{"total":33,"rows":[{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191,"area":null},{"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":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2112.00061","title":"Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources","created":"2021-11-30","cited_by_count":71,"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":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2112.00974","title":"Consensus Graph Representation Learning for Better Grounded Image Captioning","created":"2021-12-02","cited_by_count":28,"area":null},{"id":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25,"area":null},{"id":"2307.14336","title":"MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation","created":"2023-07-26","cited_by_count":24,"area":null},{"id":"2208.07722","title":"Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory","created":"2022-08-16","cited_by_count":15,"area":null},{"id":"2208.00946","title":"Motion-aware Memory Network for Fast Video Salient Object Detection","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2211.06235","title":"HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation","created":"2022-11-11","cited_by_count":11,"area":null},{"id":"2107.13978","title":"Personalized Image Semantic Segmentation","created":"2021-07-24","cited_by_count":9,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2103.11474","title":"#PraCegoVer: A Large Dataset for Image Captioning in Portuguese","created":"2021-03-21","cited_by_count":8,"area":null},{"id":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7,"area":null},{"id":"2108.05635","title":"Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments","created":"2021-08-12","cited_by_count":6,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2309.11160","title":"Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2310.17887","title":"Impressions: Understanding Visual Semiotics and Aesthetic Impact","created":"2023-10-27","cited_by_count":3,"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":"2512.06662","title":"Personalized Image Descriptions from Attention Sequences","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2106.15553","title":"Evaluation of Automated Image Descriptions for Visually Impaired Students","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2110.01033","title":"Universal Face Restoration With Memorized Modulation","created":"2021-10-03","cited_by_count":1,"area":null},{"id":"2203.01594","title":"A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism","created":"2022-03-03","cited_by_count":1,"area":null},{"id":"2406.19054","title":"A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)","created":"2024-06-27","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":"2101.11685","title":"CNN with large memory layers","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2310.07252","title":"A Comparative Study of Pre-trained CNNs and GRU-Based Attention for Image Caption Generation","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2310.12547","title":"PGA: Personalizing Grasping Agents with Single Human-Robot Interaction","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2401.01637","title":"Social Media Ready Caption Generation for Brands","created":"2024-01-03","cited_by_count":0,"area":null}],"next_cursor":null}