Search Results for author:
Found 39 papers, 18 papers with code
E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance
Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications.
Controllable Generation with Text-to-Image Diffusion Models: A Survey
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions.
Concept-centric Personalization with Large-scale Diffusion Priors
In this work, we present the task of customizing large-scale diffusion priors for specific concepts as concept-centric personalization.
FFEINR: Flow Feature-Enhanced Implicit Neural Representation for Spatio-temporal Super-Resolution
To address these problems, this paper proposes a Feature-Enhanced Implicit Neural Representation (FFEINR) for spatio-temporal super-resolution of flow field data.
GPU Accelerated Color Correction and Frame Warping for Real-time Video Stitching
Traditional image stitching focuses on a single panorama frame without considering the spatial-temporal consistency in videos.
Survey on Controlable Image Synthesis with Deep Learning
Image synthesis has attracted emerging research interests in academic and industry communities.
Large-Scale Person Detection and Localization using Overhead Fisheye Cameras
Instead of existing efforts devoted to localizing tourist photos captured by perspective cameras, in this article, we focus on devising person positioning solutions using overhead fisheye cameras.
Close-up View synthesis by Interpolating Optical Flow
The virtual viewpoint is perceived as a new technique in virtual navigation, as yet not supported due to the lack of depth information and obscure camera parameters.
On the Use of Power Amplifier Nonlinearity Quotient to Improve Radio Frequency Fingerprint Identification in Time-Varying Channels
The resulting radio frequency fingerprints (RFFs) are distorted, leading to low device detection and classification accuracy.
What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion
To tackle this problem, we introduce Domain-Specific Hybrid Refinement (DHR), which draws on the advantages and disadvantages of two mainstream refinement techniques to maintain editing ability with fidelity improvement.
Learning Dynamical Systems from Data: A Simple Cross-Validation Perspective, Part V: Sparse Kernel Flows for 132 Chaotic Dynamical Systems
In this paper, we introduce the method of \emph{Sparse Kernel Flows } in order to learn the ``best'' kernel by starting from a large dictionary of kernels.
Deep Learning Technique for Human Parsing: A Survey and Outlook
Human parsing aims to partition humans in image or video into multiple pixel-level semantic parts.
TIVE: A Toolbox for Identifying Video Instance Segmentation Errors
More importantly, as the fundamental model abilities demanded by the task, spatial segmentation and temporal association are still understudied in both evaluation and interaction mechanisms.
LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space
In this work, we first point out that these two characteristics are related to the degree of alignment (or disalignment) of the inverse codes with the synthetic distribution.
TOSE: A Fast Capacity Estimation Algorithm Based on Spike Approximations
Instead, fast eigenvalue estimations can be realized based on the spike approximations in our TOSE algorithm.
POPDx: An Automated Framework for Patient Phenotyping across 392,246 Individuals in the UK Biobank Study
We describe a method for phenotype recognition that imputes phenotype codes for all UK Biobank participants.
A Survey on Long-Tailed Visual Recognition
Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality.
Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
Our target is to learn visual correspondence from unlabeled videos.
Multi-Domain Joint Training for Person Re-Identification
Our discovery is that training with such an adaptive model can better benefit from more training samples.
Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
Our target is to learn visual correspondence from unlabeled videos.
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism.
Ranked #65 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
Quality-Aware Network for Face Parsing
This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021.
Center Prediction Loss for Re-identification
In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples.
Quality-Aware Network for Human Parsing
How to estimate the quality of the network output is an important issue, and currently there is no effective solution in the field of human parsing.
Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification
Learning cross-view consistent feature representation is the key for accurate vehicle Re-identification (ReID), since the visual appearance of vehicles changes significantly under different viewpoints.
Instance and Pair-Aware Dynamic Networks for Re-Identification
The proposed model is composed of three main branches where a self-guided dynamic branch is constructed to strengthen instance-specific features, focusing on every single image.
Realizing Majorana fermion modes in the Kitaev model
We study the possibility to realize Majorana zero mode that's robust and may be easily manipulated for braiding in quantum computing in the ground state of the Kitaev model in this work.
Strongly Correlated Electrons
Renovating Parsing R-CNN for Accurate Multiple Human Parsing
Multiple human parsing aims to segment various human parts and associate each part with the corresponding instance simultaneously.
CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately.
Efficient Scene Text Detection with Textual Attention Tower
Scene text detection has received attention for years and achieved an impressive performance across various benchmarks.
A Channel Perceiving Attack on Long-Range Key Generation and Its Countermeasure
Unfortunately, there is no experimental validation for communications environments when there are large-scale and small-scale fading effects.
A Holistic Representation Guided Attention Network for Scene Text Recognition
In this work, we propose a simple yet strong approach for scene text recognition.
Vehicle Re-identification in Aerial Imagery: Dataset and Approach
It is capable of explicitly detecting discriminative parts for each specific vehicle and significantly outperforms the evaluated baselines and state-of-the-art vehicle ReID approaches.
Detector-in-Detector: Multi-Level Analysis for Human-Parts
In particular, we adopt a region-based object detection structure with two carefully designed detectors to separately pay attention to the human body and body parts in a coarse-to-fine manner, which we call Detector-in-Detector network (DID-Net).
Parsing R-CNN for Instance-Level Human Analysis
Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance.
Ranked #1 on
Pose Estimation
on DensePose-COCO
Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network
So, it is important to study how face recognition networks are subject to attacks.
FSSD: Feature Fusion Single Shot Multibox Detector
SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed.
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging.
