{"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":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"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":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"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":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2207.04535","title":"Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion","created":"2022-07-10","cited_by_count":21,"area":null},{"id":"2104.13872","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","created":"2021-04-28","cited_by_count":14,"area":null},{"id":"2110.09741","title":"Trajectory Prediction with Linguistic Representations","created":"2021-10-19","cited_by_count":13,"area":null},{"id":"2107.06538","title":"Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition","created":"2021-07-14","cited_by_count":12,"area":null},{"id":"2203.14499","title":"NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge","created":"2022-03-28","cited_by_count":10,"area":null},{"id":"2205.13282","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","created":"2022-05-26","cited_by_count":10,"area":null},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2112.00969","title":"Object-Centric Unsupervised Image Captioning","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2407.03919","title":"MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks","created":"2024-07-04","cited_by_count":9,"area":null},{"id":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2209.12343","title":"Paraphrasing Is All You Need for Novel Object Captioning","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2301.11174","title":"Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2106.01424","title":"Learning to Select: A Fully Attentive Approach for Novel Object Captioning","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2202.13623","title":"Interactive Machine Learning for Image Captioning","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2101.09865","title":"ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2312.06299","title":"RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2403.13444","title":"MedCycle: Unpaired Medical Report Generation via Cycle-Consistency","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2108.06165","title":"Caption Generation on Scenes with Seen and Unseen Object Categories","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","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":"2103.04846","title":"Relationship-based Neural Baby Talk","created":"2021-03-08","cited_by_count":0,"area":null},{"id":"2108.02807","title":"Neural Twins Talk & Alternative Calculations","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05115","title":"Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data","created":"2021-09-10","cited_by_count":0,"area":null},{"id":"2210.07076","title":"Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets","created":"2022-10-13","cited_by_count":0,"area":null}],"next_cursor":null}