中文
相关论文

相关论文: S2ED: From Story to Executable Descriptions for Co…

200 篇论文

Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely…

The current state-of-the-art video generative models can produce commercial-grade videos with highly realistic details. However, they still struggle to coherently present multiple sequential events in the stories specified by the prompts,…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Yiping Wang , Xuehai He , Kuan Wang , Luyao Ma , Jianwei Yang , Shuohang Wang , Simon Shaolei Du , Yelong Shen

Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Zhaoyuan Qiu , Ken Chen , Xiangwei Wang , Yu Xia , Sachith Seneviratne , Saman Halgamuge

Recent advances in scene-based video generation enable coherent visual narratives from structured prompts, yet a key aspect of storytelling -- character-driven dialogue and speech -- remains underexplored. We present a modular pipeline that…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Taewon Kang , Ming C. Lin

Visual storytelling requires generating multi-shot videos with cinematic quality and long-range consistency. Inspired by human memory, we propose StoryMem, a paradigm that reformulates long-form video storytelling as iterative shot…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Kaiwen Zhang , Liming Jiang , Angtian Wang , Jacob Zhiyuan Fang , Tiancheng Zhi , Qing Yan , Hao Kang , Xin Lu , Xingang Pan

Inspired by the software industry's practice of offering different editions or versions of a product tailored to specific user groups or use cases, we propose a novel task, namely, training-free editioning, for text-to-image models.…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Jinqi Wang , Yunfei Fu , Zhangcan Ding , Bailin Deng , Yu-Kun Lai , Yipeng Qin

Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and finite real datasets. Previous works evaluate the utility of synthetic data from T2I models on three…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Zhang Xiaofeng , Aaron Courville , Michal Drozdzal , Adriana Romero-Soriano

End-to-End Autonomous Driving (E2EAD) methods typically rely on supervised perception tasks to extract explicit scene information (e.g., objects, maps). This reliance necessitates expensive annotations and constrains deployment and data…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Peidong Li , Dixiao Cui

Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Qingyang Liu , Bingjie Gao , Canmiao Fu , Zhipeng Huang , Chen Li , Feng Wang , Shuochen Chang , Shaobo Wang , Yali Wang , Keming Ye , Jiangtong Li , Li Niu

Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Zilai Zeng , Mingdeng Cao , Zijie Li , Xiaochen Lian , Yichun Shi , Peihao Zhu , Chen Sun , Peng Wang

Narratives are a predominant part of games, and their design poses challenges when identifying, encoding, interpreting, evaluating, and generating them. One way to address this would be to approach narrative design in a more abstract layer,…

人机交互 · 计算机科学 2022-10-18 Alberto Alvarez , Jose Font , Julian Togelius

Training-free consistent text-to-image generation depicting the same subjects across different images is a topic of widespread recent interest. Existing works in this direction predominantly rely on cross-frame self-attention; which…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Jaskirat Singh , Junshen Kevin Chen , Jonas Kohler , Michael Cohen

Audio Descriptions (ADs) convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners to visualise the unfolding scene, rather than…

计算机视觉与模式识别 · 计算机科学 2025-10-30 Eshika Khandelwal , Junyu Xie , Tengda Han , Max Bain , Arsha Nagrani , Andrew Zisserman , Gül Varol , Makarand Tapaswi

Personalized feedback plays an important role in self-regulated learning (SRL), helping students track progress and refine their strategies. However, current common solutions, such as text-based reports or learning analytics dashboards,…

人机交互 · 计算机科学 2026-02-20 Leixian Shen , Yan Luo , Rui Sheng , Yujia He , Haotian Li , Leni Yang , Huamin Qu

Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy, and truthfulness. Although human evaluation provides…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Jia-Hong Huang , Hongyi Zhu , Yixian Shen , Stevan Rudinac , Evangelos Kanoulas

We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students…

Visual Storytelling is a challenging multimodal task between Vision & Language, where the purpose is to generate a story for a stream of images. Its difficulty lies on the fact that the story should be both grounded to the image sequence…

计算与语言 · 计算机科学 2025-08-21 Admitos Passadakis , Yingjin Song , Albert Gatt

Text-to-image generation tasks have driven remarkable advances in diverse media applications, yet most focus on single-turn scenarios and struggle with iterative, multi-turn creative tasks. Recent dialogue-based systems attempt to bridge…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Shichao Ma , Yunhe Guo , Jiahao Su , Qihe Huang , Zhengyang Zhou , Yang Wang

We propose a novel robust and efficient Speech-to-Animation (S2A) approach for synchronized facial animation generation in human-computer interaction. Compared with conventional approaches, the proposed approach utilizes phonetic…

多媒体 · 计算机科学 2022-04-07 Liyang Chen , Zhiyong Wu , Jun Ling , Runnan Li , Xu Tan , Sheng Zhao

While recent text-to-image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, their performance significantly degrades when confronted with long, detail-intensive prompts required in professional…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Qirui Jiao , Daoyuan Chen , Yilun Huang , Xika Lin , Ying Shen , Yaliang Li