{"list":"other","total":64,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"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":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"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":"2006.02631","title":"FastReID: A Pytorch Toolbox for General Instance Re-identification","created":"2020-06-04","cited_by_count":166},{"id":"1702.05729","title":"Person Search with Natural Language Description","created":"2017-02-19","cited_by_count":149},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120},{"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":"2406.11832","title":"Unveiling Encoder-Free Vision-Language Models","created":"2024-06-17","cited_by_count":94},{"id":"1910.06827","title":"Learning Generalisable Omni-Scale Representations for Person Re-Identification","created":"2019-10-15","cited_by_count":74},{"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":"2007.08434","title":"Appearance-Preserving 3D Convolution for Video-based Person Re-identification","created":"2020-07-16","cited_by_count":63},{"id":"1907.08427","title":"VRSTC: Occlusion-Free Video Person Re-Identification","created":"2019-07-19","cited_by_count":53},{"id":"1903.09776","title":"Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification","created":"2019-03-23","cited_by_count":51},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48},{"id":"1604.07528","title":"Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification","created":"2016-04-26","cited_by_count":41},{"id":"2212.00226","title":"Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification","created":"2022-12-01","cited_by_count":40},{"id":"2312.09627","title":"TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification","created":"2023-12-15","cited_by_count":40},{"id":"2107.05946","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","created":"2021-07-13","cited_by_count":39},{"id":"1908.05024","title":"Person Re-identification in Aerial Imagery","created":"2019-08-14","cited_by_count":36},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","cited_by_count":35},{"id":"2312.09612","title":"TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation","created":"2023-12-15","cited_by_count":32},{"id":"2412.10650","title":"DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification","created":"2024-12-14","cited_by_count":29},{"id":"2503.10324","title":"IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification","created":"2025-03-13","cited_by_count":28},{"id":"2401.06825","title":"Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification","created":"2024-01-12","cited_by_count":27},{"id":"2403.14513","title":"View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network","created":"2024-03-21","cited_by_count":23},{"id":"1901.01015","title":"Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding","created":"2019-01-04","cited_by_count":21},{"id":"2401.02634","title":"AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification","created":"2024-01-05","cited_by_count":20},{"id":"2412.10707","title":"MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt","created":"2024-12-14","cited_by_count":20},{"id":"2303.08597","title":"Aerial-Ground Person Re-ID","created":"2023-03-15","cited_by_count":19},{"id":"2310.18812","title":"UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification","created":"2023-10-28","cited_by_count":19},{"id":"2408.07500","title":"Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach","created":"2024-08-14","cited_by_count":17},{"id":"2503.06965","title":"SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks","created":"2025-03-10","cited_by_count":16},{"id":"2308.03703","title":"Video-based Person Re-identification with Long Short-Term Representation Learning","created":"2023-08-07","cited_by_count":13},{"id":"2503.08121","title":"AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification","created":"2025-03-11","cited_by_count":13},{"id":"2310.17218","title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","created":"2023-10-26","cited_by_count":11},{"id":"2405.05613","title":"Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification","created":"2024-05-09","cited_by_count":10},{"id":"2410.06977","title":"Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification","created":"2024-10-09","cited_by_count":10},{"id":"2412.17239","title":"Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification","created":"2024-12-23","cited_by_count":8},{"id":"2406.12316","title":"Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning","created":"2024-06-18","cited_by_count":6},{"id":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5},{"id":"2406.09198","title":"CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification","created":"2024-06-13","cited_by_count":4},{"id":"2312.09797","title":"Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identification","created":"2023-12-15","cited_by_count":3},{"id":"2406.03721","title":"Attribute-Aware Implicit Modality Alignment for Text Attribute Person Search","created":"2024-06-06","cited_by_count":2}],"next_cursor":null}