{"total":14,"rows":[{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"area":null},{"id":"2208.02532","title":"Prompt Tuning for Generative Multimodal Pretrained Models","created":"2022-08-04","cited_by_count":25,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2309.10121","title":"Pre-training on Synthetic Driving Data for Trajectory Prediction","created":"2023-09-18","cited_by_count":18,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2310.05867","title":"Domain-wise Invariant Learning for Panoptic Scene Graph Generation","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2504.05700","title":"Pose-Aware Weakly-Supervised Action Segmentation","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2303.06911","title":"ViM: Vision Middleware for Unified Downstream Transferring","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2308.12910","title":"SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2311.02536","title":"Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2605.13835","title":"Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}