{"total":16,"rows":[{"id":"2108.00399","title":"Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition","created":"2021-08-01","cited_by_count":12,"area":null},{"id":"2101.10531","title":"Deep Learning for Scene Classification: A Survey","created":"2021-01-26","cited_by_count":9,"area":null},{"id":"2305.08540","title":"SRRM: Semantic Region Relation Model for Indoor Scene Recognition","created":"2023-05-15","cited_by_count":5,"area":null},{"id":"2510.18229","title":"Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2106.05748","title":"Multi-resolution Outlier Pooling for Sorghum Classification","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2301.05174","title":"Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study","created":"2023-01-12","cited_by_count":3,"area":null},{"id":"2108.02093","title":"Free Lunch for Co-Saliency Detection: Context Adjustment","created":"2021-08-04","cited_by_count":1,"area":null},{"id":"2203.09343","title":"CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2307.12442","title":"EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2407.07771","title":"Multi-task Prompt Words Learning for Social Media Content Generation","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2107.11187","title":"Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2207.10174","title":"Scene Recognition with Objectness, Attribute and Category Learning","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2303.07402","title":"Designing Deep Networks for Scene Recognition","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2308.05896","title":"Semantic-embedded Similarity Prototype for Scene Recognition","created":"2023-08-11","cited_by_count":0,"area":null},{"id":"2505.15628","title":"SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2603.15648","title":"Improving Generative Adversarial Network Generalization for Facial Expression Synthesis","created":"2026-03-04","cited_by_count":0,"area":null}],"next_cursor":null}