Monday, July 17, 2017
Saturday, July 15, 2017
Mirzakhani, Maryam
Maryam Mirzakhani was first women to win Fields Medal in math also professor at Stanford university.
Monday, July 10, 2017
Deep Learning at Pennsylvania State University
Integrating Deep-learned Models and Photography Idea Retrieval
Intelligent Portrait Composition Assistance (IPCA) – Integrating Deep-learned Models and Photography Idea Retrieval, Farshid Farhat, Mohammad Kamani, Sahil Mishra, James Wang, ACM Multimedia 2017, Mountain View, CA, USA.
ABSTRACT: Retrieving photography ideas corresponding to a given location facilitates the usage of smart cameras, where there is a high interest among amateurs and enthusiasts to take astonishing photos at anytime and in any location. Existing research captures some aesthetic techniques such as the rule of thirds, triangle, and perspectiveness, and retrieves useful feedbacks based on one technique. However, they are restricted to a particular technique and the retrieved results have room to improve as they can be limited to the quality of the query. There is a lack of a holistic framework to capture important aspects of a given scene and give a novice photographer informative feedback to take a better shot in his/her photography adventure. This work proposes an intelligent framework of portrait composition using our deep-learned models and image retrieval methods. A highly-rated web-crawled portrait dataset is exploited for retrieval purposes. Our framework detects and extracts ingredients of a given scene representing as a correlated hierarchical model. It then matches extracted semantics with the dataset of aesthetically composed photos to investigate a ranked list of photography ideas, and gradually optimizes the human pose and other artistic aspects of the composed scene supposed to be captured. The conducted user study demonstrates that our approach is more helpful than the other constructed feedback retrieval systems.
Art, Computer Vision, Conference Paper, Deep Learning, Image Processing, Machine Learning, Pattern Recognition, Photography, Research, Thesis and tagged ACM Multimedia, ACMM, Aesthetics, AI, Art Theory, Artificial Intelligence, CBIR, Computer Vision, Content-based Image Retrieval, DEEP LEARNING, Deep-Learned Model Transfer, Human Pose, Human Pose Estimation, Image Aesthetics, Image Processing, Image Retrieval, Intelligent Portrait Composition Assistance, IPCA, Machine Learning, Object Detection, Pattern Recognition, Penn State Deep Learning, Photography, Photography Idea, Portrait, Portrait Composition, Portrait Dataset, Portrait Photography, Pose Estimation, Pose Recommendation, Scene Parsing
Wednesday, June 28, 2017
Stochastically Optimizing Data Computing Flows
Academic Endeavors at Pennsylvania State University
- Leveraging big visual data to predict severe weather conditions
- Discovering Triangles in Portraits for Supporting Photographic Creation
- Skeleton Matching with Applications in Severe Weather Detection
- Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval
- Shape matching using skeleton context for automated bow echo detection
- Detecting Vanishing Points in Natural Scenes with Application in Photo Composition Analysis
- Stochastic Modeling and Optimization of Stragglers
- Automatic Thumbnail Generation by Smart Cropping
- Evaluating the Combined Impact of Node Architecture and Cloud Workload Characteristics on Network Traffic and Performance/Cost
- Fork-Join Queue Modeling and Optimal Scheduling in Parallel Programming Frameworks
- Optimal Placement of Cores, Caches and Memory Controllers in Network On-Chip
- Towards Stochastically Optimizing Data Computing Flows
- Stochastic Modeling and Optimization of Stragglers in Map-Reduce Framework
- Towards blind detection of low-rate spatial embedding in image steganalysis
- Modeling and Optimization of Straggling Mappers
- Performance Modeling and Optimization of MapReduce
- Security Weaknesses in PGP Protocol
- Eigenvalues-based LSB steganalysis
- Image steganalysis based on SVD and noise estimation: Improve sensitivity to spatial LSB embedding families
- Multi-dimensional correlation steganalysis
- Game-theoretic approach to mitigate packet dropping in wireless ad-hoc networks
- Risk of attack coefficient effect on availability of adhoc networks
- Private Identification, Authentication and Key Agreement Protocol with Security Mode Setup
- Private Identification, Authentication and Key Agreement Protocol with Security Mode Setup (PIAKAP)
- Locally Multi-path Adaptive Routing Protocol Resilient to Selfishness and Wormholes
- Extended Authentication and Key Agreement Protocol of UMTS
Thursday, February 25, 2016
Subscribe to:
Posts (Atom)