Détail du document
Identifiant
oai:arXiv.org:2403.12042
Sujet
Computer Science - Computer Vision...Auteur
Zhu, Zixin Feng, Xuelu Chen, Dongdong Yuan, Junsong Qiao, Chunming Hua, GangCatégorie
Computer Science
Année
2024
Date de référencement
10/07/2024
Mots clés
model diffusion noise videoRésumé
In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks.
We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding.
Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task.
We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed pretrained T2V model.
Specifically, VD-IT uses textual information as a conditional input, ensuring semantic consistency across time for precise temporal instance matching.
It further incorporates image tokens as supplementary textual inputs, enriching the feature set to generate detailed and nuanced masks.
Besides, instead of using the standard Gaussian noise, we propose to predict the video-specific noise with an extra noise prediction module, which can help preserve the feature fidelity and elevates segmentation quality.
Through extensive experiments, we surprisingly observe that fixed generative T2V diffusion models, unlike commonly used video backbones (e.g., Video Swin Transformer) pretrained with discriminative image/video pre-tasks, exhibit better potential to maintain semantic alignment and temporal consistency.
On existing standard benchmarks, our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
The code is available at https://github.com/buxiangzhiren/VD-IT.
;Comment: Appear at ECCV 2024, and the code is available at https://github.com/buxiangzhiren/VD-IT
Zhu, Zixin,Feng, Xuelu,Chen, Dongdong,Yuan, Junsong,Qiao, Chunming,Hua, Gang, 2024, Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
Configurable Safety Tuning of Language Models with Synthetic Preference Data
data preference cst dpo configurable language safety
Affective flexibility as a developmental building block of cognitive reappraisal: An fMRI study
cognitive success affective flexibility
