Shuman Li — accepted AI-conference papers

2025

Anchor-Prompt-based Segmentation and Embedding Model

Shuman Li, Zhipeng Lin, Haotian Wang, Wenjing Yang, Hengzhu Liu

ICASSP 2025accepted

Tackling multi-object tracking and segmentation (MOTS) can be attributed to a multi-task learning task, i.e., performing Segmentation and Identity Embedding jointly (SIEJ). Unfortunately, achieving optimal SIEJ is non-trivial, as it relies on different spatiotemporal features of objects. Besides, th…

Cited by 0 Source ↗Scholar ↗

2024

Modality Re-Balance for Visual Question Answering: A Causal Framework

Xinpeng Lv, Wanrong Huang, Haotian Wang, Ruochun Jin, Xueqiong Li, Zhipeng Lin +3

ICASSP 2024accepted

Visual Question Answering (VQA) models often prioritize language cues over visual knowledge, leading to the "language prior" phenomenon. To address this, researchers have proposed methods to balance language and image information during training and inference. However, these approaches often struggl…

Cited by 0 Source ↗Scholar ↗