paper-with-me

홈 › Papers

AICL: Action In-Context Learning for Video Diffusion Model

2024-03-18 · Jianzhi Liu, Junchen Zhu, Lianli Gao, Heng Tao Shen, Jingkuan Song

The open-domain video generation models are constrained by the scale of the training video datasets, and some less common actions still cannot be generated. Some researchers explore video editing methods and achieve action generation by editing the spatial information of the same action video. However, this method mechanically generates identical actions without understanding, which does not align with the characteristics of open-domain scenarios. In this paper, we propose AICL, which empowers the generative model with the ability to understand action information in reference videos, similar to how humans do, through in-context learning. Extensive experiments demonstrate that AICL effectively captures the action and achieves state-of-the-art generation performance across three typical video diffusion models on five metrics when using randomly selected categories from non-training datasets.

📄 PDF Abstract BibTeX arXiv:2403.11535

Code (1)

liujianzhi/echoreel 공식 구현 pytorch

Tasks

Action GenerationIn-Context LearningVideo EditingVideo Generation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SAICL: Student Modelling with Interaction-level Auxiliary Contrastive Tasks for Knowledge Tracing and Dropout Prediction

2022-10-07 · Jungbae Park, Jinyoung Kim, Soonwoo Kwon, Sang Wan Lee

Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsit…

Contrastive LearningData AugmentationKnowledge Tracing

MetaICL: Learning to Learn In Context

2021-10-29 · NAACL 2022 7 · Sewon Min, Mike Lewis, Luke Zettlemoyer, Hannaneh Hajishirzi

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. Thi…

Few-Shot LearningIn-Context LearningLanguage ModellingMulti-Task Learning+2

Scaling In-Context Demonstrations with Structured Attention

2023-07-05 · Tianle Cai, Kaixuan Huang, Jason D. Lee, Mengdi Wang

The recent surge of large language models (LLMs) highlights their ability to perform in-context learning, i.e., "learning" to perform a task from a few demonstrations in the context without any parameter updates. However…

DecoderIn-Context LearningSentence

ParaICL: Towards Parallel In-Context Learning

2024-03-31 · Xingxuan Li, Xuan-Phi Nguyen, Shafiq Joty, Lidong Bing

Large language models (LLMs) have become the norm in natural language processing (NLP), excelling in few-shot in-context learning (ICL) with their remarkable abilities. Nonetheless, the success of ICL largely hinges on t…

In-Context LearningSemantic SimilaritySemantic Textual Similarity

MetaICL: Learning to Learn In Context

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. Thi…

Few-Shot LearningIn-Context LearningLanguage ModelingLanguage Modelling+3