Search Results for author:
Found 149 papers, 61 papers with code
Manifold Projection for Adversarial Defense on Face Recognition
We utilize variational autoencoder (VAE) to estimate the lower bound of the log-likelihood of image and explore to project the input images back into the high probability regions of image manifold again.
MoiréXNet: Adaptive Multi-Scale Demoiréing with Linear Attention Test-Time Training and Truncated Flow Matching Prior
This stems from constrained model capacity and scarce training data, which inadequately represent the clean image distribution and hinder accurate reconstruction of ground-truth images.
PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning
Federated Learning (FL) has emerged as a powerful paradigm for leveraging diverse datasets from multiple sources while preserving data privacy by avoiding centralized storage.
Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph.
KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Our results on KRAMABENCH show that, although the models are sufficiently capable of solving well-specified data science code generation tasks, when extensive data processing and domain knowledge are required to construct real-world data science pipelines, existing out-of-box models fall short.
Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification
Gradient-based adversarial attacks have become a dominant approach for evaluating the robustness of point cloud classification models.
FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods suffer from quantization loss, leading to compromised speaker similarity and intelligibility, while diffusion models require complex training and high inference latency.
Reinforcement Learning from User Feedback
We train a reward model, P[Love], to predict the likelihood that an LLM response will receive a Love Reaction, a lightweight form of positive user feedback, and integrate P[Love] into a multi-objective policy optimization framework alongside helpfulness and safety objectives.
VR-RAG: Open-vocabulary Species Recognition with RAG-Assisted Large Multi-Modal Models
In this work, we focus on open-vocabulary bird species recognition, where the goal is to classify species based on their descriptions without being constrained to a predefined set of taxonomic categories.
Kimi-Audio Technical Report
We release the codes, model checkpoints, as well as the evaluation toolkits in https://github. com/MoonshotAI/Kimi-Audio.
Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space
We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure.
NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025.
Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors.
Retinex-guided Histogram Transformer for Mask-free Shadow Removal
While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes.
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images.
Multimodal Image Matching based on Frequency-domain Information of Local Energy Response
The core of FILER is the local energy response model based on frequency-domain information, which can overcome the effect of nonlinear intensity differences.
WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation
In this work, we introduce WikiAutoGen, a novel system for automated multimodal Wikipedia-style article generation.
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities.
DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning
Multimodal learning integrates complementary information from diverse modalities to enhance the decision-making process.
Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices
Optimal transport has found widespread applications in signal processing and machine learning.
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
In this paper, we introduce LLaSE-G1, a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions.
Hyperbolic Binary Neural Network
Specifically, we transform the constrained problem in hyperbolic space into an unconstrained one in Euclidean space using the Riemannian exponential map.
LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors
Directly employing 3D Gaussian Splatting (3DGS) on images with adverse illumination conditions exhibits considerable difficulty in achieving high-quality normally-exposed representation due to: (1) The limited Structure from Motion (SfM) points estimated in adverse illumination scenarios fail to capture sufficient scene details; (2) Without ground-truth references, the intensive information loss, huge noise, and color distortion poses substantial challenges for 3DGS to produce high-quality results; (3) Combining existing exposure correction methods with 3DGS can not achieve satisfactory performance due to their individual enhancement process, which leads to the illumination inconsistency between enhanced images from different viewpoints.
Low-Light Image Enhancement via Generative Perceptual Priors
Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying current Low-Light Image Enhancement (LLIE) methods to real-world scenarios, primarily due to the diverse illumination conditions encountered.
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning over a large number of images.
Landing Trajectory Prediction for UAS Based on Generative Adversarial Network
The GAN consists of one neural network generator and a neural network discriminator.
Minimum Entropy Coupling with Bottleneck
This paper investigates a novel lossy compression framework operating under logarithmic loss, designed to handle situations where the reconstruction distribution diverges from the source distribution.
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
Inspired by Mamba which demonstrates powerful and highly efficient sequence modeling, we introduce a novel framework based on Mamba for Exposure Correction (ECMamba) with dual pathways, each dedicated to the restoration of reflectance and illumination map, respectively.
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance.
Data-driven Probabilistic Trajectory Learning with High Temporal Resolution in Terminal Airspace
Predicting flight trajectories is a research area that holds significant merit.
On the Convergence of Sigmoid and tanh Fuzzy General Grey Cognitive Maps
By comparing with the convergence theorems of FCM and FGCM, the effectiveness of the theorems proposed in this paper was verified.
Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization
This paper investigates the best known bounds on the quadratic Gaussian distortion-rate-perception function with limited common randomness for the Kullback-Leibler divergence-based perception measure, as well as their counterparts for the squared Wasserstein-2 distance-based perception measure, recently established by Xie et al.
Cross-subject Brain Functional Connectivity Analysis for Multi-task Cognitive State Evaluation
Accordingly, this study adopts brain functional connectivity with electroencephalography signals to capture associations in brain regions across multiple subjects for evaluating real-time cognitive states.
Improving Retrieval Augmented Language Model with Self-Reasoning
The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models (LLMs).
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval
Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides.
Ranked #2 on
Low-Light Image Enhancement
on LOLv2
MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis
Our empirical assessments confirm MiniGPT-Med's superior performance in disease grounding, medical report generation, and VQA benchmarks, representing a significant step towards reducing the gap in assisting radiology practice.
Timestep-Aware Correction for Quantized Diffusion Models
This accumulation of error becomes particularly problematic in low-precision scenarios, leading to significant distortions in the generated images.
Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time
Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio.
Ranked #1 on
AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)
on MUSIC-AVQA v2.0
(using extra training data)
AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)
Fact Checking
+4
DehazeDCT: Towards Effective Non-Homogeneous Dehazing via Deformable Convolutional Transformer
Image dehazing, a pivotal task in low-level vision, aims to restore the visibility and detail from hazy images.
Ranked #1 on
Nonhomogeneous Image Dehazing
on DNH-HAZE
An Introduction to Vision-Language Modeling
Then, we present and discuss approaches to evaluate VLMs.
EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations
Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world.
Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results.
ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer
Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems.
Ranked #1 on
Shadow Removal
on WSRD+
GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models
In this paper, we introduce GoodDrag, a novel approach to improve the stability and image quality of drag editing.
Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory
The distortion-rate function of output-constrained lossy source coding with limited common randomness is analyzed for the special case of squared error distortion measure.
AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction
AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network.
Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift
When applied to RF fingerprinting, our model treats RF signals from the same transmission as positive pairs and those from different transmissions as negative pairs.
SPAR: Personalized Content-Based Recommendation via Long Engagement Attention
Leveraging users' long engagement histories is essential for personalized content recommendations.
SCNet: Sparse Compression Network for Music Source Separation
We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information.
Ranked #3 on
Music Source Separation
on MUSDB18-HQ
Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure
The perception measure is based on a divergence between the distributions of the source and reconstruction sequences \emph{conditioned} on the encoder output, first proposed by Mentzer et al. We consider the case when there is no shared randomness between the encoder and the decoder and derive a single-letter characterization of the RDP function for the case of discrete memoryless sources.
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability.
Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation
Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention.
Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised visible-infrared person re-identification (US-VI-ReID) centers on learning a cross-modality retrieval model without labels reducing the reliance on expensive cross-modality manual annotation.
Learnable Chamfer Distance for Point Cloud Reconstruction
As point clouds are 3D signals with permutation invariance, most existing works train their reconstruction networks by measuring shape differences with the average point-to-point distance between point clouds matched with predefined rules.
SimCalib: Graph Neural Network Calibration based on Similarity between Nodes
A novel calibration framework, named SimCalib, is accordingly proposed to consider similarity between nodes at global and local levels.
Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations
This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models.
CR-SFP: Learning Consistent Representation for Soft Filter Pruning
In this paper, we propose to mitigate this gap by learning consistent representation for soft filter pruning, dubbed as CR-SFP.
HB-net: Holistic bursting cell cluster integrated network for occluded multi-objects recognition
Although in high-noise settings, standard CNNs exhibit slightly greater robustness when compared to HB-net models, the models that combine the HB framework and EA mechanism achieve a comparable level of accuracy and resilience to ResNet50, despite having only three convolutional layers and approximately $1/30$ of the parameters.
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others.
SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration
To overcome them, this paper proposes a novel \emph{\textbf{S}oft \textbf{U}niform \textbf{B}lock \textbf{P}runing} (SUBP) approach to train a uniform 1$\times$N sparse structured network from scratch.
Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold.
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning
Therefore, a few data-free methods are proposed to address this problem, but they perform data-free pruning and quantization separately, which does not explore the complementarity of pruning and quantization.
A Weakly Supervised Segmentation Network Embedding Cross-scale Attention Guidance and Noise-sensitive Constraint for Detecting Tertiary Lymphoid Structures of Pancreatic Tumors
The presence of tertiary lymphoid structures (TLSs) on pancreatic pathological images is an important prognostic indicator of pancreatic tumors.
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
In this paper, we propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process.
Impacts of seasonality and parasitism on honey bee population dynamics
The honeybee plays an extremely important role in ecosystem stability and diversity and in the production of bee pollinated crops.
Exploring Open-Vocabulary Semantic Segmentation without Human Labels
Although acquired extensive knowledge of visual concepts, it is non-trivial to exploit knowledge from these VL models to the task of semantic segmentation, as they are usually trained at an image level.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+3
MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding
Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function.
Learning Global-aware Kernel for Image Harmonization
To address this issue, we propose a novel Global-aware Kernel Network (GKNet) to harmonize local regions with comprehensive consideration of long-distance background references.
Ranked #5 on
Image Harmonization
on iHarmony4
Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt
To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model.
SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge
Stereo Image Super-Resolution (stereoSR) has attracted significant attention in recent years due to the extensive deployment of dual cameras in mobile phones, autonomous vehicles and robots.
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Our work, for the first time, uncovers that properly aligning the visual features with an advanced large language model can possess numerous advanced multi-modal abilities demonstrated by GPT-4, such as detailed image description generation and website creation from hand-drawn drafts.
Ranked #3 on
Visual Question Answering (VQA)
on AutoHallusion
LLM as A Robotic Brain: Unifying Egocentric Memory and Control
In this paper, we propose a novel and generalizable framework called LLM-Brain: using Large-scale Language Model as a robotic brain to unify egocentric memory and control.
A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer
Although it is possible to augment the NH-HAZE23 dataset by leveraging other non-homogeneous dehazing datasets, we observe that it is necessary to design a proper data-preprocessing approach that reduces the distribution gaps between the target dataset and the augmented one.
Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions
Video captioning aims to convey dynamic scenes from videos using natural language, facilitating the understanding of spatiotemporal information within our environment.
Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank
Despite the remarkable achievement of recent underwater image restoration techniques, the lack of labeled data has become a major hurdle for further progress.
TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge
This paper introduces the Unbeatable Team's submission to the ICASSP 2023 Deep Noise Suppression (DNS) Challenge.
ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions
By keeping acquiring new visual information from BLIP-2's answers, ChatCaptioner is able to generate more enriched image descriptions.
On the Stability and Generalization of Triplet Learning
Triplet learning, i. e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e. g., face recognition and person re-identification.
Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have shown empirical effectiveness on feature selection, ranking and recommendation tasks.
Learning Discretized Neural Networks under Ricci Flow
By introducing a partial differential equation on metrics, i. e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the $L^2$-norm perturbation.
M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion
This paper proposes ``\emph{${\bf M}$-magnitude weighted $L_{\bf 2}$ distortion + $\bf 2$ degrees of freedom''} (M22) algorithm, a rate-distortion inspired approach to gradient compression for federated training of deep neural networks (DNNs).
Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification
The grand unified representation lies in two aspects: 1) GUR adopts a bottom-up domain learning strategy with a cross-memory association embedding module to explore the information of hierarchical domains, i. e., intra-camera, inter-camera, and inter-modality domains, learning a unified and robust representation against hierarchical discrepancy.
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only
Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+3
HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Entertainment-oriented singing voice synthesis (SVS) requires a vocoder to generate high-fidelity (e. g. 48kHz) audio.
Augmented Dual-Contrastive Aggregation Learning for Unsupervised Visible-Infrared Person Re-Identification
Visible infrared person re-identification (VI-ReID) aims at searching out the corresponding infrared (visible) images from a gallery set captured by other spectrum cameras.
Progressive with Purpose: Guiding Progressive Inpainting DNNs through Context and Structure
Stacking GLE modules enables the network to extract image features from different image frequency components.
SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Gonadotrophin-releasing hormone receptor (GnRH1R) is a promising therapeutic target for the treatment of uterine diseases.
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
In this paper, we show through empirical results that adopting the data replay is surprisingly favorable.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
After finetuning the pretrained LoMaR on 384$\times$384 images, it can reach 85. 4% top-1 accuracy, surpassing MAE by 0. 6%.
Privacy-Preserving Data-Enabled Predictive Leading Cruise Control in Mixed Traffic
Data-driven predictive control of connected and automated vehicles (CAVs) has received increasing attention as it can achieve safe and optimal control without relying on explicit dynamical models.
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.
FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Previously proposed FullSubNet has achieved outstanding performance in Deep Noise Suppression (DNS) Challenge and attracted much attention.
A Unified Framework for Campaign Performance Forecasting in Online Display Advertising
Advertisers usually enjoy the flexibility to choose criteria like target audience, geographic area and bid price when planning an campaign for online display advertising, while they lack forecast information on campaign performance to optimize delivery strategies in advance, resulting in a waste of labour and budget for feedback adjustments.
An Analysis of Complex-Valued CNNs for RF Data-Driven Wireless Device Classification
We perform a deep dive into understanding the impact of (i) the input representation/type and (ii) the architectural layer of the neural network.
CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval
We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of tasks, including Multimodal Categorization, Image-Text Retrieval, Query-to-Product Retrieval, Image-to-Product Retrieval, etc.
Towards Multi-Domain Single Image Dehazing via Test-Time Training
Motivated by this observation, we propose a test-time training method which leverages a helper network to assist the dehazing model in better adapting to a domain of interest.
Dynamically Stable Poincaré Embeddings for Neural Manifolds
As a result, we prove that, if initial metrics have an $L^2$-norm perturbation which deviates from the Hyperbolic metric on the Poincar\'e ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric.
Video Frame Interpolation Transformer
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field.
Thoughts on the Consistency between Ricci Flow and Neural Network Behavior
During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.
whu-nercms at trecvid2021:instance search task
We will make a brief introduction of the experimental methods and results of the WHU-NERCMS in the TRECVID2021 in the paper.
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network
Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress.
Cross-Domain Lossy Compression as Optimal Transport with an Entropy Bottleneck
We study the problem of cross-domain lossy compression where the reconstruction distribution is different from the source distribution in order to account for distributional shift due to processing.
Manifold Micro-Surgery with Linearly Nearly Euclidean Metrics
The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular.
Riemannian Manifold Embeddings for Straight-Through Estimator
Quantized Neural Networks (QNNs) aim at replacing full-precision weights $\boldsymbol{W}$ with quantized weights $\boldsymbol{\hat{W}}$, which make it possible to deploy large models to mobile and miniaturized devices easily.
Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
For the inter-domain learning, a consistency constraint is applied to the LAs modelled by two dual-modelling networks to exploit the complementary knowledge among different data domains.
Universal Rate-Distortion-Perception Representations for Lossy Compression
In the context of lossy compression, Blau & Michaeli (2019) adopt a mathematical notion of perceptual quality and define the information rate-distortion-perception function, generalizing the classical rate-distortion tradeoff.
JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets
In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way.
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning
Recently, there has been rapid and significant progress on image dehazing.
DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing
By utilizing wavelet transform in DWT branch, our proposed method can retain more high-frequency knowledge in feature maps.
Bayesian Optimisation for a Biologically Inspired Population Neural Network
The 8-dimensional optimal hyper-parameter combination should be such that the network dynamics simulate the resting state alpha rhythm (8 - 13 Hz rhythms in brain signals).
Towards a Unified Approach to Single Image Deraining and Dehazing
We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuous limit.
GridDehazeNet+: An Enhanced Multi-Scale Network with Intra-Task Knowledge Transfer for Single Image Dehazing
We also propose a novel intra-task knowledge transfer mechanism that can memorize and take advantage of synthetic domain knowledge to assist the learning process on the translated data.
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization
To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and localize image manipulations.
Learning for Unconstrained Space-Time Video Super-Resolution
Recent years have seen considerable research activities devoted to video enhancement that simultaneously increases temporal frame rate and spatial resolution.
Optical Flow Estimation
Space-time Video Super-resolution
+2
VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning
To the best of our knowledge, this is the first work that improves data efficiency of image captioning by utilizing LM pretrained on unimodal data.
The configuration and failed eruption of a complex magnetic flux rope above a δ sunspot region
A null point is located above the flux rope.
Solar and Stellar Astrophysics Space Physics
Indirect Domain Shift for Single Image Dehazing
Therefore, it is capable of consolidating the expressibility of different architectures, resulting in a more accurate indirect domain shift (IDS) from the hazy images to that of clear images.
Edge-Featured Graph Attention Network
In this paper, we present edge-featured graph attention networks, namely EGATs, to extend the use of graph neural networks to those tasks learning on graphs with both node and edge features.
Optimizing Quantized Neural Networks with Natural Gradient
Quantized Neural Networks (QNNs) have achieved an enormous step in improving computational efficiency, making it possible to deploy large models to mobile and miniaturized devices.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment
Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio.
Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation
Then, the key is to capture the temporal evolution of node pair (term pair) relations from just the positive and unlabeled data.
Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference
Extensive experiments demonstrate that owing to the informativeness of the camera raw data, the effectiveness of the network architecture, and the separation of super-resolution and color correction processes, the proposed method achieves superior VSR results compared to the state-of-the-art and can be adapted to any specific camera-ISP.
Video Frame Interpolation via Generalized Deformable Convolution
Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies.
AWNet: Attentive Wavelet Network for Image ISP
In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem.
Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs
The automatic text-based diagnosis remains a challenging task for clinical use because it requires appropriate balance between accuracy and interpretability.
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
Efficient long-distance relation extraction with DG-SpanBERT
In natural language processing, relation extraction seeks to rationally understand unstructured text.
Ranked #17 on
Relation Extraction
on TACRED
A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
Furthermore, we also design a shift vector processing element (SVPE) array to replace all 16-bit multiplications with SHIFT operations in convolution operation on FPGAs.
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
Meanwhile, we propose a M-bit Inputs and N-bit Weights Network (MINW-Net) trained by AQE, a quantized neural network with 1-3 bits weights and activations.
Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attention
Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently (~0. 27 seconds to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices).
End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation
Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart.
Highly fluorescent copper nanoclusters for sensing and bioimaging
Metal nanoclusters (NCs), typically consisting of a few to tens of metal atoms, bridge the gap between organometallic compounds and crystalline metal nanoparticles.
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
The proposed hazing method does not rely on the atmosphere scattering model, and we provide an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model for image dehazing, even if only the dehazing results on synthetic images are concerned.
Ranked #4 on
Image Dehazing
on RS-Haze
Discriminative Consistent Domain Generation for Semi-supervised Learning
Based on the generated discriminative consistent domain, we can use the unlabeled data to learn the task model along with the labeled data via a consistent image generation.
A Fast Free-viewpoint Video Synthesis Algorithm for Sports Scenes
In this paper, we report on a parallel freeviewpoint video synthesis algorithm that can efficiently reconstruct a high-quality 3D scene representation of sports scenes.
Generic Model-Agnostic Convolutional Neural Network for Single Image Dehazing
Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis.
Ranked #24 on
Image Dehazing
on SOTS Outdoor
Keyphrase Generation with Correlation Constraints
In this paper, we study automatic keyphrase generation.
Action Recognition for Depth Video using Multi-view Dynamic Images
To better exploit three-dimensional (3D) characteristics, multi-view dynamic images are proposed.
Multiview Two-Task Recursive Attention Model for Left Atrium and Atrial Scars Segmentation
Late Gadolinium Enhanced Cardiac MRI (LGE-CMRI) for detecting atrial scars in atrial fibrillation (AF) patients has recently emerged as a promising technique to stratify patients, guide ablation therapy and predict treatment success.
Efficient Parallel Connected Components Labeling with a Coarse-to-fine Strategy
This paper proposes a new parallel approach to solve connected components on a 2D binary image implemented with CUDA.
Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects
Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map.
An Optimized Union-Find Algorithm for Connected Components Labeling Using GPUs
In this paper, we report an optimized union-find (UF) algorithm that can label the connected components on a 2D image efficiently by employing the GPU architecture.
A straightforward method to assess motion blur for different types of displays
A simulation method based on the liquid crystal response and the human visual system is suitable to characterize motion blur for LCDs but not other display types.
