Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-Stage Action Localization
CVPR 2024（2024）
关键词
Vision Transformer,Bipartite Matching,Action Localization,Classification Task,Recognition Task,Bounding Box,Detection Task,Transformer Model,Aspect Ratio,Feature Maps,Object Detection,Precision And Recall,Pooling Layer,Video Clips,Action Recognition,Image Patches,Classification Loss,Two-stage Approach,Action Classes,Good Trade-off,Action Detection,Center Of Frame,Output Embedding,Mean Average Precision,Person Detection
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要