{"total":17,"rows":[{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2408.02788","title":"GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2409.19255","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2508.10906","title":"PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2202.06633","title":"FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2412.15939","title":"Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2305.12254","title":"A request for clarity over the End of Sequence token in the Self-Critical Sequence Training","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2405.02305","title":"Inserting Faces inside Captions: Image Captioning with Attention Guided Merging","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2503.07216","title":"FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2511.15204","title":"Physics-Based Benchmarking Metrics for Multimodal Synthetic Images","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2602.01390","title":"Toward Scalable Audio Description Quality Control: A Workflow for Evaluating Human and VLM Raters","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2606.29997","title":"Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2603.10613","title":"MUNIChus: Multilingual News Image Captioning Benchmark","created":"2026-03-11","cited_by_count":0,"area":null}],"next_cursor":null}