Accès ouvert
2026
article
OpenAlex
Jiayuan Liu, Ning Zhang, Xin Xu, Pan Yue
Human pose estimation under adverse imaging conditions remains challenging for visible-light systems, where rain, snow, haze, and low illumination often cause severe contrast degradation and background interference. Although long-wave infrared (LWIR) imaging is less sensitive to illumination changes and better suited to …
cn
(code pays fourni par la source)
Accès ouvert
2026
article
OpenAlex
Ying Yu, Zheming Yan, Ning Zhang, Kerui Du
us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Han Liu, Shanghao Shi, Yevgeniy Vorobeychik, Chongjie Zhang et autres
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers using low-rank matrices. Since the generation of adversarial examples is …
us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Kehong Gong, Zhengyu Wen, Dao Thien Phong, Mingxi Xu et autres
Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully …
Accès ouvert
2026
article
OpenAlex
Ning Zhang, Shifeng Wang, Suilian You, Jin Meng et autres
Social navigation in dense human crowds requires collision-free and socially compliant behaviors under highly uncertain pedestrian dynamics. However, conflicting optimization objectives prevent existing Deep reinforcement learning (DRL) based methods from achieving stable, efficient, and socially compliant navigation. To address these challenges, we …
cn, sa
(code pays fourni par la source)