Search Results for author:
Found 17 papers, 3 papers with code
Calibrated Multi-Preference Optimization for Aligning Diffusion Models
To address this, we present Calibrated Preference Optimization (CaPO), a novel method to align T2I diffusion models by incorporating the general preference from multiple reward models without human annotated data.
Optical Diffusion Models for Image Generation
Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution.
PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
However, in the vision domain, existing RL-based reward finetuning methods are limited by their instability in large-scale training, rendering them incapable of generalizing to complex, unseen prompts.
Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation
We use the novel multi-reward optimization algorithm to jointly optimize the T2I model and a prompt expansion network, resulting in significant improvement of image quality and also allow to control the trade-off of different rewards using a reward related prompt during inference.
On-device Real-time Custom Hand Gesture Recognition
Our framework provides a pre-trained single-hand embedding model that can be fine-tuned for custom gesture recognition.
Forward-Forward Training of an Optical Neural Network
Neural networks (NN) have demonstrated remarkable capabilities in various tasks, but their computation-intensive nature demands faster and more energy-efficient hardware implementations.
MUSIQ: Multi-scale Image Quality Transformer
To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation.
Ranked #3 on
Image Quality Assessment
on MSU NR VQA Database
Adversarially Adaptive Normalization for Single Domain Generalization
As a generic tool, the improvement introduced by ASR-Norm is agnostic to the choice of ADA methods.
Multi-path Neural Networks for On-device Multi-domain Visual Classification
This approach effectively reduces the total number of parameters and FLOPS, encouraging positive knowledge transfer while mitigating negative interference across domains.
Learnable Cost Volume Using the Cayley Representation
Cost volume is an essential component of recent deep models for optical flow estimation and is usually constructed by calculating the inner product between two feature vectors.
A Survey of Visual Analysis of Human Motion and Its Applications
This paper summarizes the recent progress in human motion analysis and its applications.
Remote Health Coaching System and Human Motion Data Analysis for Physical Therapy with Microsoft Kinect
In order to generate the kinematic parameter from the noisy data captured by Kinect, we propose a kinematic filtering algorithm based on Unscented Kalman Filter and the kinematic model of human skeleton.
Unsupervised Temporal Segmentation of Repetitive Human Actions Based on Kinematic Modeling and Frequency Analysis
In this paper, we propose a method for temporal segmentation of human repetitive actions based on frequency analysis of kinematic parameters, zero-velocity crossing detection, and adaptive k-means clustering.
Evaluation of Pose Tracking Accuracy in the First and Second Generations of Microsoft Kinect
Microsoft Kinect camera and its skeletal tracking capabilities have been embraced by many researchers and commercial developers in various applications of real-time human movement analysis.
Computational Models for Multiview Dense Depth Maps of Dynamic Scene
This paper reviews the recent progresses of the depth map generation for dynamic scene and its corresponding computational models.
Content adaptive screen image scaling
This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing.
