Search Results for author:
Found 3 papers, 3 papers with code
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.
Ranked #63 on
Visual Question Answering
on MM-Vet
Regularizing Second-Order Influences for Continual Learning
Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge.
Patch-based Knowledge Distillation for Lifelong Person Re-Identification
The task of lifelong person re-identification aims to match a person across multiple cameras given continuous data streams.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
