English
Related papers

Related papers: Spivavtor: An Instruction Tuned Ukrainian Text Edi…

200 papers

Text-driven diffusion models have significantly advanced the image editing performance by using text prompts as inputs. One crucial step in text-driven image editing is to invert the original image into a latent noise code conditioned on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Ruibin Li , Ruihuang Li , Song Guo , Lei Zhang

Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, where minor alterations to the spoken script require preserving motion, temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 John Flynn , Wolfgang Paier , Dimitar Dinev , Sam Nhut Nguyen , Hayk Poghosyan , Manuel Toribio , Sandipan Banerjee , Guy Gafni

Sa2VA is a recent model for language-guided dense grounding in images and video that achieves state-of-the-art results on multiple segmentation benchmarks and that has become widely popular. However, we found that Sa2VA does not perform…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Alexey Nekrasov , Ali Athar , Daan de Geus , Alexander Hermans , Bastian Leibe

Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Hyeonyu Kim , Seokhoon Jeong , Seonghee Han , Chanhyuk Choi , Taehwan Kim

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Jefferson Hernandez , Ruben Villegas , Vicente Ordonez

This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Haozhe Zhao , Xiaojian Ma , Liang Chen , Shuzheng Si , Rujie Wu , Kaikai An , Peiyu Yu , Minjia Zhang , Qing Li , Baobao Chang

Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Weijia Wu , Yuanqiang Cai , Debing Zhang , Sibo Wang , Zhuang Li , Jiahong Li , Yejun Tang , Hong Zhou

Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs. In this paper, we propose a Unified…

Sound · Computer Science 2023-10-03 Muqiao Yang , Chunlei Zhang , Yong Xu , Zhongweiyang Xu , Heming Wang , Bhiksha Raj , Dong Yu

Learning a discriminative model that distinguishes the specified target from surrounding distractors across frames is essential for generic object tracking (GOT). Dynamic adaptation of target representation against distractors remains…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Shih-Fang Chen , Jun-Cheng Chen , I-Hong Jhuo , Yen-Yu Lin

As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Songjun Cao , Qinghua Wu , Jie Chen , Jin Li , Long Ma

Most vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts. This restricts their usability for non-English-speaking users and hinders the development of…

Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instead it emerges through iterative generation, inspection,…

Artificial Intelligence · Computer Science 2026-05-05 Qisong Zhang , Wenzhuo Wu , Zhuangzhuang Jia , Yunhao Yang , Huayu Zhang , Xianghao Zang , Zhixiang He , Zhongjiang He , Kongming Liang , Zhanyu Ma

We introduce GigaEmbeddings, a novel framework for training high-performance Russian-focused text embeddings through hierarchical instruction tuning of the decoder-only LLM designed specifically for Russian language (GigaChat-3B). Our…

Computation and Language · Computer Science 2025-10-28 Egor Kolodin , Daria Khomich , Nikita Savushkin , Anastasia Ianina , Fyodor Minkin

Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Chao Zhou , Tianyi Wei , Nenghai Yu

Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Jiaxing Huang , Jingyi Zhang , Kai Jiang , Han Qiu , Shijian Lu

We introduce Instruction Document Visual Question Answering (iDocVQA) dataset and Large Language Document (LLaDoc) model, for training Language-Vision (LV) models for document analysis and predictions on document images, respectively.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Tosin Adewumi , Nudrat Habib , Lama Alkhaled , Elisa Barney

Automatic speech editing aims to modify spoken content based on textual instructions, yet traditional cascade systems suffer from complex preprocessing pipelines and a reliance on explicit external temporal alignment. Addressing these…

Sound · Computer Science 2026-01-12 Junyang Chen , Yuhang Jia , Hui Wang , Jiaming Zhou , Yaxin Han , Mengying Feng , Yong Qin

Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yuan Liu , Le Tian , Xiao Zhou , Jie Zhou

Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained individually and do not utilize the limited (source, target)…

Computation and Language · Computer Science 2023-05-04 Hao Cheng , Meng Zhang , Liangyou Li , Qun Liu , Zhihua Zhang

The recent introduction of prompt tuning based on pre-trained vision-language models has dramatically improved the performance of multi-label image classification. However, some existing strategies that have been explored still have…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Xiangyu Wu , Qing-Yuan Jiang , Yang Yang , Yi-Feng Wu , Qing-Guo Chen , Jianfeng Lu
‹ Prev 1 8 9 10 Next ›