8 papers
Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation
Chao Li, Tianhong Li, Sai Vidyaranya Nuthalapati +9
Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives demand opposing masking regimes:…
CoMo: Compositional Motion Customization for Text-to-Video Generation
Youcan Xu, Zhen Wang, Jiaxin Shi +6
While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods f…
TarPro: Targeted Protection against Malicious Image Editing
Kaixin Shen, Ruijie Quan, Jiaxu Miao +2
The rapid advancement of image editing techniques has raised concerns about their misuse for generating Not-Safe-for-Work (NSFW) content. This necessitates a targeted protection me…
Collaborative Hybrid Propagator for Temporal Misalignment in Audio-Visual Segmentation
Kexin Li, Zongxin Yang, Yi Yang +1
Audio-visual video segmentation (AVVS) aims to generate pixel-level maps of sound-producing objects that accurately align with the corresponding audio. However, existing methods of…
AudioScenic: Audio-Driven Video Scene Editing
Kaixin Shen, Ruijie Quan, Linchao Zhu +2
Audio-driven visual scene editing endeavors to manipulate the visual background while leaving the foreground content unchanged, according to the given audio signals. Unlike current…
Neural Interaction Energy for Multi-Agent Trajectory Prediction
Kaixin Shen, Ruijie Quan, Linchao Zhu +2
Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this stability often results in fluctuations in kinematic stat…
IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagation
Kexin Li, Tao Jiang, Zongxin Yang +3
Interactive Video Object Segmentation (iVOS) is a challenging task that requires real-time human-computer interaction. To improve the user experience, it is important to consider t…
CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation
Kexin Li, Zongxin Yang, Lei Chen +2
Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, su…