GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning
IEEE/CVF Winter Conference on Applications of Computer Vision（2025）
Key words
Iterative Estimation,Performance Comparison,Low-dimensional Space,Short Video,Integral Operator,High Scalability,Pre-training Dataset,Fine-tuned,Task Performance,Temporal Dimension,Semantic Information,Video Content,Self-supervised Learning,Granular Data,Inference Stage,Low-dimensional Embedding,Video Duration,Video Compression,Video Summarization,Text Encoder,Pre-training Data,NVIDIA Tesla V100 GPU,AdamW Optimizer,Pre-training Stage,Video Encoding,Optimal Setup,Video Analysis,Text Length,Language Model
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined