Search Results for author:
Found 114 papers, 40 papers with code
Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition
Gait recognition aims at identifying different people by the walking patterns, which can be conducted at a long distance without the cooperation of subjects.
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement.
Logits DeConfusion with CLIP for Few-Shot Learning
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks.
PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025.
FVOS for MOSE Track of 4th PVUW Challenge: 3rd Place Solution
Most existing methods rely on spatiotemporal memory networks to extract frame-level features and have achieved promising results on commonly used datasets.
Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models
Time series analysis is crucial for understanding dynamics of complex systems.
AADNet: Exploring EEG Spatiotemporal Information for Fast and Accurate Orientation and Timbre Detection of Auditory Attention Based on A Cue-Masked Paradigm
To obtain high decoding accuracy with low latency, an end-to-end deep learning model, AADNet, was proposed to exploit the spatiotemporal information from the short time window of EEG signals.
Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Furthermore, a multi-modal FAP method is proposed to measure the facial attractiveness in live streaming.
Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
From the spatial data management perspective, we present a novel Transformer framework called PatchSTG to efficiently and dynamically model spatial dependencies for large-scale traffic forecasting with interpretability and fidelity.
Ranked #1 on
Traffic Prediction
on LargeST
RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts
To enhance the model's ability to capture visual information at different levels without increasing model size, we design a novel architecture called Granularity-oriented Mixture of Experts to constraint the model to about 1 billion parameters.
HDI-Former: Hybrid Dynamic Interaction ANN-SNN Transformer for Object Detection Using Frames and Events
To address these challenges, we propose HDI-Former, a Hybrid Dynamic Interaction ANN-SNN Transformer, marking the first trial to design a directly trained hybrid ANN-SNN architecture for high-accuracy and energy-efficient object detection using frames and events.
Knowledge-aware Evolutionary Graph Neural Architecture Search
According to the predicted metrics, non-dominated candidate transfer architectures are selected to warm-start the multi-objective evolutionary algorithm for optimizing the #Acc and #Params on a new dataset.
DeepContext: A Context-aware, Cross-platform, and Cross-framework Tool for Performance Profiling and Analysis of Deep Learning Workloads
This paper introduces DeepContext, a novel profiler that links program contexts across high-level Python code, deep learning frameworks, underlying libraries written in C/C++, as well as device code executed on GPUs.
GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
Additionally, we provide a comprehensive analysis of 17 baselines, which includes statistical models, deep learning models, and foundation models.
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
Frequency-level specialization is too coarse-grained to capture this level of diversity.
A physics-driven sensor placement optimization methodology for temperature field reconstruction
Furthermore, the condition number, as the physics-based criterion, is used to optimize sensor locations by the genetic algorithm.
AIM 2024 Sparse Neural Rendering Challenge: Methods and Results
In this challenge, 5 teams submitted final results to Track 1 and 4 teams submitted final results to Track 2.
A general reduced-order neural operator for spatio-temporal predictive learning on complex spatial domains
Predictive learning for spatio-temporal processes (PL-STP) on complex spatial domains plays a critical role in various scientific and engineering fields, with its essence being the construction of operators between infinite-dimensional function spaces.
Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery
In a series of FPN experiments on the scale-preferred tasks, we found that the ``divide-and-conquer'' idea of FPN severely hampers the detector's learning in the right direction due to the large number of large-scale negative samples and interference from background noise.
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes.
LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS
Video Object Segmentation (VOS) presents several challenges, including object occlusion and fragmentation, the dis-appearance and re-appearance of objects, and tracking specific objects within crowded scenes.
Fast and Efficient: Mask Neural Fields for 3D Scene Segmentation
Recent advancements in distilling 2D vision-language foundation models into neural fields, like NeRF and 3DGS, enable open-vocabulary segmentation of 3D scenes from 2D multi-view images without the need for precise 3D annotations.
A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading
The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Meta-Backscatter: A New ISAC Paradigm for Battery-Free Internet of Things
The meta-material sensor has been regarded as a next-generation sensing technology for the battery-free Internet of Things (IoT) due to its battery-free characteristic and improved sensing performance.
Multiplane Prior Guided Few-Shot Aerial Scene Rendering
By investigating NeRF's and Multiplane Image (MPI)'s behavior, we propose to guide the training process of NeRF with a Multiplane Prior.
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity.
Prompt-Based Spatio-Temporal Graph Transfer Learning
To bridge the gap, we propose Spatio-Temporal Graph Prompting (STGP), a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain.
Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing
In the second stage, we shift focus on learning the appearance features of the source video.
Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification
Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs).
Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence.
Low-rank Adaptation for Spatio-Temporal Forecasting
Spatio-temporal forecasting is crucial in real-world dynamic systems, predicting future changes using historical data from diverse locations.
Hallucination Diversity-Aware Active Learning for Text Summarization
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i. e., texts that are factually incorrect or unsupported.
CACA Agent: Capability Collaboration based AI Agent
As AI Agents based on Large Language Models (LLMs) have shown potential in practical applications across various fields, how to quickly deploy an AI agent and how to conveniently expand the application scenario of AI agents has become a challenge.
Diffeomorphism Neural Operator for various domains and parameters of partial differential equations
This paper presents a novel neural operator learning framework for solving PDEs with various domains and parameters defined for physical systems, named diffeomorphism neural operator (DNO).
QAGait: Revisit Gait Recognition from a Quality Perspective
Gait recognition is a promising biometric method that aims to identify pedestrians from their unique walking patterns.
TNANet: A Temporal-Noise-Aware Neural Network for Suicidal Ideation Prediction with Noisy Physiological Data
Current methods predominantly focus on image and text data or address artificially introduced noise, neglecting the complexities of natural noise in time-series analysis.
Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification
In this work, we propose to leverage the geometric information of the feature distribution of the well-represented head class to guide the model to learn the underlying distribution of the tail class.
LLMs for Relational Reasoning: How Far are We?
Large language models (LLMs) have revolutionized many areas (e. g. natural language processing, software engineering, etc.)
Image Quality, Uniformity and Computation Improvement of Compressive Light Field Displays with U-Net
We apply the U-Net model for compressive light field synthesis.
Towards the Unification of Generative and Discriminative Visual Foundation Model: A Survey
The advent of foundation models, which are pre-trained on vast datasets, has ushered in a new era of computer vision, characterized by their robustness and remarkable zero-shot generalization capabilities.
CLIPC8: Face liveness detection algorithm based on image-text pairs and contrastive learning
To tackle this issue, we propose a face liveness detection method based on image-text pairs and contrastive learning, dividing liveness attack problems in the financial field into eight categories and using text information to describe the images of these eight types of attacks.
Data-Centric Long-Tailed Image Recognition
In the context of the long-tail scenario, models exhibit a strong demand for high-quality data.
Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learning
In this paper, we propose to model these tasks in a unified probabilistic perspective, viewing them as predictions based on conditional information with shared dependencies.
Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning
The disadvantage is that these methods generally pursue models with balanced class accuracy on the data manifold, while ignoring the ability of the model to resist interference.
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
To address these issues, we propose UniTime for effective cross-domain time series learning.
Ranked #5 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Spiking Structured State Space Model for Monaural Speech Enhancement
Speech enhancement seeks to extract clean speech from noisy signals.
FastPoseGait: A Toolbox and Benchmark for Efficient Pose-based Gait Recognition
Our toolbox supports a set of cutting-edge pose-based gait recognition algorithms and a variety of related benchmarks.
Free Lunch for Gait Recognition: A Novel Relation Descriptor
Gait recognition is to seek correct matches for query individuals by their unique walking patterns.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
AutoST: Training-free Neural Architecture Search for Spiking Transformers
To address these limitations, we introduce AutoST, a training-free NAS method for Spiking Transformers, to rapidly identify high-performance Spiking Transformer architectures.
LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
To mitigate these limitations, we introduce the LargeST benchmark dataset.
TorchBench: Benchmarking PyTorch with High API Surface Coverage
TorchBench is able to comprehensively characterize the performance of the PyTorch software stack, guiding the performance optimization across models, PyTorch framework, and GPU libraries.
Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain
Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluate and improve NLP models.
Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes.
Ranked #19 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Unsupervised Gait Recognition with Selective Fusion
So to make the pre-trained gait recognition model able to be fine-tuned on unlabeled datasets, we propose a new task: Unsupervised Gait Recognition (UGR).
Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution.
Do We Really Need Graph Neural Networks for Traffic Forecasting?
Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting.
An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions
For the cloth-changing problem, video-based ReID is rarely studied due to the lack of a suitable cloth-changing benchmark, and gait recognition is often researched under controlled conditions.
Delving into Semantic Scale Imbalance
Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations.
Event-based Monocular Dense Depth Estimation with Recurrent Transformers
Event cameras, offering high temporal resolutions and high dynamic ranges, have brought a new perspective to address common challenges (e. g., motion blur and low light) in monocular depth estimation.
DWRSeg: Rethinking Efficient Acquisition of Multi-scale Contextual Information for Real-time Semantic Segmentation
In this method, the multi-rate depth-wise dilated convolutions take a simpler role in feature extraction: performing simple semantic-based morphological filtering with one desired receptive field in the second step based on each concise feature map of region form provided by the first step, to improve their efficiency.
Deep Active Learning for Computer Vision: Past and Future
As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model.
Task-Agnostic Learning to Accomplish New Tasks
Inspired by this observation, this paper proposes a task-agnostic learning method (TAL for short) that can learn fragmented knowledge from task-agnostic data to accomplish new tasks.
Deep Learning-based Occluded Person Re-identification: A Survey
After that, we summarize and compare the performance of recent occluded person Re-ID methods on four popular datasets: Partial-ReID, Partial-iLIDS, Occluded-ReID, and Occluded-DukeMTMC.
Progressive Feature Learning for Realistic Cloth-Changing Gait Recognition
Gait recognition is instrumental in crime prevention and social security, for it can be conducted at a long distance to figure out the identity of persons.
Reliability Analysis of Complex Multi-State System Based on Universal Generating Function and Bayesian Network
To overcome the respective defects of UGF and BN, a novel reliability analysis method called UGF-BN is proposed for the complex MSS.
Bayesian Physics-Informed Extreme Learning Machine for Forward and Inverse PDE Problems with Noisy Data
Besides, for inverse PDE problems, problem parameters considered as new output layer weights are unified in a framework with forward PDE problems.
Transformers Meet Visual Learning Understanding: A Comprehensive Review
Three image tasks and two video tasks of computer vision are investigated.
ApolloRL: a Reinforcement Learning Platform for Autonomous Driving
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving.
Mars Entry Trajectory Planning with Range Discretization and Successive Convexification
The virtual control and adaptive trust-region techniques are employed to improve the accuracy, robustness, and computation efficiency of the algorithm.
Temperature Field Inversion of Heat-Source Systems via Physics-Informed Neural Networks
In this work, we develop a physics-informed neural network-based temperature field inversion (PINN-TFI) method to solve the TFI-HSS task and a coefficient matrix condition number based position selection of observations (CMCN-PSO) method to select optima positions of noise observations.
3D Scene Understanding at Urban Intersection using Stereo Vision and Digital Map
The driving behavior at urban intersections is very complex.
Data Augmentation For Medical MR Image Using Generative Adversarial Networks
Our results show that PGGAN-SSIM successfully generates 256x256 realistic brain tumor MR images which fill the real image distribution uncovered by the original dataset.
Residual fourier neural operator for thermochemical curing of composites
During the curing process of composites, the temperature history heavily determines the evolutions of the field of degree of cure as well as the residual stress, which will further influence the mechanical properties of composite, thus it is important to simulate the real temperature history to optimize the curing process of composites.
Relative Entropy Gradient Sampler for Unnormalized Distributions
We propose a relative entropy gradient sampler (REGS) for sampling from unnormalized distributions.
Large-scale Autonomous Flight with Real-time Semantic SLAM under Dense Forest Canopy
Semantic maps represent the environment using a set of semantically meaningful objects.
When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?
In view of this, one may ask: can we leverage the additional signals from contrastive learning to alleviate data scarcity, so as to benefit STG forecasting?
Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
More critically, EAS is able to find compact architectures within 0. 1 second for 50 deployment scenarios.
Multi-Scale Progressive Attention Network for Video Question Answering
Under the question{'}s guidance of progressive attention, we realize the fusion of all-scale video features.
A novel meta-learning initialization method for physics-informed neural networks
Inspired by this idea, we propose the new Reptile initialization to sample more tasks from the parameterized PDEs and adapt the penalty term of the loss.
Deployment Optimization for Meta-material Based Internet of Things
It is a challenge to optimize the positions of the Meta-IoT devices to ensure sensing accuracy of 3D environmental conditions.
Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy
We propose a balanced coarsening scheme for multilevel hypergraph partitioning.
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
Specifically, we propose two tasks to learn the appearance and speed consistency, respectively.
One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment
When the precision of quantization is adjusted, it is necessary to fine-tune the quantized model or minimize the quantization noise, which brings inconvenience in practical applications.
GAFnet: Group Attention Fusion Network for PAN and MS Image High-Resolution Classification
Second, the group spatial attention and group spectral attention modules are proposed to extract image features.
Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization
Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method.
Autonomous Driving
Data Augmentation
+1
Robotics
Turbulence suppression by streamwise-varying wall rotation in pipe flow
Two control parameters, which are velocity amplitude and wavelength, are considered.
Fluid Dynamics
Deep-Learned Broadband Encoding Stochastic Filters for Computational Spectroscopic Instruments
Computational spectroscopic instruments with Broadband Encoding Stochastic (BEST) filters allow the reconstruction of the spectrum at high precision with only a few filters.
Instrumentation and Detectors
Group Contextual Encoding for 3D Point Clouds
In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios.
Place Recognition in Forests with Urquhart Tessellations
In this letter, we present a novel descriptor based on Urquhart tessellations derived from the position of trees in a forest.
Variational Inference-Based Dropout in Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
This paper proposes to generalize the variational recurrent neural network (RNN) with variational inference (VI)-based dropout regularization employed for the long short-term memory (LSTM) cells to more advanced RNN architectures like gated recurrent unit (GRU) and bi-directional LSTM/GRU.
C-CNN: Contourlet Convolutional Neural Networks
Second, the spatial-spectral feature fusion strategy is designed to incorporate the spectral features into CNN architecture.
The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
This paper presents and characterizes an Open Application Repository for Federated Learning (OARF), a benchmark suite for federated machine learning systems.
MultiResolution Attention Extractor for Small Object Detection
Small objects are difficult to detect because of their low resolution and small size.
Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Faces
The main cause of this problem is the loss of discriminative feature due to reduced resolution.
Facial Expression Recognition
Facial Expression Recognition (FER)
+4
SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory
This paper describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping.
PolSF: PolSAR image dataset on San Francisco
In this paper, we have collected five open polarimetric SAR images, which are images of the San Francisco area.
Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning
Eltwise layer is a commonly used structure in the multi-branch deep learning network.
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
By systematically summarizing the existing federated learning systems, we present the design factors, case studies, and future research opportunities.
PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine
In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine.
Semi-supervised Complex-valued GAN for Polarimetric SAR Image Classification
However, their interpretation faces some challenges, e. g., deficiency of labeled data, inadequate utilization of data information and so on.
An End-to-End Network for Panoptic Segmentation
Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic.
Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect
High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations.
Hardware Architecture Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Performance
Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association
We present a cheap, lightweight, and fast fruit counting pipeline that uses a single monocular camera.
Robotics
Deep Adaptive Proposal Network for Object Detection in Optical Remote Sensing Images
More recently, a two-stage detector Faster R-CNN is proposed and demonstrated to be a promising tool for object detection in optical remote sensing images, while the sparse and dense characteristic of objects in remote sensing images is complexity.
Polarimetric Convolutional Network for PolSAR Image Classification
Based on sparse scattering coding and convolution neural network, the polarimetric convolutional network is proposed to classify PolSAR images by making full use of polarimetric information.
Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion
We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images.
Deep Hashing with Category Mask for Fast Video Retrieval
This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval.
DualNet: Learn Complementary Features for Image Recognition
Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed.
Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration
In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space.
Unsupervised Submodular Rank Aggregation on Score-based Permutations
Unsupervised rank aggregation on score-based permutations, which is widely used in many applications, has not been deeply explored yet.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Highway Vehicle Counting in Compressed Domain
HCR hierarchically divides the traffic scenes into different cases according to vehicle density, such that the broad-variation characteristics of traffic scenes can be better approximated.
