2 citations · 3 across the 8 of their papers we have counts for
9 papers
UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance
Gaoxiang Cong, Liang Li, Jianwei Wen +3
Visual voice cloning requires intelligible, speaker-consistent speech synchronized with visible articulation. However, sequential multimodal conditioning can disrupt previously est…
LogiShot: Logically Coherent Cross-Shot Video Generation
Shuai Guo, Yuhang Yang, Zeyu Zhang +4
Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such as short-drama production,…
SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
Jiadong Pan, Liang Li, Hongcheng Gao +3
Diffusion models (DMs) have demonstrated exceptional performance in text-to-image tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), t…
Context-aware Difference Distilling for Multi-change Captioning
Yunbin Tu, Liang Li, Li Su +3
Multi-change captioning aims to describe complex and coupled changes within an image pair in natural language. Compared with single-change captioning, this task requires the model…
Event-based Asynchronous HDR Imaging by Temporal Incident Light Modulation
Yuliang Wu, Ganchao Tan, Jinze Chen +3
Dynamic Range (DR) is a pivotal characteristic of imaging systems. Current frame-based cameras struggle to achieve high dynamic range imaging due to the conflict between globally u…
LEMON: Learning 3D Human-Object Interaction Relation from 2D Images
Yuhang Yang, Wei Zhai, Hongchen Luo +2
Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interactio…
Self-supervised Cross-view Representation Reconstruction for Change Captioning
Yunbin Tu, Liang Li, Li Su +3
Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused…
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Wei Zhai, Pingyu Wu, Kai Zhu +3
Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. Recently, a new paradigm has emerged by generating a foregrou…
BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View
Yuxiang Yang, Yingqi Deng, Mian Pan +2
3D Single Object Tracking (SOT) is a fundamental task in computer vision and plays a critical role in applications like autonomous driving. However, existing algorithms often invol…