{"total":33,"rows":[{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745,"area":null},{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2212.04408","title":"OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13,"area":null},{"id":"2303.13455","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2208.06162","title":"Layout-Bridging Text-to-Image Synthesis","created":"2022-08-12","cited_by_count":9,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2405.19333","title":"Multi-Modal Generative Embedding Model","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2208.03431","title":"IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation","created":"2022-08-06","cited_by_count":6,"area":null},{"id":"2207.13428","title":"Leveraging GAN Priors for Few-Shot Part Segmentation","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2210.00434","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2404.11824","title":"TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2203.04218","title":"Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2502.08921","title":"Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2510.16791","title":"Personalized Image Filter: Mastering Your Photographic Style","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2210.16174","title":"Multimodal Transformer for Parallel Concatenated Variational Autoencoders","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2311.17959","title":"Transformer Based Model for Predicting Rapid Impact Compaction Outcomes: A Case Study of Utapao International Airport","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2312.03041","title":"Transformer-Based Deep Learning Model for Bored Pile Load-Deformation Prediction in Bangkok Subsoil","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2409.05918","title":"Developing an Explainable Artificial Intelligent (XAI) Model for Predicting Pile Driving Vibrations in Bangkok's Subsoil","created":"2024-09-08","cited_by_count":0,"area":null}],"next_cursor":null}