{"total":22,"rows":[{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85,"area":null},{"id":"2111.10023","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","created":"2021-11-19","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2202.07247","title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","created":"2022-02-15","cited_by_count":25,"area":null},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23,"area":null},{"id":"2105.13073","title":"Maria: A Visual Experience Powered Conversational Agent","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"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":"2312.15162","title":"Cycle-Consistency Learning for Captioning and Grounding","created":"2023-12-23","cited_by_count":6,"area":null},{"id":"2305.14260","title":"R2H: Building Multimodal Navigation Helpers that Respond to Help Requests","created":"2023-05-23","cited_by_count":5,"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":"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":"2107.13083","title":"Is Object Detection Necessary for Human-Object Interaction Recognition?","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2308.11331","title":"GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2407.11008","title":"Figuring out Figures: Using Textual References to Caption Scientific Figures","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2410.16624","title":"EVC-MF: End-to-end Video Captioning Network with Multi-scale Features","created":"2024-10-22","cited_by_count":0,"area":null}],"next_cursor":null}