{"total":23,"rows":[{"id":"2408.02265","title":"Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts","created":"2024-08-05","cited_by_count":20,"area":null},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2508.01602","title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2504.19742","title":"EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observations and Wikipedia","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2510.14737","title":"Free-Grained Hierarchical Visual Recognition","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2509.08003","title":"An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Cities","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2412.00364","title":"LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2503.01169","title":"A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2506.15084","title":"An Empirical Study of Bugs in Data Visualization Libraries","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2606.26734","title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2504.21309","title":"An Evaluation of a Visual Question Answering Strategy for Zero-shot Facial Expression Recognition in Still Images","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2508.13814","title":"Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.18938","title":"No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.17626","title":"CaMiT: A Time-Aware Car Model Dataset for Classification and Generation","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.04485","title":"Not All Birds Look The Same: Identity-Preserving Generation For Birds","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.10244","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.12303","title":"Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2601.21426","title":"MultiModal Fine-tuning with Synthetic Captions","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.15134","title":"Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2608.31107","title":"VeriCam: A Verification Baseline for the Classification of Unknown Data","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01103","title":"When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}