6 papers
Resonant Minds: Closed-Loop Social Avatars with Theory of Mind
Jianxu Shangguan, Jing Xu, Hang Ye +4
Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent framework. Current approaches tr…
BCL: Bayesian In-Context Learning Framework for Information Extraction
Haoliang Liu, Chengkun Cai, Xu Zhao +7
Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance…
Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction
Jen-Hao Cheng, Yipeng Wang, Hao Zhang +2
We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos usi…
Understanding Identity Continuity in Thermal Video through Scene-Level Consistency
Wei-Chieh Sun, Gyungmin Ko, Heejae Kwon +2
Thermal pedestrian MOT remains challenging because weak appearance cues and frequent detection interruptions cause severe trajectory fragmentation. We study whether lightweight pos…
From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
Aotian Zheng, Winston Sun, Bahaa Alattar +2
CLIP-based person re-identification (ReID) methods aggregate spatial features into a single global \texttt{[CLS]} token optimized for image-text alignment rather than spatial selec…
milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion
Niraj Prakash Kini, Shiau-Rung Tsai, Guan-Hsun Lin +3
Millimeter-wave radar offers a privacy-preserving and lighting-invariant alternative to RGB sensors for Human Pose Estimation (HPE) task. However, the radar signals are often spars…