Clustering driven deep autoencoder for video anomaly detection

Y Chang, Z Tu, W Xie, J Yuan - Computer Vision–ECCV 2020: 16th …, 2020 - Springer
… and the motion encoder to extract common factors of variation … appearance or motion, [23]
uses two processing streams, … In this paper, we decouple the spatial-temporal information

H-nerf: Neural radiance fields for rendering and temporal reconstruction of humans in motion

H Xu, T Alldieck… - … Information Processing …, 2021 - proceedings.neurips.cc
… exponentially decayed by a factor 0.1 until the … visual surveillance or person identification
as a particular set-up and a cooperating subject is needed. We do not build an audio-visual

Learning to estimate hidden motions with global motion aggregation

S Jiang, D Campbell, Y Lu, H Li… - … on computer vision, 2021 - openaccess.thecvf.com
… At the time of submission, our method ranks first on these … There are many factors that
make optical flow prediction a … first successful in natural language processing (NLP), due to …

From HMI to HMIs: Towards an HMI framework for automated driving

K Bengler, M Rettenmaier, N Fritz, A Feierle - Information, 2020 - mdpi.com
… same time, the use of automated driving in series production … , vehicle movement provides
sufficient information for … , this paper analyzes and summarizes factors that influence HMI type …

Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition

CY Wu, Y Li, K Mangalam, H Fan… - … Computer Vision …, 2022 - openaccess.thecvf.com
… methods, we propose to process videos in an online fashion … We use downsampling factor
of 4×2×2 (for time, height, and … quite challenging due to severe motion blur and occlusions on …

Systematic literature review and bibliometric analysis on virtual reality and education

MA Rojas-Sánchez, PR Palos-Sánchez… - … and Information …, 2023 - Springer
… performance indicators for the production of articles and their … the information about VR in
the educational field over the time … , visual or observational exploration and affective skills for …

Talking-head generation with rhythmic head motion

L Chen, G Cui, C Liu, Z Li, Z Kou, Y Xu, C Xu - … on Computer Vision, 2020 - Springer
… {h}\), where we omit the camera motion and other factors. At each time step t, we compute the
rigid … Then, the encoded audio feature is processed by a multi-layer perception, where the …

Little road driving hud: Heads-up display complexity influences drivers' perceptions of automated vehicles

R Currano, SY Park, DJ Moore, K Lyons… - … on human factors in …, 2021 - dl.acm.org
… And second, different formats of HUDs’ visual warnings can influence reaction times and …
With respect to visual processing in driving, researchers have found that fewer eye movements

Social Internet of Things: vision, challenges, and trends

M Malekshahi Rad, AM Rahmani, A Sahafi… - … and Information …, 2020 - Springer
… , in the web service process, time 23% and scalability 16% are the most mentioned and
finally in information processing, throughput and time 25% are the most investigated factor. Also, …

Human action recognition using attention based LSTM network with dilated CNN features

K Muhammad, A Ullah, AS Imran, M Sajjad… - Future Generation …, 2021 - Elsevier
information, but they are not very effective for temporal data, which is an important factor to
capture motion information for … We process every eighth frame from a video to extract the high-…