Search Results for author:
Found 33 papers, 6 papers with code
AgentAlign: Misalignment-Adapted Multi-Agent Perception for Resilient Inter-Agent Sensor Correlations
Cooperative perception has attracted wide attention given its capability to leverage shared information across connected automated vehicles (CAVs) and smart infrastructures to address sensing occlusion and range limitation issues.
V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction
Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems.
DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines
Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision, which can be exploited to promote machine vision oriented visual signal processing.
Joint multi-dimensional dynamic attention and transformer for general image restoration
Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks.
LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution
Meanwhile, disentangled LF representation network is proposed to enhance the LF feature disentangling and decoupling.
Global-Local Progressive Integration Network for Blind Image Quality Assessment
Moreover, our model and its counterpart pre-trained on the proposed dataset respectively exhibited 5. 40% and 13. 23% improvements on across-synthetic datasets evaluation.
Multi-Granularity Semantic Revision for Large Language Model Distillation
At the sequence level, we propose a sequence correction and re-generation (SCRG) strategy.
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model.
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
However, most AT methods suffer from robust overfitting, i. e., a significant generalization gap in adversarial robustness between the training and testing curves.
Eliminating Warping Shakes for Unsupervised Online Video Stitching
In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching.
Graph Elimination Networks
Graph Neural Networks (GNNs) are widely applied across various domains, yet they perform poorly in deep layers.
CBQ: Cross-Block Quantization for Large Language Models
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
Data Upcycling Knowledge Distillation for Image Super-Resolution
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models.
Ranked #28 on
Image Super-Resolution
on Urban100 - 4x upscaling
LSCD: A Large-Scale Screen Content Dataset for Video Compression
Multimedia compression allows us to watch videos, see pictures and hear sounds within a limited bandwidth, which helps the flourish of the internet.
Enhancing Recommender Systems: A Strategy to Mitigate False Negative Impact
In implicit collaborative filtering (CF) task of recommender systems, recent works mainly focus on model structure design with promising techniques like graph neural networks (GNNs).
Epigenetic factor competition reshapes the EMT landscape
In such models, epigenetic factors are usually proposed to act on the chromatin regions directly involved in the expression of relevant genes.
FastBVP-Net: a lightweight pulse extraction network for measuring heart rhythm via facial videos
Remote photoplethysmography (rPPG) is an attractive camera-based health monitoring method that can measure the heart rhythm from facial videos.
Deep Learning-Based Intra Mode Derivation for Versatile Video Coding
To further improve the performance of intra coding in Versatile Video Coding (VVC), an intelligent intra mode derivation method is proposed in this paper, termed as Deep Learning based Intra Mode Derivation (DLIMD).
Remote blood pressure measurement via spatiotemporal mapping of a short-time facial video
Blood pressure (BP) monitoring is vital in daily healthcare, especially for cardiovascular diseases.
Distortion-Aware Loop Filtering of Intra 360^o Video Coding with Equirectangular Projection
In this paper, we propose a distortion-aware loop filtering model to improve the performance of intra coding for 360$^o$ videos projected via equirectangular projection (ERP) format.
Sphere Face Model:A 3D Morphable Model with Hypersphere Manifold Latent Space
However, the shape parameters of traditional 3DMMs satisfy the multivariate Gaussian distribution while the identity embeddings satisfy the hypersphere distribution, and this conflict makes it challenging for face reconstruction models to preserve the faithfulness and the shape consistency simultaneously.
A Dynamic 3D Spontaneous Micro-expression Database: Establishment and Evaluation
Micro-expressions are spontaneous, unconscious facial movements that show people's true inner emotions and have great potential in related fields of psychological testing.
Content-Preserving Image Stitching with Piecewise Rectangular Boundary Constraints
By analyzing the irregular boundary, we construct a piecewise rectangular boundary.
Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display
The impact of distorted geometry and texture attributes is further discussed in this paper.
DymSLAM:4D Dynamic Scene Reconstruction Based on Geometrical Motion Segmentation
The only input of DymSLAM is stereo video, and its output includes a dense map of the static environment, 3D model of the moving objects and the trajectories of the camera and the moving objects.
SUR-FeatNet: Predicting the Satisfied User Ratio Curvefor Image Compression with Deep Feature Learning
We then use deep feature learning to predict samples of the SUR curve and apply the method of least squares to fit the parametric model to the predicted samples.
Stereo-based Multi-motion Visual Odometry for Mobile Robots
In this letter, a stereo-based multi-motion visual odometry method is proposed to acquire the poses of the robot and other moving objects.
A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed.
Attention Distillation for Learning Video Representations
To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for recognition.
Ranked #41 on
Action Recognition
on UCF101
R$^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
In this paper, we propose a novel deep network, called rotatable region-based residual network (R$^3$-Net), to detect multi-oriented vehicles in aerial images and videos.
Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency
This paper addresses the challenging problem of estimating the general visual attention of people in images.
Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices
Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years.
