Trista Chen

MMEDIA 2013 The Fifth International Conferences on Advances in Multimedia MMEDIA 2013 Committee MMEDIA Advisory Committee MMEDIA 2013 Technical Program Committee

in Venice, Italy, was an international forum for researchers, students, and professionals where t... more in Venice, Italy, was an international forum for researchers, students, and professionals where to present recent research results on advances in multimedia, and mobile and ubiquitous multimedia. MMEDIA 2012 brought together experts from both academia and industry for the exchange of ideas and discussion on future challenges in multimedia fundamentals, mobile and ubiquitous multimedia, multimedia ontology, multimedia user-centered perception, multimedia services and applications, and mobile multimedia. The rapid growth of information on the Web, its ubiquity and pervasiveness, makes the www the biggest repository. While the volume of information may be useful, it creates new challenges for information retrieval, identification, understanding, selection, etc. Investigating new forms of platforms, tools, principles offered by Semantic Web opens another door to enable human programs, or agents, to understand what records are about, and allows integration between domain-dependent and me...

Download

Estimation

Current approaches to pose estimation and tracking can be classified into two categories: generat... more Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human pose from image observations, they are computationally expensive due to search in the high dimensional human pose space. On the other hand, discriminative approaches do not generalize well, but are computationally efficient. We present a hybrid model that combines the strengths of the two in an integrated learning and inference framework. We extend the Gaussian process latent variable model (GPLVM) to include an embedding from observation space (the space of image features) to the latent space. GPLVM is a generative model, but the inclusion of this mapping provides a discriminative component,

Deriving User Influences on Topics from Visual and Social Content

VRAPS: Visual Rhythm-based Audio Playback System

2010 IEEE International Conference on Multimedia and Expo, 2010

VRAPS (Visual Rhythm-based Audio Playback System) is an interactive multimedia application that u... more VRAPS (Visual Rhythm-based Audio Playback System) is an interactive multimedia application that uses a novel visual rhythm detection technique to allow a user to control the playback speed of an audio signal by moving in front of a video camera. As traditionally defined in the context of music, a beat represents a distinctive musical event such as the hitting of

Geometric Tools for Multicamera Surveillance Systems

2007 First ACM/IEEE International Conference on Distributed Smart Cameras, 2007

Our analysis and visualization tools use 3D building geometry to support surveillance tasks. Thes... more Our analysis and visualization tools use 3D building geometry to support surveillance tasks. These tools are part of DOTS,........ our multicamera surveillance system; a system with over 20 cameras spread throughout the public spaces of our building The geometric input to DOTS is a floor plan and information such as cubicle wall heights. From this input we construct a 3D model and an enhanced 2D floor plan that are the bases for more specific visualization and analysis tools. Foreground objects of interest can be placed within these models and dynamically updated in real time across camera views. Alternatively, a virtual first-person view suggests what a tracked person can see as she moves about. Interactive visualization tools support complex camera-placement tasks. Extrinsic camera calibration is supported both by visualizations of parameter adjustment results and by methods for establishing correspondences between image features and the 3D model.

Download

Improving branch prediction accuracy with parallel conservative correctors

Proceedings of the 2nd conference on Computing frontiers - CF '05, 2005

... with Parallel Conservative Correctors Chunrong Lai1, Shih-Lien Lu2, Yurong Chen1, Trista Chen... more

Method for video error concealment by updating statistics

Systems and methods for interactive semi-automatic document scanning

Digital watermarking

Watermarking of a digitized image

System and method for efficiently finding near-similar images in massive databases

A Trainable Reconciliation Method for Hierarchical Time-Series

ArXiv, 2021

In numerous applications, it is required to produce forecasts for multiple time-series at differe... more In numerous applications, it is required to produce forecasts for multiple time-series at different hierarchy levels. An obvious example is given by the supply chain in which demand forecasting may be needed at a store, city, or country level. The independent forecasts typically do not add up properly because of the hierarchical constraints, so a reconciliation step is needed. In this paper, we propose a new general, flexible, and easy-to-implement reconciliation strategy based on an encoder-decoder neural network. By testing our method on four realworld datasets, we show that it can consistently reach or surpass the performance of existing methods in the reconciliation setting.

Download

TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

In this paper, we propose a framework called Trust-MAE to address the problem of product defect c... more In this paper, we propose a framework called Trust-MAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid overgeneralizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises away from the memory slots. The result is a framework that can reconstruct defect-free images and identify the defective regions using a perceptual distance network. When compared against various state-of-the-art baselines, our approach performs competitively under noise-free MVTec datasets. More importantly, it remains effective at a noise level up to 40% while significantly outperforming other baselines.

Download

Computer vision workload analysis: case study of video surveillance systems

... Surveillance Systems. Trista P Chen, Horst Hanssecker, Alexander Bovyrin, Roman Belenov, Kons... more

Carl

ACM Transactions on Graphics

create autonomous agents in dynamic environments by adding navigation modules over the entire pro... more

Download

Challenges and opportunities of obtaining performance from multi-core CPUs and many-core GPUs

Proceedings of the 2009 Ieee International Conference on Acoustics Speech and Signal Processing, 2009

... Trista P. Chen* and Yen-Kuang Chen+ ... and scalable model for developers of shared-memory pa... more

Graphical System and Method for User Authentication

Error-Resilient Rate Shaping For Video Streaming Over Packet-Loss Networks

Deriving Visual Rhythm from Video Signals

Systems and methods for human body pose estimation

Uploads

Papers by Trista Chen

Log In