Search Results for author:
Found 172 papers, 55 papers with code
Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning
Specifically, inspired by large language models (LLMs), we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space through tokenization and LLM processing, enabling zero-shot prediction across different hardware platforms for the first time.
Application of convolutional neural networks in image super-resolution
Due to strong learning abilities of convolutional neural networks (CNNs), they have become mainstream methods for image super-resolution.
Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization.
NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
This paper reviews the NTIRE 2025 Efficient Burst HDR and Restoration Challenge, which aims to advance efficient multi-frame high dynamic range (HDR) and restoration techniques.
Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition
Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action recognition (FSAR).
No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance the generation quality of diffusion transformers.
Ranked #27 on
Image Generation
on ImageNet 256x256
Vision and Intention Boost Large Language Model in Long-Term Action Anticipation
To tackle these limitations single-modality methods face, we propose a novel Intention-Conditioned Vision-Language (ICVL) model in this study that fully leverages the rich semantic information of visual data and the powerful reasoning capabilities of LLMs.
Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
We present a Gaussian Splatting method for surface reconstruction using sparse input views.
FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
The advent of Deep Neural Networks (DNNs) has driven remarkable progress in low-light image enhancement (LLIE), with diverse architectures (e. g., CNNs and Transformers) and color spaces (e. g., sRGB, HSV, HVI) yielding impressive results.
SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model
Extensive experiments on four benchmarks demonstrate that SlowFastVAD effectively combines the strengths of both fast and slow detectors, and achieves remarkable detection accuracy and interpretability with significantly reduced computational overhead, making it well-suited for real-world VAD applications with high reliability requirements.
Boosting HDR Image Reconstruction via Semantic Knowledge Transfer
Recovering High Dynamic Range (HDR) images from multiple Low Dynamic Range (LDR) images becomes challenging when the LDR images exhibit noticeable degradation and missing content.
AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation
Specifically, AxisPose constructs an Axis Generation Module (AGM) to capture the latent geometric distribution of object axes through a diffusion model.
HVI: A New color space for Low-light Image Enhancement
Low-Light Image Enhancement (LLIE) is a crucial computer vision task that aims to restore detailed visual information from corrupted low-light images.
C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation
Furthermore, we introduce a new video object interaction (VOI) dataset to evaluate the generation quality of motion controlled video generation methods.
Learning to Generalize without Bias for Open-Vocabulary Action Recognition
Leveraging the effective visual-text alignment and static generalizability from CLIP, recent video learners adopt CLIP initialization with further regularization or recombination for generalization in open-vocabulary action recognition in-context.
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD).
MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks.
Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression
To mitigate this, we propose Decoupled Feature 3D Gaussian Splatting (DF-3DGS), a novel method that decouples the color and semantic fields, thereby reducing the number of 3D Gaussians required for semantic representation.
Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
Large Vision-Language Models (LVLMs) have obtained impressive performance in visual content understanding and multi-modal reasoning.
Low-Biased General Annotated Dataset Generation
Pre-training backbone networks on a general annotated dataset (e. g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks.
Dual-Granularity Semantic Guided Sparse Routing Diffusion Model for General Pansharpening
To address the domain gap produced by varying satellite sensors and distinct scenes, we propose a dual-granularity semantic guided sparse routing diffusion model for general pansharpening.
Revisiting Generative Replay for Class Incremental Object Detection
Furthermore, we propose to use a Similarity-based Cross Sampling mechanism to select more valuable confusing data between old and new tasks to more effectively mitigate catastrophic forgetting and reduce the false alarm rate for the new task.
3D Registration in 30 Years: A Survey
3D point cloud registration is a fundamental problem in computer vision, computer graphics, robotics, remote sensing, and etc.
Unbiased General Annotated Dataset Generation
Pre-training backbone networks on a general annotated dataset (e. g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks.
Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP
Zero-shot action recognition (ZSAR) requires collaborative multi-modal spatiotemporal understanding.
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models
Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational cost poses a significant barrier to wider application.
Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component Analysis
This paper addresses the challenge of spectral-spatial feature extraction for hyperspectral image classification by introducing a novel tensor-based framework.
Hyperspectral image analysis
Hyperspectral Image Classification
+1
Sustainable Self-evolution Adversarial Training
With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security.
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
To push this paradigm toward practical applications, it is crucial for LLMs to consider tool execution costs (e. g. execution time) for tool planning.
Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution
In this work, we emphasize the infrared spectral distribution fidelity and propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain.
Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation
To facilitate adaptation while preserving data privacy, source-free domain adaptation (SFDA) and test-time adaptation (TTA) have emerged as effective paradigms, relying solely on target domain data.
UIR-LoRA: Achieving Universal Image Restoration through Multiple Low-Rank Adaptation
Inspired by the success of deep generative models and fine-tuning techniques, we proposed a universal image restoration framework based on multiple low-rank adapters (LoRA) from multi-domain transfer learning.
Frequency-Guided Spatial Adaptation for Camouflaged Object Detection
Existing adapter modules mainly care about the feature adaptation in the spatial domain.
Deep Learning for Video Anomaly Detection: A Review
Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos.
Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
In this paper, we construct a large-scale benchmark dataset for Ground-to-Aerial Video-based person Re-Identification, named G2A-VReID, which comprises 185, 907 images and 5, 576 tracklets, featuring 2, 788 distinct identities.
Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts
Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension.
3D Single-object Tracking in Point Clouds with High Temporal Variation
The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT).
Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition
Existing works in few-shot action recognition mostly fine-tune a pre-trained image model and design sophisticated temporal alignment modules at feature level.
A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap
On one hand, considering the crucial role of human-object pairs information in HOI tasks, the feature alignment module aligns the human-object pairs by aggregating instance information.
Visual Prompt Selection for In-Context Learning Segmentation
As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level.
Indoor 3D Reconstruction with an Unknown Camera-Projector Pair
Structured light-based method with a camera-projector pair (CPP) plays a vital role in indoor 3D reconstruction, especially for scenes with weak textures.
Unleashing the Potential of Open-set Noisy Samples Against Label Noise for Medical Image Classification
Addressing mixed closed-set and open-set label noise in medical image classification remains a largely unexplored challenge.
Visual Prompt Tuning in Null Space for Continual Learning
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models.
Multi-Granularity Language-Guided Multi-Object Tracking
To this end, we propose a new multi-object tracking framework, named LG-MOT, that explicitly leverages language information at different levels of granularity (scene-and instance-level) and combines it with standard visual features to obtain discriminative representations.
RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision
Multispectral object detection, utilizing both visible (RGB) and thermal infrared (T) modals, has garnered significant attention for its robust performance across diverse weather and lighting conditions.
C3L: Content Correlated Vision-Language Instruction Tuning Data Generation via Contrastive Learning
Vision-Language Instruction Tuning (VLIT) is a critical training phase for Large Vision-Language Models (LVLMs).
Dual-Modal Prompting for Sketch-Based Image Retrieval
In this study, we aim to tackle two major challenges of this task simultaneously: i) zero-shot, dealing with unseen categories, and ii) fine-grained, referring to intra-category instance-level retrieval.
The Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images.
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition
Specifically, we employ two modules for feature extraction: shared weight modules and non-shared weight modules.
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals.
Ranked #2 on
3D Reconstruction
on DTU
Generating Content for HDR Deghosting from Frequency View
To address this challenge, we propose the Low-Frequency aware Diffusion (LF-Diff) model for ghost-free HDR imaging.
A self-supervised CNN for image watermark removal
Popular convolutional neural networks mainly use paired images in a supervised way for image watermark removal.
Perceptive self-supervised learning network for noisy image watermark removal
Specifically, mentioned paired watermark images are obtained in a self supervised way, and paired noisy images (i. e., noisy and reference images) are obtained in a supervised way.
Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey
Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics.
You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement
Further, we design a novel Color and Intensity Decoupling Network (CIDNet) with two branches dedicated to processing the decoupled image brightness and color in the HVI space.
Ranked #1 on
Low-Light Image Enhancement
on LOL-v2
Low-light Image Deblurring and Enhancement
Low-Light Image Enhancement
Instance by Instance: An Iterative Framework for Multi-instance 3D Registration
Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system.
Boosting Multi-view Stereo with Late Cost Aggregation
To address this challenge, we present a late aggregation approach that allows for aggregating pairwise costs throughout the network feed-forward process, achieving accurate estimations with only minor changes of the plain CasMVSNet.
CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model
Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution.
DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution
It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable artifacts, leading to large distortion.
Open-Vocabulary Video Anomaly Detection
Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task.
Multiple Object Tracking based on Occlusion-Aware Embedding Consistency Learning
The OPM predicts occlusion information for each true detection, facilitating the selection of valid samples for consistency learning of the track's visual embedding.
Towards High-quality HDR Deghosting with Conditional Diffusion Models
To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition, consisting of the feature condition generator and the noise predictor.
Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Models
Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data.
A cross Transformer for image denoising
To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes.
Human-centric Behavior Description in Videos: New Benchmark and Model
To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7, 820 individuals.
S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning
VQA Natural Language Explanation (VQA-NLE) task aims to explain the decision-making process of VQA models in natural language.
Ground-to-Aerial Person Search: Benchmark Dataset and Approach
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31, 770 images of 260, 559 annotated bounding boxes for 2, 644 identities appearing in both of the UAVs and ground surveillance cameras.
VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection
With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task.
Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching
Recently, learning-based algorithms have achieved promising performance on cross-spectral image patch matching, which, however, is still far from satisfactory for practical application.
Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization
By decoupling the gradients of visual and audio modalities, the discriminative visual representations of sound sources can be learned with the designed Induction Vector in a bootstrap manner, which also enables the audio modality to be aligned with the visual modality consistently.
All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation
To address this issue, we propose a novel All-in-one Multi-degradation Image Restoration Network (AMIRNet) that can effectively capture and utilize accurate degradation representation for image restoration.
Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model
In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e. g., language descriptions and synchronous audios.
Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection
Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task.
VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation
Egocentric action anticipation is a challenging task that aims to make advanced predictions of future actions from current and historical observations in the first-person view.
ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
To speed up inference and further enhance the performance, our research revisits diffusion models in image super-resolution and proposes a straightforward yet significant diffusion model-based super-resolution method called ACDMSR (accelerated conditional diffusion model for image super-resolution).
A Dynamic Feature Interaction Framework for Multi-task Visual Perception
In particular, one feature merge branch is designed for instance-level recognition the other for dense predictions.
Learning from Multi-Perception Features for Real-Word Image Super-resolution
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods.
A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
At present, it is the largest semi-supervised VAD dataset with the largest number of scenes and classes of anomalies, the longest duration, and the only one considering the scene-dependent anomaly.
3D Registration with Maximal Cliques
The key insight is to loosen the previous maximum clique constraint, and mine more local consensus information in a graph for accurate pose hypotheses generation: 1) A compatibility graph is constructed to render the affinity relationship between initial correspondences.
Context-aware Style Learning and Content Recovery Networks for Neural Style Transfer
Neural text transfer aims to change the style of a text sequence while keeping its original content.
Glocal Energy-based Learning for Few-Shot Open-Set Recognition
Few-shot open-set recognition (FSOR) is a challenging task of great practical value.
Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
To let the geometric perception learned from multi-view cues in static areas propagate to the monocular representation in dynamic areas and let monocular cues enhance the representation of multi-view cost volume, we propose a cross-cue fusion (CCF) module, which includes the cross-cue attention (CCA) to encode the spatially non-local relative intra-relations from each source to enhance the representation of the other.
Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features
Instead, by mixing new and old features, old knowledge can be retained without increasing the computational complexity.
SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders
In this work, we propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR.
A Unified HDR Imaging Method with Pixel and Patch Level
The proposed HyHDRNet consists of a content alignment subnetwork and a Transformer-based fusion subnetwork.
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
Specifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles, which strengthen the tracker's robustness to motion variations and the template noise caused by the template update strategy.
Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization
Existing works in this field mainly suffer from two weaknesses: (1) They often neglect the multi-label case and only focus on temporal modeling.
PSNet: a deep learning model based digital phase shifting algorithm from a single fringe image
As the gold standard for phase retrieval, phase-shifting algorithm (PS) has been widely used in optical interferometry, fringe projection profilometry, etc.
GRAN: Ghost Residual Attention Network for Single Image Super Resolution
GRAB consists of the Ghost Module and Channel and Spatial Attention Module (CSAM) to alleviate the generation of redundant features.
New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
In all settings, the online class incremental learning (OCIL), where incoming samples from data stream can be used only once, is more challenging and can be encountered more frequently in real world.
Take a Prior from Other Tasks for Severe Blur Removal
For general scene deblurring, the feature space of the blurry image and corresponding sharp image under the high-level vision task is closer, which inspires us to rely on other tasks (e. g. classification) to learn a comprehensive prior in severe blur removal cases.
CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution
Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images.
MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions.
Revisiting Prototypical Network for Cross Domain Few-Shot Learning
Prototypical Network is a popular few-shot solver that aims at establishing a feature metric generalizable to novel few-shot classification (FSC) tasks using deep neural networks.
Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance
To enhance the discriminative power of features, we propose a batch clustering based loss to encourage a clustering branch to generate distinct normal and abnormal clusters based on a batch of data.
Generalizable Person Re-Identification via Viewpoint Alignment and Fusion
The key insight of this design is that the cross-attention mechanism in the transformer could be an ideal solution to align the discriminative texture clues from the original image with the canonical view image, which could compensate for the low-quality texture information of the canonical view image.
Domain Generalization
Generalizable Person Re-identification
+1
A Simple and Robust Correlation Filtering Method for Text-based Person Search
Text-based person search aims to associate pedestrian images with natural language descriptions.
Ranked #5 on
Text based Person Retrieval
on CUHK-PEDES
Multi-stage image denoising with the wavelet transform
In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i. e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB).
A heterogeneous group CNN for image super-resolution
To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN.
Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
For the context recovery stream, we propose a spatiotemporal U-Net which can fully utilize the motion information to predict the future frame.
Ranked #1 on
Anomaly Detection
on Corridor
Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
To make the final image feature concentrate more on the target visual concept, a Class-Aware Visual Prompt Tuning (CAVPT) scheme is further proposed in our DPT, where the class-aware visual prompt is generated dynamically by performing the cross attention between text prompts features and image patch token embeddings to encode both the downstream task-related information and visual instance information.
PC-GANs: Progressive Compensation Generative Adversarial Networks for Pan-sharpening
Most of the available deep learning-based pan-sharpening methods sharpen the multispectral images through a one-step scheme, which strongly depends on the reconstruction ability of the network.
Pansharpening via Frequency-Aware Fusion Network with Explicit Similarity Constraints
The process of fusing a high spatial resolution (HR) panchromatic (PAN) image and a low spatial resolution (LR) multispectral (MS) image to obtain an HRMS image is known as pansharpening.
SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision
Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications.
Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model
An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation.
Ranked #2 on
Face Image Quality Assessment
on CGFIQA-40k
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Exploring and Evaluating Image Restoration Potential in Dynamic Scenes
In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP).
An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection
DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved.
Audio-visual speech separation based on joint feature representation with cross-modal attention
Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments.
Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos
For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual information.
Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign
The former works only for a relatively small perturbation 8/255 with the l_\infty constraint, and GradAlign improves it by extending the perturbation size to 16/255 (with the l_\infty constraint) but at the cost of being 3 to 4 times slower.
Multi-Domain Joint Training for Person Re-Identification
Our discovery is that training with such an adaptive model can better benefit from more training samples.
Learnable Locality-Sensitive Hashing for Video Anomaly Detection
In this paper, we propose a novel distance-based VAD method to take advantage of all the available normal data efficiently and flexibly.
NAS-FCOS: Efficient Search for Object Detection Architectures
Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures.
Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance. However, different from the real-world scenarios where the bounding boxes are not available, existing text-based person retrieval methods mainly focus on the cross modal matching between the query text descriptions and the gallery of cropped pedestrian images.
Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking
To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data.
Unsupervised Video Summarization with a Convolutional Attentive Adversarial Network
Specifically, the generator employs a fully convolutional sequence network to extract global representation of a video, and an attention-based network to output normalized importance scores.
Generative Adversarial Network
Unsupervised Video Summarization
Center Prediction Loss for Re-identification
In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples.
Dynamic Image Restoration and Fusion Based on Dynamic Degradation
In addition, a dynamic degradation kernel is proposed to improve the robustness of image restoration and fusion.
Efficient Spatialtemporal Context Modeling for Action Recognition
Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition.
Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification
Learning cross-view consistent feature representation is the key for accurate vehicle Re-identification (ReID), since the visual appearance of vehicles changes significantly under different viewpoints.
Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance
While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered.
Non-uniform Motion Deblurring with Blurry Component Divided Guidance
To tackle the above problems, we present a deep two-branch network to deal with blurry images via a component divided module, which divides an image into two components based on the representation of blurry degree.
Towards Accurate Camouflaged Object Detection with Mixture Convolution and Interactive Fusion
Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context information from a large receptive field.
Semantic-Guided Representation Enhancement for Self-supervised Monocular Trained Depth Estimation
Based on this framework, we enhance the local feature representation by sampling and feeding the point-based features that locate on the semantic edges to an individual Semantic-guided Edge Enhancement module (SEEM), which is specifically designed for promoting depth estimation on the challenging semantic borders.
Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution
One of the main reason comes from the fact that the predefined degeneration models (e. g. blur in spatial domain) utilized by most HSI SR methods often exist great discrepancy with the real one, which results in these deep models overfit and ultimately degrade their performance on real data.
Meta-Generating Deep Attentive Metric for Few-shot Classification
To mitigate this problem, we present a novel deep metric meta-generation method that turns to an orthogonal direction, ie, learning to adaptively generate a specific metric for a new FSL task based on the task description (eg, a few labelled samples).
On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration
This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration.
Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network
Fashion products typically feature in compositions of a variety of styles at different clothing parts.
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application.
AE-Netv2: Optimization of Image Fusion Efficiency and Network Architecture
Finally, we explore the commonness and characteristics of different image fusion tasks, which provides a research basis for further research on the continuous learning characteristics of human brain in the field of image fusion.
3D Correspondence Grouping with Compatibility Features
We present a simple yet effective method for 3D correspondence grouping.
AE-Net: Autonomous Evolution Image Fusion Method Inspired by Human Cognitive Mechanism
Firstly, the relationship between human brain cognitive mechanism and image fusion task is analyzed and a physical model is established to simulate human brain cognitive mechanism.
IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality
This paper presents an illumination estimation method for virtual objects in real environment by learning.
A Robust Attentional Framework for License Plate Recognition in the Wild
On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly.
Attention-based network for low-light image enhancement
Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.
Learning to Compare Relation: Semantic Alignment for Few-Shot Learning
First, we introduce a semantic alignment loss to align the relation statistics of the features from samples that belong to the same category.
Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs.
Cross-Modal Image Fusion Theory Guided by Subjective Visual Attention
In order to improve the robustness and contextual awareness of image fusion tasks, we proposed a multi-task auxiliary learning image fusion theory guided by subjective attention.
Non-linear and Selective Fusion of Cross-Modal Images
The human visual perception system has strong robustness in image fusion.
A Cross-Modal Image Fusion Method Guided by Human Visual Characteristics
The characteristics of feature selection, nonlinear combination and multi-task auxiliary learning mechanism of the human visual perception system play an important role in real-world scenarios, but the research of image fusion theory based on the characteristics of human visual perception is less.
Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation
The problem of cross-modality person re-identification has been receiving increasing attention recently, due to its practical significance.
Cross-Modality Person Re-identification
Person Re-Identification
Person Re-identification in Aerial Imagery
Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching
Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision.
Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching
The outcomes present interesting findings that may shed new light on this community and provide complementary perspectives to existing evaluations on the topic of local geometric feature description.
NAS-FCOS: Fast Neural Architecture Search for Object Detection
The success of deep neural networks relies on significant architecture engineering.
Ranked #129 on
Object Detection
on COCO test-dev
Attention-guided Network for Ghost-free High Dynamic Range Imaging
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
A Holistic Representation Guided Attention Network for Scene Text Recognition
In this work, we propose a simple yet strong approach for scene text recognition.
Vehicle Re-identification in Aerial Imagery: Dataset and Approach
It is capable of explicitly detecting discriminative parts for each specific vehicle and significantly outperforms the evaluated baselines and state-of-the-art vehicle ReID approaches.
Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution
To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks.
MPTV: Matching Pursuit Based Total Variation Minimization for Image Deconvolution
Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization.
A Pulmonary Nodule Detection Model Based on Progressive Resolution and Hierarchical Saliency
Detection of pulmonary nodules on chest CT is an essential step in the early diagnosis of lung cancer, which is critical for best patient care.
Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain.
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network
In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.
Learning Deep Gradient Descent Optimization for Image Deconvolution
Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.
Significantly Fast and Robust Fuzzy C-MeansClustering Algorithm Based on MorphologicalReconstruction and Membership Filtering
However, the introduction oflocal spatial information often leads to a high computationalcomplexity, arising out of an iterative calculation of the distancebetween pixels within local spatial neighbors and clusteringcenters.
Self-Paced Kernel Estimation for Robust Blind Image Deblurring
Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process.
Beyond Low Rank: A Data-Adaptive Tensor Completion Method
The prior for the non-low-rank structure is established based on a mixture of Gaussians which is shown to be flexible enough, and powerful enough, to inform the completion process for a variety of real tensor data.
From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
Tensor Power Iteration for Multi-Graph Matching
Due to its wide range of applications, matching between two graphs has been extensively studied and remains an active topic.
Blind Image Deconvolution by Automatic Gradient Activation
We show here that a subset of the image gradients are adequate to estimate the blur kernel robustly, no matter the gradient image is sparse or not.
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
Feature matching is a key problem in computer vision and pattern recognition.
Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior
To reconstruct hyperspectral image (HSI) accurately from a few noisy compressive measurements, we present a novel manifold-structured sparsity prior based hyperspectral compressive sensing (HCS) method in this study.
Modeling Deformable Gradient Compositions for Single-Image Super-Resolution
Based on the fact that singular primitive patches are more invariant to the scale change (i. e. have less ambiguity across different scales), we represent the non-singular primitives as compositions of singular ones, each of which is allowed some deformation.
Reweighted Laplace Prior Based Hyperspectral Compressive Sensing for Unknown Sparsity
To address this problem, a novel reweighted Laplace prior based hyperspectral compressive sensing method is proposed in this study.
Single Image Super-resolution using Deformable Patches
We proposed a deformable patches based method for single image super-resolution.
Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations
We show that using Marginal Polytope Diagrams allows the number of constraints to be reduced without loosening the LP relaxations.
Part-Based Visual Tracking with Online Latent Structural Learning
Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking.
Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
This paper presents a robust algorithm for estimating a single latent sharp image given multiple blurry and/or noisy observations.
