paper-with-me

홈 › Papers

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation

2026-04-21 · Hongyu Zhang, Yufan Deng, Zilin Pan, Peng-Tao Jiang, Bo Li, Qibin Hou, Zhiyang Dou, Zhen Dong, Daquan Zhou arxiv

Generating high-quality videos from complex temporal descriptions that contain multiple sequential actions is a key unsolved problem. Existing methods are constrained by an inherent trade-off: using multiple short prompts fed sequentially into the model improves action fidelity but compromises temporal consistency, while a single complex prompt preserves consistency at the cost of prompt-following capability. We attribute this problem to two primary causes: 1) temporal misalignment between video content and the prompt, and 2) conflicting attention coupling between motion-related visual objects and their associated text conditions. To address these challenges, we propose a novel, training-free attention mechanism, Temporal-wise Separable Attention (TS-Attn), which dynamically rearranges attention distribution to ensure temporal awareness and global coherence in multi-event scenarios. TS-Attn can be seamlessly integrated into various pre-trained text-to-video models, boosting StoryEval-Bench scores by 33.5% and 16.4% on Wan2.1-T2V-14B and Wan2.2-T2V-A14B with only a 2% increase in inference time. It also supports plug-and-play usage across models for multi-event image-to-video generation. The source code and project page are available at https://github.com/Hong-yu-Zhang/TS-Attn.

📄 PDF Abstract BibTeX arXiv:2604.19473

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition

2022-10-14 · WACV 2023 1 · Dasom Ahn, Sangwon Kim, Hyunsu Hong, Byoung Chul Ko

In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are requ…

Action RecognitionDecoderTemporal Action Localization

Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

2024-10-09 · Siyuan Huang, Yunchong Song, Jiayue Zhou, Zhouhan Lin

In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these m…

Graph LearningNode Clustering

An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG

2021-04-28 · Emadeldeen Eldele, Zhenghua Chen, Chengyu Liu, Min Wu 외

Automatic sleep stage mymargin classification is of great importance to measure sleep quality. In this paper, we propose a novel attention-based deep learning architecture called AttnSleep to classify sleep stages using …

Automatic Sleep Stage ClassificationEEGElectroencephalogram (EEG)Sleep Quality+1

GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs

2026-07-16 · Xiangni Tian, Kaixian Yu, Runpeng Dai, Niansheng Tang 외 arxiv

Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on diff…

Knowledge Graphs

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

2025-03-28 · Hanling Zhang, Rundong Su, Zhihang Yuan, Pengtao Chen 외

Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often face significant computational bottlene…

2kImage GenerationText to Image GenerationText-to-Image Generation