paper-with-me

홈 › Papers

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

2025-10-08 · Jiaben Chen, Zixin Wang, Ailing Zeng, Yang Fu, Xueyang Yu, Siyuan Cen, Julian Tanke, Yihang Chen, Koichi Saito, Yuki Mitsufuji, Chuang Gan arxiv

In this work, we present TalkCuts, a large-scale dataset designed to facilitate the study of multi-shot human speech video generation. Unlike existing datasets that focus on single-shot, static viewpoints, TalkCuts offers 164k clips totaling over 500 hours of high-quality human speech videos with diverse camera shots, including close-up, half-body, and full-body views. The dataset includes detailed textual descriptions, 2D keypoints and 3D SMPL-X motion annotations, covering over 10k identities, enabling multimodal learning and evaluation. As a first attempt to showcase the value of the dataset, we present Orator, an LLM-guided multi-modal generation framework as a simple baseline, where the language model functions as a multi-faceted director, orchestrating detailed specifications for camera transitions, speaker gesticulations, and vocal modulation. This architecture enables the synthesis of coherent long-form videos through our integrated multi-modal video generation module. Extensive experiments in both pose-guided and audio-driven settings show that training on TalkCuts significantly enhances the cinematographic coherence and visual appeal of generated multi-shot speech videos. We believe TalkCuts provides a strong foundation for future work in controllable, multi-shot speech video generation and broader multimodal learning.

📄 PDF Abstract BibTeX arXiv:2510.07249

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

2023-07-14 · Siyuan Yang, Jun Liu, Shijian Lu, Er Meng Hwa 외

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale…

Action Recognition

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

2022-08-02 · Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta 외

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than …

Causal Language ModelingCommon Sense ReasoningCoreference ResolutionDecoder+8

Personalizing Pre-trained Models

2021-06-02 · Mina Khan, P Srivatsa, Advait Rane, Shriram Chenniappa 외

Self-supervised or weakly supervised models trained on large-scale datasets have shown sample-efficient transfer to diverse datasets in few-shot settings. We consider how upstream pretrained models can be leveraged for d…

Continual LearningFew-Shot LearningPrivacy PreservingRepresentation Learning

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

2022-11-13 · TaeHoon Kim, Mark Marsden, Pyunghwan Ahn, Sangyun Kim 외

When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To improve performance, pretraining-and-fin…

Image CaptioningKeyword Extraction

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation

2022-08-18 · COLING 2022 10 · Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such…

Data AugmentationDialogue GenerationText Generation