{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"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":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"2007.13467","title":"Identity-Guided Human Semantic Parsing for Person Re-Identification","created":"2020-07-27","cited_by_count":118},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2402.12192","title":"Pan-Mamba: Effective pan-sharpening with State Space Model","created":"2024-02-19","cited_by_count":73},{"id":"2404.04256","title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","created":"2024-04-05","cited_by_count":71},{"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":"2403.12494","title":"Task-Customized Mixture of Adapters for General Image Fusion","created":"2024-03-19","cited_by_count":59},{"id":"2103.02440","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","created":"2021-03-03","cited_by_count":55},{"id":"2103.04337","title":"Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification","created":"2021-03-07","cited_by_count":45},{"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":"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":"2104.01745","title":"A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification","created":"2021-04-05","cited_by_count":28},{"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":"2008.02763","title":"Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network","created":"2020-08-06","cited_by_count":25},{"id":"2304.14122","title":"Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification","created":"2023-04-27","cited_by_count":21},{"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":"2310.18812","title":"UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification","created":"2023-10-28","cited_by_count":19},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18},{"id":"2208.00632","title":"Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark","created":"2022-08-01","cited_by_count":17},{"id":"2407.18112","title":"Keypoint Promptable Re-Identification","created":"2024-07-25","cited_by_count":15},{"id":"2406.13607","title":"Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution","created":"2024-06-19","cited_by_count":14},{"id":"2402.19026","title":"Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification","created":"2024-02-29","cited_by_count":13},{"id":"2305.13659","title":"Flare-Aware Cross-modal Enhancement Network for Multi-spectral Vehicle Re-identification","created":"2023-05-23","cited_by_count":10},{"id":"2305.15762","title":"Dynamic Enhancement Network for Partial Multi-modality Person Re-identification","created":"2023-05-25","cited_by_count":10},{"id":"2310.17952","title":"Shape-centered Representation Learning for Visible-Infrared Person Re-identification","created":"2023-10-27","cited_by_count":9},{"id":"2404.14985","title":"Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification","created":"2024-04-23","cited_by_count":9},{"id":"2506.02439","title":"Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification","created":"2025-06-03","cited_by_count":9},{"id":"1804.03864","title":"MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification","created":"2018-04-11","cited_by_count":8},{"id":"2409.20081","title":"ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification","created":"2024-09-30","cited_by_count":8},{"id":"2310.16856","title":"GraFT: Gradual Fusion Transformer for Multimodal Re-Identification","created":"2023-10-25","cited_by_count":7},{"id":"2603.00853","title":"Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement","created":"2026-03-01","cited_by_count":7},{"id":"2505.16161","title":"Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey","created":"2025-05-22","cited_by_count":6},{"id":"2411.00330","title":"Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification","created":"2024-11-01","cited_by_count":5},{"id":"2008.13450","title":"Receptive Multi-granularity Representation for Person Re-Identification","created":"2020-08-31","cited_by_count":4},{"id":"2511.13575","title":"Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification","created":"2025-11-17","cited_by_count":4},{"id":"2507.18064","title":"Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement","created":"2025-07-24","cited_by_count":2}],"next_cursor":null}