{"total":41,"rows":[{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76,"area":null},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67,"area":null},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2203.15793","title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":55,"area":null},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35,"area":null},{"id":"2102.04990","title":"In Defense of Scene Graphs for Image Captioning","created":"2021-02-09","cited_by_count":31,"area":null},{"id":"2310.10404","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"area":null},{"id":"2304.03495","title":"Devil's on the Edges: Selective Quad Attention for Scene Graph Generation","created":"2023-04-07","cited_by_count":23,"area":null},{"id":"2201.06794","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2210.03925","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","created":"2022-10-08","cited_by_count":18,"area":null},{"id":"2307.08699","title":"Pair then Relation: Pair-Net for Panoptic Scene Graph Generation","created":"2023-07-17","cited_by_count":17,"area":null},{"id":"2303.06338","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","created":"2023-03-11","cited_by_count":12,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2308.03282","title":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation","created":"2023-08-07","cited_by_count":9,"area":null},{"id":"2201.04027","title":"Representing Videos as Discriminative Sub-graphs for Action Recognition","created":"2022-01-11","cited_by_count":8,"area":null},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2504.00844","title":"PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2210.14862","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2203.05346","title":"Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling","created":"2022-03-10","cited_by_count":3,"area":null},{"id":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2111.10146","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2210.08675","title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2305.10126","title":"Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2309.03542","title":"Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2407.11393","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2308.06685","title":"Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion","created":"2023-08-13","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":"2602.00637","title":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2308.12048","title":"Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2503.08496","title":"SuperCap: Multi-resolution Superpixel-based Image Captioning","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2603.07704","title":"PARSE: Part-Aware Relational Spatial Modeling","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.26804","title":"The Language of Touch: Translating Vibrations into Text with Dual-Branch Learning","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}