Détail du document
Identifiant
oai:arXiv.org:2405.13951
Sujet
Computer Science - Computer Vision...Auteur
Kothandaraman, Divya Sohn, Kihyuk Villegas, Ruben Voigtlaender, Paul Manocha, Dinesh Babaeizadeh, MohammadCatégorie
Computer Science
Année
2024
Date de référencement
29/05/2024
Mots clés
concepts multi-concept videoRésumé
We present a method for multi-concept customization of pretrained text-to-video (T2V) models.
Intuitively, the multi-concept customized video can be derived from the (non-linear) intersection of the video manifolds of the individual concepts, which is not straightforward to find.
We hypothesize that sequential and controlled walking towards the intersection of the video manifolds, directed by text prompting, leads to the solution.
To do so, we generate the various concepts and their corresponding interactions, sequentially, in an autoregressive manner.
Our method can generate videos of multiple custom concepts (subjects, action and background) such as a teddy bear running towards a brown teapot, a dog playing violin and a teddy bear swimming in the ocean.
We quantitatively evaluate our method using videoCLIP and DINO scores, in addition to human evaluation.
Videos for results presented in this paper can be found at https://github.com/divyakraman/MultiConceptVideo2024.
;Comment: Paper accepted to AI4CC Workshop at CVPR 2024
Kothandaraman, Divya,Sohn, Kihyuk,Villegas, Ruben,Voigtlaender, Paul,Manocha, Dinesh,Babaeizadeh, Mohammad, 2024, Text Prompting for Multi-Concept Video Customization by Autoregressive Generation
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
methods salience efficiency quantization language slim-llm llms
Prediction Models for Suicide Attempts among Adolescents Using Machine Learning Techniques
using data ml prediction 0 suicide adolescents
