{"total":17,"rows":[{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"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":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2204.04216","title":"Learning Trajectory-Aware Transformer for Video Super-Resolution","created":"2022-04-08","cited_by_count":61,"area":null},{"id":"2201.10737","title":"Class-Aware Adversarial Transformers for Medical Image Segmentation","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2208.03012","title":"Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution","created":"2022-08-05","cited_by_count":25,"area":null},{"id":"2305.06524","title":"Can SAM Boost Video Super-Resolution?","created":"2023-05-11","cited_by_count":21,"area":null},{"id":"2208.05621","title":"ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design","created":"2022-08-11","cited_by_count":16,"area":null},{"id":"2203.16015","title":"ITTR: Unpaired Image-to-Image Translation with Transformers","created":"2022-03-30","cited_by_count":15,"area":null},{"id":"2210.05176","title":"Fine-Grained Image Style Transfer with Visual Transformers","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2302.08641","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2208.13717","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","created":"2022-08-29","cited_by_count":9,"area":null},{"id":"2209.03160","title":"AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2407.16171","title":"Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2212.14046","title":"Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution","created":"2022-12-27","cited_by_count":1,"area":null},{"id":"2501.02007","title":"TART: Token-based Architecture Transformer for Neural Network Performance Prediction","created":"2025-01-02","cited_by_count":0,"area":null}],"next_cursor":null}