Search Results for author:
Found 78 papers, 31 papers with code
FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos
Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models.
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR).
Low-Light Image Enhancement using Event-Based Illumination Estimation
Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments.
Rethinking Image Evaluation in Super-Resolution
Following this observation, in this paper, we are interested in the following questions: Are GT images in existing SR datasets 100% trustworthy for model evaluations?
Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
The rapid expansion of mobile internet has resulted in a substantial increase in user-generated content (UGC) images, thereby making the thorough assessment of UGC images both urgent and essential.
Ranked #1 on
Image Quality Assessment
on KonIQ-10k
Latent Swap Joint Diffusion for 2D Long-Form Latent Generation
To address this issue, we propose Self-Loop Latent Swap, a frame-level bidirectional swap applied to the overlapping region of adjacent views.
Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs
This structure is designed to reflect the input question and generate more validated deductive knowledge, thereby enhancing the alignment of LLMs and KGs and ensuring more cohesive integration.
The Mitochondrial Genome of Cathaya argyrophylla Reaches 18.99 Mb: Analysis of Super-Large Mitochondrial Genomes in Pinaceae
In this study, we sequenced and analyzed the mitochondrial genome of Cathaya argyrophylla, an endangered and endemic Pinaceae species, uncovering a genome size of 18. 99 Mb, meaning the largest mitochondrial genome reported to date.
Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues
In this paper, we propose a novel task named Explainable Personality Recognition, aiming to reveal the reasoning process as supporting evidence of the personality trait.
Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions
A Depth-aware Controllable DoF Imaging (DCDI) framework is proposed equipped with All-in-Focus (AiF) aberration correction and monocular depth estimation, where the recovered image and corresponding depth map are utilized to produce imaging results under diverse DoFs of any high-end lens via patch-wise convolution.
A Flexible Framework for Universal Computational Aberration Correction via Automatic Lens Library Generation and Domain Adaptation
OmniLens extends the idea of universal CAC to a broader concept, where a base model is trained for three cases, including zero-shot CAC with the pre-trained model, few-shot CAC with a little lens-specific data for fine-tuning, and domain adaptive CAC using domain adaptation for lens-descriptions-unknown lens.
Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
Meanwhile, based on the diffusion model, preferred actions within the same behavior distribution are automatically generated through the critic function.
Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems
Recently, joint design approaches that simultaneously optimize optical systems and downstream algorithms through data-driven learning have demonstrated superior performance over traditional separate design approaches.
AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results
The performance of the top-5 submissions is reviewed and provided here as a survey of diverse deep models for efficient video quality assessment of user-generated content.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs
However, existing methodologies that integrate LLMs and KGs often navigate the task-solving process solely based on the LLM's analysis of the question, overlooking the rich cognitive potential inherent in the vast knowledge encapsulated in KGs.
Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector Quantization
Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications.
SGE: Structured Light System Based on Gray Code with an Event Camera
Fast and accurate depth sensing has long been a significant research challenge.
Temporal-Mapping Photography for Event Cameras
Different from traditional methods that mainly rely on event integration, the proposed Event-Based Temporal Mapping Photography (EvTemMap) measures the time of event emitting for each pixel.
Ultraviolet Positioning via TDOA: Error Analysis and System Prototype
The theoretical average error matches well with the simulation results, which indicates that theoretical fitting can provide reliable guidance and prediction for hardware experiments.
Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis
Our end-to-end system achieves state-of-the-art performance on two large-scale document layout analysis datasets (PubLayNet and DocLayNet), a high-quality hierarchical document structure reconstruction dataset (HRDoc), and our Comp-HRDoc benchmark.
Dynamic Relation Transformer for Contextual Text Block Detection
Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes.
Perceptual Quality Assessment for Video Frame Interpolation
To evaluate the quality of VFI frames without reference videos, a no-reference perceptual quality assessment method is proposed in this paper.
YAYI 2: Multilingual Open-Source Large Language Models
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence.
The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
This technical report details our submission system to the CHiME-7 DASR Challenge, which focuses on speaker diarization and speech recognition under complex multi-speaker scenarios.
Key Gene Mining in Transcriptional Regulation for Specific Biological Processes with Small Sample Sizes Using Multi-network pipeline Transformer
Gene mining is an important topic in the field of life sciences, but traditional machine learning methods cannot consider the regulatory relationships between genes.
A Multi-Scale Recurrent Framework for Motion Segmentation With Event Camera
Motion segmentation is a formidable computer vision task, aiming to segment moving targets from a dynamic scene.
Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation
In this paper, we propose an adaptive two-stage knowledge distillation method consisting of hidden layer learning and output layer learning.
Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers
In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging.
A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images
In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images.
Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer
Unlike previous methods, we formulate table separation line prediction as a line regression problem instead of an image segmentation problem and propose a new two-stage dynamic queries enhanced DETR based separation line regression approach, named DQ-DETR, to predict separation lines from table images directly.
Improving Fast Auto-Focus with Event Polarity
Specifically, the symmetrical relationship between the event polarities in focusing is investigated, and the event-based focus evaluation function is proposed based on the principles of the event cameras and the imaging model in the focusing process.
Event-Based Frame Interpolation with Ad-hoc Deblurring
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene.
Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations
Further, we propose Computational Imaging Assisted Domain Adaptation (CIADA) to leverage prior knowledge of CI for robust performance in SSOA.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Robust Human Matting via Semantic Guidance
Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes.
TSRFormer: Table Structure Recognition with Transformers
We present a new table structure recognition (TSR) approach, called TSRFormer, to robustly recognizing the structures of complex tables with geometrical distortions from various table images.
Ranked #2 on
Table Recognition
on PubTabNet
(TEDS-Struct metric)
Real Image Restoration via Structure-preserving Complementarity Attention
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks.
DETRs with Hybrid Matching
One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections.
FaceFormer: Scale-aware Blind Face Restoration with Transformers
Blind face restoration usually encounters with diverse scale face inputs, especially in the real world.
Multi-Task Learning Framework for Emotion Recognition in-the-wild
This paper presents our system for the Multi-Task Learning (MTL) Challenge in the 4th Affective Behavior Analysis in-the-wild (ABAW) competition.
Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens
In this paper, we propose an Annular Computational Imaging (ACI) framework to break the optical limit of light-weight PAL design.
Efficient Human Pose Estimation via 3D Event Point Cloud
We then leverage the rasterized event point cloud as input to three different backbones, PointNet, DGCNN, and Point Transformer, with two linear layer decoders to predict the location of human keypoints.
Ranked #1 on
3D Human Pose Estimation
on DHP19
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Rethinking Classifier and Adversarial Attack
Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robustness of these models (i. e., not approaching the lower bound of robustness).
CE-based white-box adversarial attacks will not work using super-fitting
This is especially dangerous for some systems with high-security requirements, so this paper proposes a new defense method by using the model super-fitting state to improve the model's adversarial robustness (i. e., the accuracy under adversarial attacks).
Outlier-Robust Geometric Perception: A Novel Thresholding-Based Estimator with Intra-Class Variance Maximization
In this paper, we present a novel general-purpose robust estimator TIVM (Thresholding with Intra-class Variance Maximization) that can collaborate with standard non-minimal solvers to efficiently reject outliers for geometric perception problems.
Robust Table Detection and Structure Recognition from Heterogeneous Document Images
We introduce a new table detection and structure recognition approach named RobusTabNet to detect the boundaries of tables and reconstruct the cellular structure of each table from heterogeneous document images.
Ranked #5 on
Table Recognition
on PubTabNet
(TEDS-Struct metric)
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times.
Ranked #2 on
Object Detection
on DSEC
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
Practical, Fast and Robust Point Cloud Registration for 3D Scene Stitching and Object Localization
3D point cloud registration ranks among the most fundamental problems in remote sensing, photogrammetry, robotics and geometric computer vision.
TriVoC: Efficient Voting-based Consensus Maximization for Robust Point Cloud Registration with Extreme Outlier Ratios
Correspondence-based point cloud registration is a cornerstone in robotics perception and computer vision, which seeks to estimate the best rigid transformation aligning two point clouds from the putative correspondences.
DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios
In this paper, we present a novel time-efficient RANSAC-type consensus maximization solver, named DANIEL (Double-layered sAmpliNg with consensus maximization based on stratIfied Element-wise compatibiLity), for robust registration.
Conditional DETR for Fast Training Convergence
Our approach, named conditional DETR, learns a conditional spatial query from the decoder embedding for decoder multi-head cross-attention.
Ranked #109 on
Object Detection
on COCO minival
Separation Guided Speaker Diarization in Realistic Mismatched Conditions
We propose a separation guided speaker diarization (SGSD) approach by fully utilizing a complementarity of speech separation and speaker clustering.
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents
In this paper, we propose a new multi-modal backbone network by concatenating a BERTgrid to an intermediate layer of a CNN model, where the input of CNN is a document image and the BERTgrid is a grid of word embeddings, to generate a more powerful grid-based document representation, named ViBERTgrid.
Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
A lightweight panoramic annular semantic segmentation neural network model is designed to achieve high-accuracy and real-time scene parsing.
Ranked #81 on
Semantic Segmentation
on Cityscapes val
ICOS: Efficient and Highly Robust Rotation Search and Point Cloud Registration with Correspondences
Rotation search and point cloud registration are two fundamental problems in robotics and computer vision, which aim to estimate the rotation and the transformation between the 3D vector sets and point clouds, respectively.
RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration using Invariant Compatibility
Correspondence-based rotation search and point cloud registration are two fundamental problems in robotics and computer vision.
USTC-NELSLIP System Description for DIHARD-III Challenge
This system description describes our submission system to the Third DIHARD Speech Diarization Challenge.
IRON: Invariant-based Highly Robust Point Cloud Registration
Once the scale is estimated, our second contribution is to relax the non-convex global registration problem into a convex Semi-Definite Program (SDP) in a certifiable way using Sum-of-Squares (SOS) Relaxation and show that the relaxation is tight.
The Post-impact Evolution of the X-ray Emitting Gas in SNR 1987A Viewed by XMM-Newton
In the last few years, the emission measure of the low-temperature plasma has been decreasing, indicating that the blast wave has left the main ER.
High Energy Astrophysical Phenomena
P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
The progressive learning of knowledge distillation is a two-step approach that continuously improves the performance of the student GAN and achieves better performance than single step methods.
Ranked #6 on
Anomaly Detection
on MNIST
(using extra training data)
Adaptive Operator Selection Based on Dynamic Thompson Sampling for MOEA/D
In particular, each arm of our bandit learning model represents a reproduction operator and is assigned with a prior reward distribution.
ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
The key idea is to decompose text detection into two subproblems, namely detection of text primitives and prediction of link relationships between nearby text primitive pairs.
Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
Semantic segmentation has made striking progress due to the success of deep convolutional neural networks.
Ranked #11 on
Semantic Segmentation
on EventScape
Speaker detection in the wild: Lessons learned from JSALT 2019
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios.
Audio and Speech Processing Sound
See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
However, in face of adverse conditions such as the nighttime, semantic segmentation loses its accuracy significantly.
Ranked #8 on
Semantic Segmentation
on Nighttime Driving
Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data
The challenges for this problem are two-fold: on the one hand, we have to derive a causal estimator to estimate the causal quantity from observational data, where there exists confounding bias; on the other hand, we have to deal with the identification of CATE when the distribution of covariates in treatment and control groups are imbalanced.
Solving the Empirical Bayes Normal Means Problem with Correlated Noise
The Normal Means problem plays a fundamental role in many areas of modern high-dimensional statistics, both in theory and practice.
Mask R-CNN with Pyramid Attention Network for Scene Text Detection
In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner.
Ranked #6 on
Scene Text Detection
on SCUT-CTW1500
Gradient-Free Learning Based on the Kernel and the Range Space
In this article, we show that solving the system of linear equations by manipulating the kernel and the range space is equivalent to solving the problem of least squares error approximation.
Deterministic Stretchy Regression
An extension of the regularized least-squares in which the estimation parameters are stretchable is introduced and studied in this paper.
An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
The anchor mechanism of Faster R-CNN and SSD framework is considered not effective enough to scene text detection, which can be attributed to its IoU based matching criterion between anchors and ground-truth boxes.
Bayesian $l_0$-regularized Least Squares
To illustrate our methodology, we provide simulation evidence and a real data example on the statistical properties and computational efficiency of SBR versus direct posterior sampling using spike-and-slab priors.
Constrained Maximum Correntropy Adaptive Filtering
Most existing constrained adaptive filtering algorithms are developed under mean square error (MSE) criterion, which is an ideal optimality criterion under Gaussian noises.
