Mingda Jia

Explicit Temporal-Semantic Modeling for Dense Video Captioning via Context-Aware Cross-Modal Interaction

Mingda Jia, Weiliang Meng, Zheng Qing Fu, Yiheng Li et autres

Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi-task architectures to achieve competitive performance. However, these pipelines rely on implicit modeling that uses frame-level or fragmented video …

AccidentX: A Large-Scale Multimodal BEV Dataset for Traffic Accident Analysis and Prevention

Muyang Zhang, Zhe Feng, Jinming Yang, Mingda Jia et autres

With the rapid development and widespread application of autonomous driving technology, the accurate analysis and prevention of traffic accidents have become critical challenges. However, current traffic accident datasets are often constrained by limited scale and diversity, impeding progress in this field. To …

cn (code pays fourni par la source)

Campus landscape perception decoded by surveys combined with eye tracking: Visual and cultural perception for user well-being

Mingda Jia, Yong Zhang

cn (code pays fourni par la source)

Campus Landscape Perception Decoded by Eye-Tracking: Visual and Cultural Perception for Well-Being

Mingda Jia, Yong Zhang

Seeing the Invisible: Recovering Surveillance Video With COTS mmWave Radar

Mingda Han, Huanqi Yang, Mingda Jia, Weitao Xu et autres

Video surveillance systems play a crucial role in ensuring public safety and security by capturing and monitoring critical events in various areas. However, traditional surveillance cameras face limitations when it comes to malicious physical damage or obscuring by offenders. To overcome this …

cn, hk, sg (code pays fourni par la source)

XGait: Cross-Modal Translation via Deep Generative Sensing for RF-based Gait Recognition

Huanqi Yang, Mingda Han, Mingda Jia, Zehua Sun et autres

Radio Frequency (RF)-based gait recognition has emerged as a promising technology to authenticate individuals in a pervasive and unobtrusive way. However, a fundamental challenge remains in collecting extensive data of the same user in the same environment. To address this challenge, this …

hk, cn, au (code pays fourni par la source)

Targeting HDAC3, a new partner protein of AKT in the reversal of chemoresistance in acute myeloid leukemia via DNA damage response

Jun Long, Weiyue Fang, Chang Li, W H Gao et autres

cn (code pays fourni par la source)