Results 301 to 310 of about 3,424,284 (379)

Semantic composition of robotic solver algorithms on graph structures. [PDF]

Front Robot AI
Schneider S, Hochgeschwender N, Bruyninckx H.   +2 more
europepmc   +1 more source

Robust style injection for person image synthesis

CAAI Transactions on Intelligence Technology, Volume 10, Issue 2, Page 402-414, April 2025.
Abstract Person Image Synthesis has been widely used in fashion with extensive application scenarios. The point of this task is how to synthesise person image from a single source image under arbitrary poses. Prior methods generate the person image with target pose well; however, they fail to preserve the fine style details of the source image.
Yan Huang, Jianjun Qian, Shumin Zhu, Jun Li, Jian Yang   +4 more
wiley   +1 more source

Making sense of transformer success. [PDF]

Front Artif Intell
Angius N, Perconti P, Plebe A, Acciai A.
europepmc   +1 more source

BAHGRF3: Human gait recognition in the indoor environment using deep learning features fusion assisted framework and posterior probability moth flame optimisation

CAAI Transactions on Intelligence Technology, Volume 10, Issue 2, Page 387-401, April 2025.
Abstract Biometric characteristics are playing a vital role in security for the last few years. Human gait classification in video sequences is an important biometrics attribute and is used for security purposes. A new framework for human gait classification in video sequences using deep learning (DL) fusion assisted and posterior probability‐based ...
Muhammad Abrar Ahmad Khan, Muhammad Attique Khan, Ateeq Ur Rehman, Ahmed Ibrahim Alzahrani, Nasser Alalwan, Deepak Gupta, Saima Ahmed Rahin, Yudong Zhang   +7 more
wiley   +1 more source

The poetry of senses: exploring semantic mediation in timbre-aroma correspondences. [PDF]

Front Psychol
Zacharakis A.
europepmc   +1 more source

Feature pyramid attention network for audio‐visual scene classification

CAAI Transactions on Intelligence Technology, Volume 10, Issue 2, Page 359-374, April 2025.
Abstract Audio‐visual scene classification (AVSC) poses a formidable challenge owing to the intricate spatial‐temporal relationships exhibited by audio‐visual signals, coupled with the complex spatial patterns of objects and textures found in visual images.
Liguang Zhou, Yuhongze Zhou, Xiaonan Qi, Junjie Hu, Tin Lun Lam, Yangsheng Xu   +5 more
wiley   +1 more source

LViT-Net: a domain generalization person re-identification model combining local semantics and multi-feature cross fusion. [PDF]

Vis Comput Ind Biomed Art
Hu X, Liu P, Wang X, Wu P, Tang R.
europepmc   +1 more source

Point‐PC: Point cloud completion guided by prior knowledge via causal inference

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints. Numerous methods use a partial‐to‐complete framework, directly predicting missing components via global characteristics extracted from incomplete inputs.
Xuesong Gao, Chuanqi Jiao, Ruidong Chen, Weijie Wang, Weizhi Nie   +4 more
wiley   +1 more source

Compositional depths of cognitive semantics: bridging perceptual experiences and conceptual structures. [PDF]

Front Psychol
Pala K, Nedumpozhimana V, Shalu S.
europepmc   +1 more source

RJAN: Region‐based joint attention network for 3D shape recognition

CAAI Transactions on Intelligence Technology, Volume 10, Issue 2, Page 460-473, April 2025.
Abstract As an essential field of multimedia and computer vision, 3D shape recognition has attracted much research attention in recent years. Multiview‐based approaches have demonstrated their superiority in generating effective 3D shape representations.
Yue Zhao, Weizhi Nie, Jie Nie, Yuyi Zhang, Bo Wang   +4 more
wiley   +1 more source