7 papers
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
Jiayi Liu, Ali Mahdavi-Amiri, Manolis Savva
We address the task of simultaneous part-level reconstruction and motion parameter estimation for articulated objects. Given two sets of multi-view images of an object in two stati…
Exemplar-based Pattern Synthesis with Implicit Periodic Field Network
Haiwei Chen, Jiayi Liu, Weikai Chen +2
Synthesis of ergodic, stationary visual patterns is widely applicable in texturing, shape modeling, and digital content creation. The wide applicability of this technique thus requ…
ImageSubject: A Large-scale Dataset for Subject Detection
Xin Miao, Jiayi Liu, Huayan Wang +1
Main subjects usually exist in the images or videos, as they are the objects that the photographer wants to highlight. Human viewers can easily identify them but algorithms often c…
A Customized NoC Architecture to Enable Highly Localized Computing-On-the-Move DNN Dataflow
Kaining Zhou, Yangshuo He, Rui Xiao +2
The ever-increasing computation complexity of fastgrowing Deep Neural Networks (DNNs) has requested new computing paradigms to overcome the memory wall in conventional Von Neumann…
Fine-Grained Control of Artistic Styles in Image Generation
Xin Miao, Huayan Wang, Jun Fu +3
Recent advances in generative models and adversarial training have enabled artificially generating artworks in various artistic styles. It is highly desirable to gain more control…
Stochastic Whitening Batch Normalization
Shengdong Zhang, Ehsan Nezhadarya, Homa Fashandi +3
Batch Normalization (BN) is a popular technique for training Deep Neural Networks (DNNs). BN uses scaling and shifting to normalize activations of mini-batches to accelerate conver…
Improving Model Training by Periodic Sampling over Weight Distributions
Samarth Tripathi, Jiayi Liu, Unmesh Kurup +2
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentu…