{"total":20,"rows":[{"id":"2301.09506","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","created":"2023-01-23","cited_by_count":43,"area":null},{"id":"2308.11322","title":"CiteTracker: Correlating Image and Text for Visual Tracking","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2309.00096","title":"AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation","created":"2023-08-31","cited_by_count":29,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2404.03539","title":"Is CLIP the main roadblock for fine-grained open-world perception?","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2410.18195","title":"Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2412.16829","title":"Visual Prompting with Iterative Refinement for Design Critique Generation","created":"2024-12-22","cited_by_count":5,"area":null},{"id":"2405.16071","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2411.19106","title":"Detailed Object Description with Controllable Dimensions","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2503.19145","title":"Compositional Caching for Training-free Open-vocabulary Attribute Detection","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2406.01551","title":"ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2503.14862","title":"Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2305.20047","title":"LOWA: Localize Objects in the Wild with Attributes","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2406.12757","title":"MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2410.12439","title":"Beyond Attribution: Unified Concept-Level Explanations","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2409.06300","title":"An Attribute-Enriched Dataset and Auto-Annotated Pipeline for Open Detection","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2609.08886","title":"FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.27076","title":"Pro-Bench: Prompt-Robust Open-Vocabulary Visual Grounding Across Real-World Heterogeneous Environments","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.03084","title":"NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}