Search Results for author:
Found 52 papers, 18 papers with code
SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification
Furthermore, we propose the View-Refine Decoder (VRD) to obtain additional controllable conditions to generate missing cross-view features.
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey
Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation.
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction.
Towards Real-Time Open-Vocabulary Video Instance Segmentation
In this paper, we address the challenge of performing open-vocabulary video instance segmentation (OV-VIS) in real-time.
Signal Adversarial Examples Generation for Signal Detection Network via White-Box Attack
With the development and application of deep learning in signal detection tasks, the vulnerability of neural networks to adversarial attacks has also become a security threat to signal detection networks.
Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reduction
However, these methods have limited perception ability in the diverse morphologies of different metal implants with artifacts, which may generate spurious anatomical structures and exhibit inferior generalization capability.
Efficient Pretraining Model based on Multi-Scale Local Visual Field Feature Reconstruction for PCB CT Image Element Segmentation
In this model, the teacher-guided MIM pretraining model is introduced into PCB CT image element segmentation for the first time, and a multi-scale local visual field extraction (MVE) module is proposed to reduce redundancy by focusing on local visual fields.
Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex
Next, we use the contrast loss function to minimize the distance between the image embedding features and the text embedding features to complete the alignment operation of the stimulus image and text information.
UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
We evaluate our unified models on various benchmarks.
A Multimodal Visual Encoding Model Aided by Introducing Verbal Semantic Information
A convolutional network then maps from this multimodal feature space to voxel space, constructing the multimodal visual information encoding network model.
Exploring Transformers for Open-world Instance Segmentation
Open-world instance segmentation is a rising task, which aims to segment all objects in the image by learning from a limited number of base-category objects.
Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
Ranked #6 on
Object Tracking
on QuadTrack
Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
The deep neural network has attained significant efficiency in image recognition.
Muti-scale Graph Neural Network with Signed-attention for Social Bot Detection: A Frequency Perspective
Recently, more and more GNN-based methods have been proposed for bot detection.
RF-GNN: Random Forest Boosted Graph Neural Network for Social Bot Detection
This paper proposes a Random Forest boosted Graph Neural Network for social bot detection, called RF-GNN, which employs graph neural networks (GNNs) as the base classifiers to construct a random forest, effectively combining the advantages of ensemble learning and GNNs to improve the accuracy and robustness of the model.
Universal Instance Perception as Object Discovery and Retrieval
All instance perception tasks aim at finding certain objects specified by some queries such as category names, language expressions, and target annotations, but this complete field has been split into multiple independent subtasks.
Described Object Detection
Generalized Referring Expression Comprehension
+15
Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection
The proposed framework is evaluated using three real-world bot detection benchmark datasets, and it consistently exhibits superiority over the baselines.
MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark
However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.
Ranked #1 on
Stance Detection
on MGTAB
Segment Every Reference Object in Spatial and Temporal Spaces
In this work, we end the current fragmented situation and propose UniRef to unify the three reference-based object segmentation tasks with a single architecture.
Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks
Adversarial attacks are considered the intrinsic vulnerability of CNNs.
Towards Grand Unification of Object Tracking
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters.
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+4
Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks
The Graph Convolutional Networks (GCNs) have achieved excellent results in node classification tasks, but the model's performance at low label rates is still unsatisfactory.
High-Performance Transformer Tracking
First, we present a transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head.
Heterogeneous Architecture Search Approach within Adversarial Dynamic Defense Framework
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks (DNNs).
The Diversity Metrics of Sub-models based on SVD of Jacobians for Ensembles Adversarial Robustness
A new constraints norm is proposed in model training based on these criteria to isolate adversarial transferability without any prior knowledge of adversarial samples.
Adaptive Multi-layer Contrastive Graph Neural Networks
AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks.
Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout
In this paper, we propose a new gradient iteration framework, which redefines the relationship between the above three.
Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN.
Dynamic Defense Approach for Adversarial Robustness in Deep Neural Networks via Stochastic Ensemble Smoothed Model
The defense strategies are particularly passive in these processes, and enhancing initiative of such strategies can be an effective way to get out of this arms race.
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Object tracking has achieved significant progress over the past few years.
Ranked #27 on
Video Object Tracking
on NT-VOT211
Learning Spatio-Temporal Transformer for Visual Tracking
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component.
Ranked #6 on
Visual Object Tracking
on AVisT
Transformer Tracking
The correlation operation is a simple fusion manner to consider the similarity between the template and the search region.
Ranked #5 on
Visual Tracking
on TNL2K
Charged Lepton Flavor Violation at the EIC
We present a comprehensive analysis of the potential sensitivity of the Electron-Ion Collider (EIC) to charged lepton flavor violation (CLFV) in the channel $ep\to \tau X$, within the model-independent framework of the Standard Model Effective Field Theory (SMEFT).
High Energy Physics - Phenomenology High Energy Physics - Experiment Nuclear Experiment Nuclear Theory
The anomalous $Zb\bar{b}$ couplings: From LEP to LHC
We demonstrate that the $Zh$ data collected at the 13 TeV LHC can already resolve the apparent degeneracy of the anomalous $Zb\bar{b}$ couplings implied by the LEP precision electroweak measurements, with a strong dependence on the observed distribution of the $Z$ boson transverse momentum.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Energy storage and coherence in closed and open quantum batteries
We study the role of coherence in closed and open quantum batteries.
Quantum Physics Other Condensed Matter
Nonadiabatic Phase Transition with Broken Chiral Symmetry
We explore nonadiabatic quantum phase transitions in an Ising spin chain with a linearly time-dependent transverse field and two different spins per unit cell.
Statistical Mechanics General Relativity and Quantum Cosmology High Energy Physics - Theory Quantum Physics
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
Many recent trackers adopt the multiple-stage tracking strategy to improve the quality of bounding box estimation.
Ranked #18 on
Semi-Supervised Video Object Segmentation
on VOT2020
Semi-Supervised Video Object Segmentation
Visual Object Tracking
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
In recent years, the multiple-stage strategy has become a popular trend for visual tracking.
Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features
Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies.
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises
An effective and efficient perturbation generator is trained with a carefully designed adversarial loss, which can simultaneously cool hot regions where the target exists on the heatmaps and force the predicted bounding box to shrink, making the tracked target invisible to trackers.
BigGAN-based Bayesian reconstruction of natural images from human brain activity
In this study, we proposed a new GAN-based Bayesian visual reconstruction method (GAN-BVRM) that includes a classifier to decode categories from fMRI data, a pre-trained conditional generator to generate natural images of specified categories, and a set of encoding models and evaluator to evaluate generated images.
AdvJND: Generating Adversarial Examples with Just Noticeable Difference
To alleviate the tradeoff between the attack success rate and image fidelity, we propose a method named AdvJND, adding visual model coefficients, just noticeable difference coefficients, in the constraint of a distortion function when generating adversarial examples.
'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking
In this work, we present a novel robust and real-time long-term tracking framework based on the proposed skimming and perusal modules.
Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization
Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation.
Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense
In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them.
Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices
Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively.
Neurons and Cognition
A Sinogram Inpainting Method based on Generative Adversarial Network for Limited-angle Computed Tomography
Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data.
Medical Physics
A visual encoding model based on deep neural networks and transfer learning
In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i. e., AlexNet) and train a nonlinear mapping from visual features to brain activity.
Dissociable neural representations of adversarially perturbed images in convolutional neural networks and the human brain
Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images.
Constraint-free Natural Image Reconstruction from fMRI Signals Based on Convolutional Neural Network
Without semantic prior information, we present a novel method to reconstruct nature images from fMRI signals of human visual cortex based on the computation model of convolutional neural network (CNN).
Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture
We firstly employed the CapsNet to train the nonlinear mapping from image stimuli to high-level capsule features, and from high-level capsule features to image stimuli again in an end-to-end manner.
Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network
The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography.
