{"total":114,"rows":[{"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,"area":"mllm"},{"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,"area":null},{"id":"2212.04074","title":"Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence","created":"2022-12-08","cited_by_count":70,"area":null},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","cited_by_count":35,"area":null},{"id":"2411.18894","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","created":"2024-11-28","cited_by_count":35,"area":null},{"id":"2312.09612","title":"TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation","created":"2023-12-15","cited_by_count":32,"area":null},{"id":"2306.03428","title":"GaitGCI: Generative Counterfactual Intervention for Gait Recognition","created":"2023-06-06","cited_by_count":31,"area":null},{"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,"area":null},{"id":"2203.02751","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","created":"2022-03-05","cited_by_count":28,"area":null},{"id":"2308.09624","title":"GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglement","created":"2023-08-18","cited_by_count":28,"area":null},{"id":"2303.06442","title":"Fine-grained Visual Classification with High-temperature Refinement and Background Suppression","created":"2023-03-11","cited_by_count":22,"area":null},{"id":"2209.02109","title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","created":"2022-09-05","cited_by_count":21,"area":null},{"id":"2412.10707","title":"MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt","created":"2024-12-14","cited_by_count":20,"area":"ssm"},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"area":"lr"},{"id":"2208.14607","title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","created":"2022-08-31","cited_by_count":19,"area":null},{"id":"2208.00967","title":"Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification","created":"2022-08-01","cited_by_count":18,"area":null},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17,"area":null},{"id":"2411.18111","title":"When Large Vision-Language Models Meet Person Re-Identification","created":"2024-11-27","cited_by_count":15,"area":"mllm"},{"id":"2309.08912","title":"Delving into Multimodal Prompting for Fine-grained Visual Classification","created":"2023-09-16","cited_by_count":14,"area":null},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2406.14551","title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","created":"2024-06-20","cited_by_count":12,"area":null},{"id":"2202.03822","title":"A Novel Plug-in Module for Fine-Grained Visual Classification","created":"2022-02-08","cited_by_count":11,"area":null},{"id":"2310.17218","title":"Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification","created":"2023-10-26","cited_by_count":11,"area":"mllm"},{"id":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11,"area":null},{"id":"2210.13889","title":"Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2305.15762","title":"Dynamic Enhancement Network for Partial Multi-modality Person Re-identification","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2410.06977","title":"Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification","created":"2024-10-09","cited_by_count":10,"area":null},{"id":"2110.07933","title":"Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems","created":"2021-10-15","cited_by_count":8,"area":null},{"id":"2205.10529","title":"Fine-Grained Visual Classification using Self Assessment Classifier","created":"2022-05-21","cited_by_count":8,"area":null},{"id":"2410.21938","title":"ReMix: Training Generalized Person Re-identification on a Mixture of Data","created":"2024-10-29","cited_by_count":8,"area":null},{"id":"2505.17821","title":"ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2210.07138","title":"Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning","created":"2022-10-13","cited_by_count":7,"area":"lr"},{"id":"2308.14551","title":"Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics","created":"2023-08-28","cited_by_count":7,"area":null},{"id":"2501.16811","title":"Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2510.23301","title":"MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2112.02747","title":"Making a Bird AI Expert Work for You and Me","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2305.06145","title":"Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID","created":"2023-05-10","cited_by_count":6,"area":null},{"id":"2308.10717","title":"Rethinking Person Re-identification from a Projection-on-Prototypes Perspective","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2405.01101","title":"Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2406.16042","title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","created":"2024-06-23","cited_by_count":6,"area":"diffusion"},{"id":"2503.08173","title":"Towards All-in-One Medical Image Re-Identification","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2505.20001","title":"NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification","created":"2025-05-26","cited_by_count":6,"area":"moe"},{"id":"2208.01997","title":"Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization","created":"2022-08-03","cited_by_count":5,"area":null},{"id":"2209.08630","title":"RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learning","created":"2022-09-18","cited_by_count":5,"area":null},{"id":"2504.11798","title":"Neighbor-Based Feature and Index Enhancement for Person Re-Identification","created":"2025-04-16","cited_by_count":5,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2209.06367","title":"A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2407.12891","title":"Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2410.09382","title":"CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification","created":"2024-10-12","cited_by_count":4,"area":"mllm"},{"id":"2503.12385","title":"Car-1000: A New Large Scale Fine-Grained Visual Categorization Dataset","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2504.10985","title":"DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2504.14847","title":"Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2210.12348","title":"A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning","created":"2022-10-22","cited_by_count":3,"area":null},{"id":"2305.15354","title":"Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2403.10298","title":"Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2405.19005","title":"Auto-selected Knowledge Adapters for Lifelong Person Re-identification","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2502.16815","title":"CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2603.25144","title":"FD$^2$: A Dedicated Framework for Fine-Grained Dataset Distillation","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2207.09884","title":"Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2305.15764","title":"Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2203.12816","title":"ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2206.01153","title":"Multi-View Active Fine-Grained Recognition","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2309.01166","title":"Spatial-temporal Vehicle Re-identification","created":"2023-09-03","cited_by_count":1,"area":null},{"id":"2401.08860","title":"Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2407.03842","title":"Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2408.13542","title":"Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2409.11051","title":"Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2412.11668","title":"Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2505.23365","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2112.04662","title":"Dual Cluster Contrastive learning for Object Re-Identification","created":"2021-12-09","cited_by_count":0,"area":null},{"id":"2209.09857","title":"Fine-grained Classification of Solder Joints with {\\alpha}-skew Jensen-Shannon Divergence","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2212.02398","title":"Generalizable Person Re-Identification via Viewpoint Alignment and Fusion","created":"2022-12-05","cited_by_count":0,"area":null},{"id":"2302.05753","title":"DaliID: Distortion-Adaptive Learned Invariance for Identification Models","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2302.10275","title":"Semantic Feature Integration network for Fine-grained Visual Classification","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2304.01647","title":"SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2309.13924","title":"Recursive Counterfactual Deconfounding for Object Recognition","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2310.15999","title":"Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2403.08270","title":"Identity-aware Dual-constraint Network for Cloth-Changing Person Re-identification","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2407.04243","title":"Exploration of Class Center for Fine-Grained Visual Classification","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2407.07351","title":"Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2407.07842","title":"Study on Aspect Ratio Variability toward Robustness of Vision Transformer-based Vehicle Re-identification","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2408.05558","title":"Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matching","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2408.13774","title":"Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild","created":"2024-08-25","cited_by_count":0,"area":null},{"id":"2409.12002","title":"Towards Global Localization using Multi-Modal Object-Instance Re-Identification","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.06600","title":"DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2411.15729","title":"OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2503.07075","title":"XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition","created":"2025-03-10","cited_by_count":0,"area":"mllm"},{"id":"2504.08919","title":"Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.20540","title":"Causality and \"In-the-Wild\" Video-Based Person Re-ID: A Survey","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2508.21154","title":"RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.18535","title":"Trace Is In Sentences: Unbiased Lightweight ChatGPT-Generated Text Detector","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.10260","title":"H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2511.12547","title":"HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models","created":"2025-11-16","cited_by_count":0,"area":"diffusion"},{"id":"2511.12992","title":"Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2511.21653","title":"CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2603.17412","title":"Mutually Causal Semantic Distillation Network for Zero-Shot Learning","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.21482","title":"ALADIN:Attribute-Language Distillation Network for Person Re-Identification","created":"2026-03-23","cited_by_count":0,"area":"mllm"},{"id":"2604.19345","title":"Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":"100"}