Search Results for author:
Found 48 papers, 20 papers with code
Matting by Generation
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge.
The SkatingVerse Workshop & Challenge: Methods and Results
The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding.
TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content
Our proposed approach achieves an IOU of 0. 96 and an OCR Accuracy of 78%, showcasing a remarkable improvement of approximately 25% in the OCR Accuracy compared to the previous Table Transformer approach.
RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization
To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain.
The Effects of Short Video-Sharing Services on Video Copy Detection
From the experimental results focusing on segment-level and video-level situations, we can see that three effects: "Segment-level VCD in short video-sharing services is more difficult than those in general video-sharing services", "Video-level VCD in short video-sharing services is easier than those in general video-sharing services", "The video alignment component mainly suppress the detection performance in short video-sharing services".
Contributing Dimension Structure of Deep Feature for Coreset Selection
Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm.
Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval
2) Multi-perspective and multi-style.
TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting
For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature.
Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser
However, these methods suffer from high model variance with low performance on high-dimensional datasets due to the ineffective design of the denoiser and are limited in their utilization of ZO techniques.
Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
Human evaluation is critical for validating the performance of text-to-image generative models, as this highly cognitive process requires deep comprehension of text and images.
DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
Close-up facial images captured at short distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances.
Single Image Deblurring with Row-dependent Blur Magnitude
Image degradation often occurs during fast camera or object movements, regardless of the exposure modes: global shutter (GS) or rolling shutter (RS).
HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design
Adversarial attacks on thermal infrared imaging expose the risk of related applications.
Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning
However, this type of method normally ignores the crucial knowledge hidden in the data (e. g., intra-class information variation), which is harmful to the generalization of the trained model.
Multiple Object Tracking from appearance by hierarchically clustering tracklets
Current approaches in Multiple Object Tracking (MOT) rely on the spatio-temporal coherence between detections combined with object appearance to match objects from consecutive frames.
Ranked #13 on
Multi-Object Tracking
on MOT17
Physical Adversarial Attack meets Computer Vision: A Decade Survey
Building upon this foundation, we uncover the pervasive role of artifacts carrying adversarial perturbations in the physical world.
Reference-Guided Texture and Structure Inference for Image Inpainting
Existing learning-based image inpainting methods are still in challenge when facing complex semantic environments and diverse hole patterns.
Improving Generalization of Metric Learning via Listwise Self-distillation
Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones.
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion
Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme.
Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks.
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature
In this paper, we investigate using rolling shutter with a global reset feature (RSGR) to restore clean global shutter (GS) videos.
Optimal Correction Cost for Object Detection Evaluation
OC-cost computes the cost of correcting detections to ground truths as a measure of accuracy.
Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
This framework consists of three key components, i. e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module.
Scalable Personalised Item Ranking through Parametric Density Estimation
However, such methods have two main drawbacks particularly in large-scale applications; (1) the pairwise approach is severely inefficient due to the quadratic computational cost; and (2) even recent model-based samplers (e. g. IRGAN) cannot achieve practical efficiency due to the training of an extra model.
Density-Ratio Based Personalised Ranking from Implicit Feedback
Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones.
Image Inpainting Guided by Coherence Priors of Semantics and Textures
In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner.
Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph
Solving cold-start problems is indispensable to provide meaningful recommendation results for new users and items.
Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.
Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge.
GAN-based Multiple Adjacent Brain MRI Slice Reconstruction for Unsupervised Alzheimer's Disease Diagnosis
Unsupervised learning can discover various unseen diseases, relying on large-scale unannotated medical images of healthy subjects.
Generative Adversarial Network
Unsupervised Anomaly Detection
Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification
An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis.
DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning
To gain the superiority of deep learning models, we treat a group as multiple persons and transfer the domain of a labeled ReID dataset to a G-ReID target dataset style to learn single representations.
Illumination-Adaptive Person Re-identification
To demonstrate the illumination issue and to evaluate our model, we construct two large-scale simulated datasets with a wide range of illumination variations.
Learning More with Less: GAN-based Medical Image Augmentation
Convolutional Neural Network (CNN)-based accurate prediction typically requires large-scale annotated training data.
Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
Accurate Computer-Assisted Diagnosis, associated with proper data wrangling, can alleviate the risk of overlooking the diagnosis in a clinical environment.
Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years.
Ranked #1 on
Image Retrieval
on Par6k
Reconfigurable Inverted Index
Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system.
Harnessing AI for Speech Reconstruction using Multi-view Silent Video Feed
Recently, research has started venturing into generating (audio) speech from silent video sequences but there have been no developments thus far in dealing with divergent views and poses of a speaker.
Sound Audio and Speech Processing
Digital Watermarking for Deep Neural Networks
In this paper, we propose a digital watermarking technology for ownership authorization of deep neural networks.
Consensus-based Sequence Training for Video Captioning
First we show that, by replacing model samples with ground-truth sentences, RL training can be seen as a form of weighted cross-entropy loss, giving a fast, RL-based pre-training algorithm.
Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation
The proposed method can retrieve and localize objects specified by a textual query from one million images in only 0. 5 seconds with high precision.
Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge
Although convolutional neural networks (CNNs) have achieved promising results in learning such concepts, it remains an open question as to how to effectively use CNNs for abnormal event detection, mainly due to the environment-dependent nature of the anomaly detection.
Region-Based Image Retrieval Revisited
Second, to help users specify spatial relationships among objects in an intuitive way, we propose recommendation techniques of spatial relationships.
Embedding Watermarks into Deep Neural Networks
Secondly, we propose a general framework to embed a watermark into model parameters using a parameter regularizer.
Adaptive Substring Extraction and Modified Local NBNN Scoring for Binary Feature-based Local Mobile Visual Search without False Positives
In this paper, we propose a stand-alone mobile visual search system based on binary features and the bag-of-visual words framework.
Image Retrieval with Fisher Vectors of Binary Features
Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval.
Faster R-CNN Features for Instance Search
This work explores the suitability for instance retrieval of image- and region-wise representations pooled from an object detection CNN such as Faster R-CNN.
Generalized Lasso based Approximation of Sparse Coding for Visual Recognition
Sparse coding, a method of explaining sensory data with as few dictionary bases as possible, has attracted much attention in computer vision.
