Search Results for author:
Found 63 papers, 21 papers with code
CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly.
CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning
Inspired by hypothesis and verification method and identification of irrelevant information in human thinking process, we propose a new framework for LLMs abductive logical reasoning called CauseJudger (CJ), which identifies the authenticity of possible cause by transforming thinking from reverse to forward and removing irrelevant information.
Emotional Conversation: Empowering Talking Faces with Cohesive Expression, Gaze and Pose Generation
In the second step, these relocated landmarks are mapped to latent key points using self-supervised learning and then input into a pretrained model to create high-quality face images.
Research on the Spatial Data Intelligent Foundation Model
This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models.
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition
Over the past decade, most methods in visual place recognition (VPR) have used neural networks to produce feature representations.
Deep Homography Estimation for Visual Place Recognition
Moreover, we design a re-projection error of inliers loss to train the DHE network without additional homography labels, which can also be jointly trained with the backbone network to help it extract the features that are more suitable for local matching.
Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time, and uses about only 3% retrieval runtime of the two-stage VPR methods with RANSAC-based spatial verification.
Ranked #2 on
Visual Place Recognition
on Pittsburgh-250k-test
From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation
In this paper we propose Analytical Gaze Generalization framework (AGG) to improve the generalization ability of gaze estimation models without touching target domain data.
Unsupervised Gaze Representation Learning from Multi-view Face Images
Annotating gaze is an expensive and time-consuming endeavor requiring costly eye-trackers or complex geometric calibration procedures.
UVAGaze: Unsupervised 1-to-2 Views Adaptation for Gaze Estimation
To address these challenges, we propose a novel 1-view-to-2-views (1-to-2 views) adaptation solution in this paper, the Unsupervised 1-to-2 Views Adaptation framework for Gaze estimation (UVAGaze).
CGS-Mask: Making Time Series Predictions Intuitive for All
Artificial intelligence (AI) has immense potential in time series prediction, but most explainable tools have limited capabilities in providing a systematic understanding of important features over time.
AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition
Here we propose a Dynamically Aligning Local Features (DALF) algorithm to align the local features under spatial constraints.
PCFGaze: Physics-Consistent Feature for Appearance-based Gaze Estimation
Although recent deep learning based gaze estimation approaches have achieved much improvement, we still know little about how gaze features are connected to the physics of gaze.
DVGaze: Dual-View Gaze Estimation
We further propose a dual-view transformer to estimate gaze from dual-view features.
SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations
Our method also achieves an accuracy of 74. 84% on the task of recognizing low-resolution facial expressions, surpassing the current state-of-the-art FMD by 9. 48%.
Visibility Enhancement for Low-light Hazy Scenarios
The simulation is designed for generating the dataset with ground-truths by the proposed low-light hazy imaging model.
NPR: Nocturnal Place Recognition in Streets
Then we used this model to process existing large-scale VPR datasets to generate the VPR-Night datasets and demonstrated how to combine them with two popular VPR pipelines.
Jitter Does Matter: Adapting Gaze Estimation to New Domains
We evaluate the proposed method on four cross-domain gaze estimation tasks, and experimental results demonstrate that it significantly reduces the gaze jitter and improves the gaze estimation performance in target domains.
Discriminative feature encoding for intrinsic image decomposition
Intrinsic image decomposition is an important and long-standing computer vision problem.
Layout-Bridging Text-to-Image Synthesis
Specifically, we formulate the text-to-layout generation as a sequence-to-sequence modeling task, and build our model upon Transformer to learn the spatial relationships between objects by modeling the sequential dependencies between them.
Gaze-Vergence-Controlled See-Through Vision in Augmented Reality
This is because when we want to see through something, it is physically related to our gaze depth/vergence and thus should be naturally controlled by the eyes.
GazeOnce: Real-Time Multi-Person Gaze Estimation
In this paper, we propose the first one-stage end-to-end gaze estimation method, GazeOnce, which is capable of simultaneously predicting gaze directions for multiple faces (>10) in an image.
Generalizing Gaze Estimation With Rotation Consistency
Consequently, we propose the Rotation-enhanced Unsupervised Domain Adaptation (RUDA) for gaze estimation.
Cloud Sphere: A 3D Shape Representation via Progressive Deformation
In the area of 3D shape analysis, the geometric properties of a shape have long been studied.
Separating Content and Style for Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation aims to learn the mapping between two visual domains with unpaired samples.
Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation
Deep neural networks have significantly improved appearance-based gaze estimation accuracy.
Assessment of Deep Learning-based Heart Rate Estimation using Remote Photoplethysmography under Different Illuminations
We evaluate the performance of three deep learning-based methods (Deepphys, rPPGNet, and Physnet) to that of four traditional methods (CHROM, GREEN, ICA, and POS) using two public datasets: the UBFC-rPPG dataset and the BH-rPPG dataset.
Explainable Diabetic Retinopathy Detection and Retinal Image Generation
Though deep learning has shown successful performance in classifying the label and severity stage of certain diseases, most of them give few explanations on how to make predictions.
Gaze Estimation using Transformer
In this paper, we employ transformers and assess their effectiveness for gaze estimation.
Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark
This paper serves not only as a reference to develop deep learning-based gaze estimation methods, but also a guideline for future gaze estimation research.
STA-VPR: Spatio-temporal Alignment for Visual Place Recognition
Here we split the holistic mid-layer features into local features, and propose an adaptive dynamic time warping (DTW) algorithm to align local features from the spatial domain while measuring the distance between two images.
PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation
Different from common domain adaption methods, we propose a domain generalization method to improve the cross-domain performance without touching target samples.
Vulnerability of Appearance-based Gaze Estimation
However, many deep learning-based methods suffer from the vulnerability property, i. e., perturbing the raw image using noise confuses the gaze estimation models.
Polarization Guided Specular Reflection Separation
Based on the analysis of polarization, we propose a polarization guided model to generate a polarization chromaticity image, which is able to reveal the geometrical profile of the input image in complex scenarios, such as diversity of illumination.
Unsupervised Two-Stage Anomaly Detection
Anomaly detection from a single image is challenging since anomaly data is always rare and can be with highly unpredictable types.
Ranked #21 on
Anomaly Detection
on One-class CIFAR-10
Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets
Meanwhile, we also propose Adaptive Group Normalization to recalibrate eye features with the guidance of facial feature.
An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation
Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner.
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data.
Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs
This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively.
An Integrated Enhancement Solution for 24-hour Colorful Imaging
The current industry practice for 24-hour outdoor imaging is to use a silicon camera supplemented with near-infrared (NIR) illumination.
Beyond Optimizing for Clicks: Incorporating Editorial Values in News Recommendation
In our first study we explore how our news recommender steers reading behavior in the context of editorial values such as serendipity, dynamism, diversity, and coverage.
A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation
Human gaze is essential for various appealing applications.
CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly.
A Sparse Representation Based Joint Demosaicing Method for Single-Chip Polarized Color Sensor
Instead of mechanically demosaicing for the multi-channel polarized color image, we further present a sparse representation-based optimization strategy that utilizes chromatic information and polarimetric information to jointly optimize the model.
Unsupervised Learning for Intrinsic Image Decomposition from a Single Image
Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene.
Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
Specifically, it achieves 77. 1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75. 4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.
Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark.
Ranked #1 on
Low-Light Image Enhancement
on 3DMatch Benchmark
(using extra training data)
Semantic Guided Single Image Reflection Removal
Reflection is common in images capturing scenes behind a glass window, which is not only a disturbance visually but also influence the performance of other computer vision algorithms.
Hyperspectral City V1.0 Dataset and Benchmark
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
This raises safety concerns about the deployment of these systems in clinical settings.
Separate In Latent Space: Unsupervised Single Image Layer Separation
Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation.
What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis
However, techniques for analyzing the first-person video can be fundamentally different from those for the third-person video, and it is even more difficult to explore the shared information from both viewpoints.
Pathological Evidence Exploration in Deep Retinal Image Diagnosis
Inspired by Koch's Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector.
Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application.
VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes
Voxel is an important format to represent geometric data, which has been widely used for 3D deep learning in shape analysis due to its generalization ability and regular data format.
Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression
Inspired by this, we design the multi-stream ARE-Net; one asymmetric regression network (AR-Net) predicts 3D gaze directions for both eyes with a novel asymmetric strategy, and the evaluation network (E-Net) adaptively adjusts the strategy by evaluating the two eyes in terms of their performance during optimization.
Uncalibrated Photometric Stereo Under Natural Illumination
This paper presents a photometric stereo method that works with unknown natural illuminations without any calibration object.
Look, Perceive and Segment: Finding the Salient Objects in Images via Two-Stream Fixation-Semantic CNNs
Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by selecting the pre-segmented semantic objects that receive the highest fixation density in eye-tracking experiments.
Uncalibrated Photometric Stereo Based on Elevation Angle Recovery From BRDF Symmetry of Isotropic Materials
This sort of symmetry can be observed in a 1D BRDF slice from a subset of surface normals with the same azimuth angle, and we use it to devise an efficient modeling and solution method to constrain and recover the elevation angles of surface normals accurately.
A New Way to Factorize Linear Cameras
The implementation details of factorizing the 3x4 projection matrices of linear cameras into their left matrix factors and the 4x4 homogeneous central(also parallel for infinite center cases) projection factors are presented in this work.
A General Homogeneous Matrix Formulation to 3D Rotation Geometric Transformations
We present algebraic projective geometry definitions of 3D rotations so as to bridge a small gap between the applications and the definitions of 3D rotations in homogeneous matrix form.
Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances
We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances.
