Search Results for author:
Found 36 papers, 12 papers with code
A Novel Line Integral Transform for 2D Affine-Invariant Shape Retrieval
While conducting the trace transform once only generates a single feature and multiple trace transforms of different functionals are needed to derive more to make the descriptors informative.
EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles
A major challenge in SFDA is deriving accurate categorical information for the target domain, especially when sample embeddings from different classes appear similar.
Fine-Grained Visual Categorization
Source-Free Domain Adaptation
SpectralKAN: Kolmogorov-Arnold Network for Hyperspectral Images Change Detection
In this paper, we propose an spectral Kolmogorov-Arnold Network for HSIs-CD (SpectralKAN).
CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks
Inspired by geographical analysis, the proposed CSA exploits the spatial relationships between channels of feature maps to produce an effective channel descriptor.
Towards Temporally Consistent Referring Video Object Segmentation
Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects.
Ranked #3 on
Referring Expression Segmentation
on DAVIS 2017 (val)
(using extra training data)
A Language Model based Framework for New Concept Placement in Ontologies
In all steps, we propose to leverage neural methods, where we apply embedding-based methods and contrastive learning with Pre-trained Language Models (PLMs) such as BERT for edge search, and adapt a BERT fine-tuning-based multi-label Edge-Cross-encoder, and Large Language Models (LLMs) such as GPT series, FLAN-T5, and Llama 2, for edge selection.
Hy-Tracker: A Novel Framework for Enhancing Efficiency and Accuracy of Object Tracking in Hyperspectral Videos
Hyperspectral object tracking has recently emerged as a topic of great interest in the remote sensing community.
Spectrum-guided Multi-granularity Referring Video Object Segmentation
To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks.
Ranked #1 on
Referring Expression Segmentation
on J-HMDB
(using extra training data)
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
However, all the CAM-based methods (e. g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier.
Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval
Fine-grained leaf image retrieval (FGLIR) aims to search similar leaf images in subspecies level which involves very high interclass visual similarity and accordingly poses great challenges to leaf image description.
Region Aware Video Object Segmentation with Deep Motion Modeling
Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory.
Ranked #16 on
Semi-Supervised Video Object Segmentation
on DAVIS 2017 (val)
(using extra training data)
Imitation of Manipulation Skills Using Multiple Geometries
Daily manipulation tasks are characterized by geometric primitives related to actions and object shapes.
A Compositional Feature Embedding and Similarity Metric for Ultra-Fine-Grained Visual Categorization
Motivated by these issues, this paper proposes a novel compositional feature embedding and similarity metric (CECS).
Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization
The advantage of the proposed method is that the feature detection and extraction model only requires a small amount of target region samples with bounding boxes for training, then it can automatically locate the target area for a large number of images in the dataset at a high detection accuracy.
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation.
Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
We verify the effectiveness of FFVT on three benchmarks where FFVT achieves the state-of-the-art performance.
Ranked #6 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Categorization
EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation
The precise detection of blood vessels in retinal images is crucial to the early diagnosis of the retinal vascular diseases, e. g., diabetic, hypertensive and solar retinopathies.
Image Feature Information Extraction for Interest Point Detection: A Review
The existing popular datasets and evaluation standards are provided and the performances for eighteen state-of-the-art approaches are evaluated and discussed.
NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification
Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples.
Mask Guided Attention For Fine-Grained Patchy Image Classification
Specifically, the proposed MGA integrates a pre-trained semantic segmentation model that produces auxiliary supervision signal, i. e., patchy attention mask, enabling a discriminative representation learning.
Benchmark Platform for Ultra-Fine-Grained Visual Categorization Beyond Human Performance
The proposed UFG image dataset and evaluation protocols is intended to serve as a benchmark platform that can advance research of visual classification from approaching human performance to beyond human ability, via facilitating benchmark data of artificial intelligence (AI) not to be limited by the labels of human intelligence (HI).
Multi-layer Feature Aggregation for Deep Scene Parsing Models
The proposed module can auto-select the intermediate visual features to correlate the spatial and semantic information.
Ranked #51 on
Semantic Segmentation
on NYU Depth v2
Parameter Efficient Deep Neural Networks with Bilinear Projections
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy.
Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy
Traditional tensor decomposition methods, e. g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers.
A Robust Matching Pursuit Algorithm Using Information Theoretic Learning
Current orthogonal matching pursuit (OMP) algorithms calculate the correlation between two vectors using the inner product operation and minimize the mean square error, which are both suboptimal when there are non-Gaussian noises or outliers in the observation data.
A Unified Weight Learning and Low-Rank Regression Model for Robust Complex Error Modeling
For the structured error caused by occlusions or disguises, we propose a GC function based rank approximation to measure the rank of error matrices.
A Generalized Kernel Risk Sensitive Loss for Robust Two-Dimensional Singular Value Decomposition
Two-dimensional singular decomposition (2DSVD) has been widely used for image processing tasks, such as image reconstruction, classification, and clustering.
Deep Residual-Dense Lattice Network for Speech Enhancement
Motivated by this, we propose the residual-dense lattice network (RDL-Net), which is a new CNN for speech enhancement that employs both residual and dense aggregations without over-allocating parameters for feature re-usage.
Ranked #21 on
Speech Enhancement
on VoiceBank + DEMAND
Patchy Image Structure Classification Using Multi-Orientation Region Transform
To address above limitations, this paper proposes a novel Multi-Orientation Region Transform (MORT), which can effectively characterize both contour and structure features simultaneously, for patchy image structure classification.
From Species to Cultivar: Soybean Cultivar Recognition using Multiscale Sliding Chord Matching of Leaf Images
Encouraging experimental results of the proposed method in comparison to the state-of-the-art leaf species recognition methods demonstrate the availability of cultivar information in soybean leaves and effectiveness of the proposed MSCM for soybean cultivar identification, which may advance the research in leaf recognition from species to cultivar.
MobileFAN: Transferring Deep Hidden Representation for Face Alignment
To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder.
Robust Facial Landmark Localization Based on Texture and Pose Correlated Initialization
In this paper, we propose a Robust Initialization for Cascaded Pose Regression (RICPR) by providing texture and pose correlated initial shapes for the testing face.
Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing.
Can Walking and Measuring Along Chord Bunches Better Describe Leaf Shapes?
A novel chord bunch walks (CBW) descriptor is developed through the chord walking that effectively integrates the shape image function over the walked chord to reflect the contour features and the inner properties of the shape.
On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification
Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification.
Face Recognition using Optimal Representation Ensemble
It also overwhelms other modular heuristics on the faces with random occlusions, extreme expressions and disguises.
