E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer

Add code
Nov 28, 2023
Figure 1 for E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer
Figure 2 for E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer
Figure 3 for E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer
Figure 4 for E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: