{"total":21,"rows":[{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35,"area":null},{"id":"2302.06098","title":"Towards Local Visual Modeling for Image Captioning","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2111.09276","title":"Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval","created":"2021-11-17","cited_by_count":13,"area":null},{"id":"2403.17709","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","created":"2024-03-26","cited_by_count":11,"area":null},{"id":"2211.16769","title":"Uncertainty-Aware Image Captioning","created":"2022-11-30","cited_by_count":6,"area":null},{"id":"2305.18668","title":"Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2405.16116","title":"REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2504.11441","title":"TADACap: Time-series Adaptive Domain-Aware Captioning","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2401.12835","title":"SGTR+: End-to-end Scene Graph Generation with Transformer","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2506.05399","title":"Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2603.06386","title":"REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2204.13324","title":"Controllable Image Captioning","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2206.06322","title":"Tackling Multiple Tasks with One Single Learning Framework","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2206.06323","title":"Visual Transformer for Object Detection","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2209.09198","title":"A Masked Bounding-Box Selection Based ResNet Predictor for Text Rotation Prediction","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2603.10538","title":"DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime","created":"2026-03-11","cited_by_count":0,"area":null}],"next_cursor":null}