This panel brings together academics and practitioners to discuss the structural problems facing visual effects within the film and television industry today. This discussion is organized around four sub-Topics: 1) la...
详细信息
ISBN:
(纸本)9781450379694
This panel brings together academics and practitioners to discuss the structural problems facing visual effects within the film and television industry today. This discussion is organized around four sub-Topics: 1) labor solutions and what unionization would mean, 2) perceptions of VFX artists and their contributions within the industry by filmmakers and artists themselves, as well as the audience, 3) issues of inclusivity along gender and racial lines, and their effects on work/life balances, and 4) VFX as equal creative partners rather than isolated, temporary, highly-skilled specialists. This panel is a continuation of work begun by the faculty and practitioner organizers, Heath Hanlin (Syracuse University, VPA) and Shaina Holmes (Syracuse University, Newhouse) on studying structural challenges and obstacles to entry for students hoping to enter the VFX industry, in particular women, and artists of color. An earlier iteration of this discussion was held at the 2020 Sundance Film Festival. The hope is that the technical focus and high attendance by industry practitioners at Siggraph, adds practitioner perspectives and educator feedback to the sub-Topics listed above. Simply put, today's film and television industry rely heavily on visual effects, both to advance the story or as a means to hide imperfections to keep the audience engaged without technical distractions. Traditional conceptions of VFX artistry as a production step that comes after primary cinematography is simply outdated. Unfortunately, the economic and work-flow structure of the industry accepts this new reality while at the same time attempting to compensate, credit, and organize VFX artists within the outdated framework. Often this aspect of the conversation is moored in debates surrounding the potentiality of AI to either positively impact the industry (no more underpaid routinized tasks for artists) or negatively (crafts persons and artists can be replaced by algorithms). Rather, a more fruitful
Nowadays, data science projects are usually developed in an unstructured way, which makes it difficult to reproduce. It is also hard to move from an experimental environment to production. Operational workflows such a...
Nowadays, data science projects are usually developed in an unstructured way, which makes it difficult to reproduce. It is also hard to move from an experimental environment to production. Operational workflows such as containerization, continuous deployment, and cloud orchestration allow data science researchers to move a pipeline from a local environment to the cloud. Being aware of the difficulties of setting those workflows up, this paper presents a framework to ease experiment tracking and operationalizing machine learning by combining existent and well-supported technologies. These technologies include Docker, Mlflow, Ray, among others. The framework provides an opinionated workflow to design and execute experiments either on a local environment or the cloud. ml-experiment includes: an automatic tracking system for the most famous machine learning libraries: Tensorflow, Keras, Fastai, Xgboost and Lightgdm, first-class support for distributed training and hyperparameter optimization, and a Command Line Interface (CLI) for packaging and running projects inside containers.
With the fast evolvement of embedded deep-learning computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying neural networks (NNs) onto the devices under complex en...
详细信息
Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models ...
详细信息
In current convolutional neural network (CNN) accelerators, communication (i.e., memory access) dominates the energy consumption. This work provides comprehensive analysis and methodologies to minimize the communicati...
详细信息
ISBN:
(数字)9781728161495
ISBN:
(纸本)9781728161501
In current convolutional neural network (CNN) accelerators, communication (i.e., memory access) dominates the energy consumption. This work provides comprehensive analysis and methodologies to minimize the communication for CNN accelerators. For the off-chip communication, we derive the theoretical lower bound for any convolutional layer and propose a dataflow to reach the lower bound. This fundamental problem has never been solved by prior studies. The on-chip communication is minimized based on an elaborate workload and storage mapping scheme. We in addition design a communication-optimal CNN accelerator architecture. Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a three-level memory hierarchy and it is computation dominant. The gap between the energy efficiency of our accelerator and the theoretical best value is only 37-87%.
The eXtended isogeometric analysis (X-IGA) combined with Particle swarm optimization (PSO) is used for crack identification in twodimensional linear elastic problems based on inverse problem. The application of fractu...
详细信息
This paper develops a model to plan energy-efficient speed trajectories of electric trucks in real time by taking into account the information of topography and traffic ahead of the vehicle. In this real time control ...
详细信息
暂无评论