Data movement is all you need: A case study on optimizing transformers
Transformers are one of the most important machine learning workloads today. Training one
is a very compute-intensive task, often taking days or weeks, and significant attention has …
is a very compute-intensive task, often taking days or weeks, and significant attention has …
A novel graph-tcn with a graph structured representation for micro-expression recognition
L Lei, J Li, T Chen, S Li - Proceedings of the 28th ACM International …, 2020 - dl.acm.org
Facial micro-expressions (MEs) recognition has attracted much attention recently. However,
because MEs are spontaneous, subtle and transient, recognizing MEs is a challenge task. In …
because MEs are spontaneous, subtle and transient, recognizing MEs is a challenge task. In …
NUMA-aware shared-memory collective communication for MPI
As the number of cores per node keeps increasing, it becomes increasingly important for
MPI to leverage shared memory for intranode communication. This paper investigates the …
MPI to leverage shared memory for intranode communication. This paper investigates the …
Parallel processing systems for big data: a survey
The volume, variety, and velocity properties of big data and the valuable information it
contains have motivated the investigation of many new parallel data processing systems in …
contains have motivated the investigation of many new parallel data processing systems in …
Eye-model-based gaze estimation by RGB-D camera
L Jianfeng, L Shigang - Proceedings of the IEEE Conference on …, 2014 - cv-foundation.org
This paper proposes a method of eye-model-based gaze estimation by RGB-D camera, Kinect
sensor. Different from other methods, our method sets up a model to calibrate the eyeball …
sensor. Different from other methods, our method sets up a model to calibrate the eyeball …
Deep learning for post-processing ensemble weather forecasts
Quantifying uncertainty in weather forecasts is critical, especially for predicting extreme
weather events. This is typically accomplished with ensemble prediction systems, which consist …
weather events. This is typically accomplished with ensemble prediction systems, which consist …
Micro-expression recognition based on facial graph representation learning and facial action unit fusion
L Lei, T Chen, S Li, J Li - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Micro-expressions recognition is a challenge because it involves subtle variations in facial
organs. In this paper, first, we propose a novel pipeline to learn a facial graph (nodes and …
organs. In this paper, first, we propose a novel pipeline to learn a facial graph (nodes and …
Chimera: efficiently training large-scale neural networks with bidirectional pipelines
Training large deep learning models at scale is very challenging. This paper proposes
Chimera, a novel pipeline parallelism scheme which combines bidirectional pipelines for …
Chimera, a novel pipeline parallelism scheme which combines bidirectional pipelines for …
Binocular spherical stereo
S Li - IEEE Transactions on intelligent transportation systems, 2008 - ieeexplore.ieee.org
A fish-eye camera has a wide field of view (FOV), and the realization of a binocular fish-eye
stereo for sensing the surrounding 3-D information of the environment around a vehicle is …
stereo for sensing the surrounding 3-D information of the environment around a vehicle is …
Description and climate simulation performance of CAS‐ESM version 2
The second version of Chinese Academy of Sciences Earth System Model (CAS‐ESM 2) is
described with emphasis on the development process, strength and weakness, and climate …
described with emphasis on the development process, strength and weakness, and climate …