5 papers
Fast Wrong-way Cycling Detection in CCTV Videos: Sparse Sampling is All You Need
Jing Xu, Wentao Shi, Sheng Ren +4
Effective monitoring of unusual transportation behaviors, such as wrong-way cycling (i.e., riding a bicycle or e-bike against designated traffic flow), is crucial for optimizing la…
Probing the Representational Geometry of Color Qualia: Dissociating Pure Perception from Task Demands in Brains and AI Models
Jing Xu
Probing the computational underpinnings of subjective experience, or qualia, remains a central challenge in cognitive neuroscience. This project tackles this question by performing…
Robot Learning with Sparsity and Scarcity
Jingxi Xu
Unlike in language or vision, one of the fundamental challenges in robot learning is the lack of access to vast data resources. We can further break down the problem into (1) data…
Video Individual Counting With Implicit One-to-Many Matching
Xuhui Zhu, Jing Xu, Bingjie Wang +2
Video Individual Counting (VIC) is a recently introduced task that aims to estimate pedestrian flux from a video. It extends conventional Video Crowd Counting (VCC) beyond the per-…
Variational Source-Channel Coding for Semantic Communication
Yulong Feng, Jing Xu, Liujun Hu +2
Semantic communication technology emerges as a pivotal bridge connecting AI with classical communication. The current semantic communication systems are generally modeled as an Aut…