Results 221 to 230 of about 103,607 (290)

Enhancing Long-Term Action Quality Assessment: A Dual-Modality Dataset and Causal Cross-Modal Framework for Trampoline Gymnastics. [PDF]

Sensors (Basel)
Lin F, Huang J, Chen Z, Zhu K, Feng C.
europepmc   +1 more source

M3OT: A Multi-Drone Multi-Modality dataset for Multi-Object Tracking. [PDF]

Sci Data
Nie Z, Xue L, Fang Z, Ren J, Wei Y, Zheng J.   +5 more
europepmc   +1 more source

STFormer: Spatio‐temporal former for hand–object interaction recognition from egocentric RGB video [PDF]

Jiao Liang, Xihan Wang, Jiayi Yang, Quanli Gao   +3 more
openalex   +1 more source

ADAT novel time-series-aware adaptive transformer architecture for sign language translation. [PDF]

Sci Rep
Shahin N, Ismail L.
europepmc   +1 more source

A Unified GAN-Based Framework for Unsupervised Video Anomaly Detection Using Optical Flow and RGB Cues. [PDF]

Sensors (Basel)
Kang SH, Kang HS.
europepmc   +1 more source

A deep learning-based method combines manual and non-manual features for sign language recognition. [PDF]

Sci Rep
Harrouch H, Trabelsi L, Jebali M, Gammoudi O.   +3 more
europepmc   +1 more source

SAT: shift alignment transformer for video denoising without flow estimation. [PDF]

Sci Rep
Zhang X, Fan S, Zhang H, Gao Y, Hu Y.
europepmc   +1 more source

3D facial performance capture from monocular RGB video.

3D facial performance capture is an essential technique for animation production in featured films, video gaming, human computer interaction, VR/AR asset creation and digital heritage, which all have huge impact on our daily life. Traditionally, dedicated hardware such as depth sensors, laser scanners and camera arrays have been developed to acquire ...
openaire  

Forest Inspection Dataset: A Synthetic UAV Dataset for Semantic Segmentation of Forest Environments. [PDF]

Sci Data
Blaga BC, Nedevschi S.
europepmc   +1 more source