Search Results for author:
Found 5 papers, 1 papers with code
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
To tackle the problems, we propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation.
Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering
Based on our formulation, we further propose MulTi-Modal PRompt LearnIng with DecouPLing bEfore InTeraction (TRIPLET), a novel approach that builds on a pre-trained vision-language model and consists of decoupled prompts and prompt interaction strategies to capture the complex interactions between modalities.
Unsupervised Visual Program Induction with Function Modularization
Program induction serves as one way to analog the ability of human thinking.
Weakly Supervised Dense Event Captioning in Videos
Dense event captioning aims to detect and describe all events of interest contained in a video.
Learning-to-Ask: Knowledge Acquisition via 20 Questions
Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors.
