Search Results for author:
Found 35 papers, 12 papers with code
Disentangling Imperfect: A Wavelet-Infused Multilevel Heterogeneous Network for Human Activity Recognition in Flawed Wearable Sensor Data
To address these challenges, we propose a multilevel heterogeneous neural network, called MHNN, for sensor data analysis.
CVPR 2023 Text Guided Video Editing Competition
In this paper we present a retrospective on the competition and describe the winning method.
Modality Unifying Network for Visible-Infrared Person Re-Identification
Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations.
MAE-GEBD:Winning the CVPR'2023 LOVEU-GEBD Challenge
The Generic Event Boundary Detection (GEBD) task aims to build a model for segmenting videos into segments by detecting general event boundaries applicable to various classes.
High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection
Accurate and reliable optical remote sensing image-based small-ship detection is crucial for maritime surveillance systems, but existing methods often struggle with balancing detection performance and computational complexity.
Friend Ranking in Online Games via Pre-training Edge Transformers
Friend recall is an important way to improve Daily Active Users (DAU) in online games.
Advancing 3D finger knuckle recognition via deep feature learning
However, this approach results in a large feature dimension, and the trained classification layer is required for comparing probe samples, which limits the introduction of new classes.
TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition
Visible-infrared recognition (VI recognition) is a challenging task due to the enormous visual difference across heterogeneous images.
Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration
However, the performance of in-context learning is susceptible to the choice of prompt format, training examples and the ordering of the training examples.
A Review of Federated Learning in Energy Systems
Then, we conducted a comprehensive review of FL applications in the energy domain (refer to the smart grid in this paper).
Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification
This paper provides a new perspective to explain the success of knowledge distillation, i. e., quantifying knowledge points encoded in intermediate layers of a DNN for classification, based on the information theory.
Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability
This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i. e., these methods all reduce game-theoretic interactions between regional adversarial perturbations.
Masked Autoencoders for Generic Event Boundary Detection CVPR'2022 Kinetics-GEBD Challenge
In this paper, we apply Masked Autoencoders to improve algorithm performance on the GEBD tasks.
Why Adversarial Training of ReLU Networks Is Difficult?
We also prove that adversarial training tends to strengthen the influence of unconfident input samples with large gradient norms in an exponential manner.
GRAND+: Scalable Graph Random Neural Networks
In this work, we present a scalable and high-performance GNN framework GRAND+ for semi-supervised graph learning.
Ranked #1 on
Node Classification
on MAG-scholar-C
Flexible-Modal Face Anti-Spoofing: A Benchmark
Can we train a unified model, and flexibly deploy it under various modality scenarios?
SCR: Training Graph Neural Networks with Consistency Regularization
However, it is unclear how to best design the generalization strategies in GNNs, as it works in a semi-supervised setting for graph data.
Ranked #3 on
Node Property Prediction
on ogbn-papers100M
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i. e.} the view of multi-order interactions between input variables of DNNs.
A HYPOTHESIS FOR THE COGNITIVE DIFFICULTY OF IMAGES
This paper proposes a hypothesis to analyze the underlying reason for the cognitive difficulty of an image from two perspectives, i. e. a cognitive image usually makes a DNN strongly activated by cognitive concepts; discarding massive non-cognitive concepts may also help the DNN focus on cognitive concepts.
A Hypothesis for the Aesthetic Appreciation in Neural Networks
This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts.
A Game-Theoretic Taxonomy of Visual Concepts in DNNs
In this paper, we rethink how a DNN encodes visual concepts of different complexities from a new perspective, i. e. the game-theoretic multi-order interactions between pixels in an image.
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
Volume properties and rigidity on self-expanders of mean curvature flow
We also give the upper and lower bounds for the bottom of the spectrum of the $L$-stability operator and discuss the $L$-stability of some special self-expanders.
Differential Geometry
Technical Note: Game-Theoretic Interactions of Different Orders
In this study, we define interaction components of different orders between two input variables based on game theory.
DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning
In DualDE, we propose a soft label evaluation mechanism to adaptively assign different soft label and hard label weights to different triples, and a two-stage distillation approach to improve the student's acceptance of the teacher.
Building Interpretable Interaction Trees for Deep NLP Models
This paper proposes a method to disentangle and quantify interactions among words that are encoded inside a DNN for natural language processing.
Rotation-Equivariant Neural Networks for Privacy Protection
Compared to the traditional neural network, the RENN uses d-ary vectors/tensors as features, in which each element is a d-ary number.
VPQC: A Domain-Specific Vector Processor for Post-Quantum Cryptography Based on RISC-V Architecture
In the 5G era, massive devices need to be securely connected to the edge of communication networks, while emerging quantum computers can easily crack the traditional public-key ciphers.
Hardware Architecture
Explaining Knowledge Distillation by Quantifying the Knowledge
Whereas, in the scenario of learning from raw data, the DNN learns visual concepts sequentially.
Learning High-order Structural and Attribute information by Knowledge Graph Attention Networks for Enhancing Knowledge Graph Embedding
The goal of representation learning of knowledge graph is to encode both entities and relations into a low-dimensional embedding spaces.
Initialization for Network Embedding: A Graph Partition Approach
Network embedding has been intensively studied in the literature and widely used in various applications, such as link prediction and node classification.
An Attention-Based Approach for Single Image Super Resolution
We propose an attention-based approach to give a discrimination between texture areas and smooth areas.
Properties on n-dimensional convolution for image deconvolution
Convolution system is linear and time invariant, and can describe the optical imaging process.
Tracking Deformable Parts via Dynamic Conditional Random Fields
Despite the success of many advanced tracking methods in this area, tracking targets with drastic variation of appearance such as deformation, view change and partial occlusion in video sequences is still a challenge in practical applications.
