1903.06325","title":"Unsupervised Person Re-identification by Soft Multilabel Learning","created":"2019-03-15","cited_by_count":53},{"id":"2004.05021","title":"Parsing-based View-aware Embedding Network for Vehicle Re-Identification","created":"2020-04-10","cited_by_count":53},{"id":"2103.11658","title":"Intra-Inter Camera Similarity for Unsupervised Person Re-Identification","created":"2021-03-22","cited_by_count":52},{"id":"2108.02413","title":"IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID","created":"2021-08-05","cited_by_count":51},{"id":"2107.05475","title":"GiT: Graph Interactive Transformer for Vehicle Re-identification","created":"2021-07-12","cited_by_count":49},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48},{"id":"1811.07749","title":"Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data","created":"2018-11-19","cited_by_count":46},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46},{"id":"2106.06133","title":"Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification","created":"2021-06-11","cited_by_count":45},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45},{"id":"2104.04163","title":"Combined Depth Space based Architecture Search For Person Re-identification","created":"2021-04-09","cited_by_count":44},{"id":"2107.02380","title":"Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification","created":"2021-07-06","cited_by_count":44},{"id":"2107.05946","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","created":"2021-07-13","cited_by_count":39},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38},{"id":"1905.13258","title":"A survey of advances in vision-based vehicle re-identification","created":"2019-05-30","cited_by_count":36},{"id":"1908.05024","title":"Person Re-identification in Aerial Imagery","created":"2019-08-14","cited_by_count":36},{"id":"1912.08855","title":"Simulating Content Consistent Vehicle Datasets with Attribute Descent","created":"2019-12-18","cited_by_count":36},{"id":"2012.04268","title":"UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification","created":"2020-12-08","cited_by_count":36}],"next_cursor":"100"}