MMSP-P2: Temporal Modeling and Video Synthesis
Poster
Tue, 5 May, 14:00 - 16:00
Location: Poster Area 21
Session Type: Poster
Track: Multimedia Signal Processing [MM]
Click the to view the manuscript on IEEE Xplore Open Preview

MMSP-P2.1: SAVGBENCH: BENCHMARKING SPATIALLY ALIGNED AUDIO-VIDEO GENERATION

Kazuki Shimada, Sony AI, Japan; Christian Simon, Sony Group Corporation, Japan; Takashi Shibuya, Sony AI, Japan; Shusuke Takahashi, Sony Group Corporation, Japan; Yuki Mitsufuji, Sony AI, Japan

MMSP-P2.2: TRAINING-FREE MULTIMODAL GUIDANCE FOR VIDEO TO AUDIO GENERATION

Eleonora Grassucci, Sapienza University of Rome, Italy; Giuliano Galadini, Politecnico di Milano, Italy; Giordano Cicchetti, Aurelio Uncini, Sapienza University of Rome, Italy; Fabio Antonacci, Politecnico di Milano, Italy; Danilo Comminiello, Sapienza University of Rome, Italy

MMSP-P2.3: PaintFlow: Stage-Aware Temporal Modeling for Text-to-Video Synthesis of Painting Processes

Yixuan Zhang, Fengzhou Liang, Yuta Sugiura, Keio University, Japan

MMSP-P2.4: 3D MOTION SYNTHESIS FROM SPARSE TRACKING WITH AUTOREGRESSIVE TEMPORAL WINDOWS

Georgios Angelis, CERTH, Greece; Savas Ozkan, Sinan Mutlu, Samsung R&D Institute, United Kingdom of Great Britain and Northern Ireland; Anastasios Drosou, CERTH, Greece; Mete Ozay, Samsung R&D Institute, United Kingdom of Great Britain and Northern Ireland

MMSP-P2.5: KD-CVG: A KNOWLEDGE-DRIVEN APPROACH FOR CREATIVE VIDEO GENERATION

Linkai Liu, Sun Yat-sen University, China; Wei Feng, Xi Zhao, Shen Zhang, JD.com, China; Xingye Chen, Huazhong University of Science and Technology, China; Zheng Zhang, Jingjing Lv, Junjie Shen, Ching Law, JD.com, China; Yuchen Zhou, Zipeng Guo, Chao Gou, Sun Yat-sen University, China

MMSP-P2.6: TOWARDS MULTI-VIEW HIERARCHICAL VIDEO-TO-PIANO GENERATION WITH MIDI GUIDANCE

Chang Liu, University of Trento, Italy; Zihao Chen, Gongyu Chen, Chaofan Ding, Giant Network, China; Nicu Sebe, University of Trento, Italy

MMSP-P2.7: LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation

Junchen Fu, University of Glasgow, United Kingdom of Great Britain and Northern Ireland; Xuri Ge, Shandong University, China; Kaiwen Zheng, University of Glasgow, United Kingdom of Great Britain and Northern Ireland; Alexandros Karatzoglou, Amazon, Spain; Ioannis Arapakis, Telefónica Scientific Research, Spain; Xin Xin, Shandong University, China; Yongxin Ni, National University of Singapore, Singapore; Joemon Jose, University of Glasgow, United Kingdom of Great Britain and Northern Ireland

MMSP-P2.8: Towards Dynamic World Model Generation with Monocular Video

Keyuan Li, Shixiong Zhang, Yixuan Fang, Shuangjie Yuan, Yizhi Zou, Lu Yang, University of Electronic Science and Technology of China, China

MMSP-P2.9: TPEformer: Temporal Patch Embedding Transformer

Ziqing Yang, Houwei Cao, New York Institute of Technology, United States of America

MMSP-P2.10: WHY TEMPORAL MODELING MODULES FALL SHORT IN TEMPORALLY SENSITIVE VIDEO-TEXT RETRIEVAL TASKS

Chen He, Bowen Yang, Yuqi Pang, Yun Cao, University of Chinese Academy of Sciences, China