Search Results for author:
Found 25 papers, 8 papers with code
GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images
Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures.
Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement
In this work, we investigate injecting the depth prior into the deep UIE model for more precise scene enhancement capability.
End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning
The streaming temporal action segmentation (STAS) task, a supplementary task of temporal action segmentation (TAS), has not received adequate attention in the field of video understanding.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
Streaming Video Temporal Action Segmentation In Real Time
As the real-time action segmentation task is different from TAS task, we define it as streaming video real-time temporal action segmentation (SVTAS) task.
A unified framework based on graph consensus term for multi-view learning
In this paper, we propose a novel multi-view learning framework, which aims to leverage most existing graph embedding works into a unified formula via introducing the graph consensus term.
Efficient Two-Step Networks for Temporal Action Segmentation
Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging.
Ranked #14 on
Action Segmentation
on GTEA
Self-Supervised Deep Graph Embedding with High-Order Information Fusion for Community Discovery
However, most self-supervised graph neural networks only use adjacency matrix as the input topology information of graph and cannot obtain too high-order information since the number of layers of graph neural network is fairly limited.
Multimodal-Aware Weakly Supervised Metric Learning with Self-weighting Triplet Loss
Therefore, how to learn an appropriate distance metric from weakly supervised data remains an open but challenging problem.
Multi-view Low-rank Preserving Embedding: A Novel Method for Multi-view Representation
Unlike existing methods with additive parameters, the proposed method could automatically allocate a suitable weight for each view in multi-view information fusion.
FSD-10: A Dataset for Competitive Sports Content Analysis
To promote the research on action recognition from competitive sports video clips, we introduce a Figure Skating Dataset (FSD-10) for finegrained sports content analysis.
The Similarity-Consensus Regularized Multi-view Learning for Dimension Reduction
Two schemes based on pairwise-consensus and centroid-consensus are separately proposed to force multiple views to learn from each other and then an iterative alternating strategy is developed to obtain the optimal solution.
Hierarchic Neighbors Embedding
Manifold learning now plays a very important role in machine learning and many relevant applications.
Multi-view Locality Low-rank Embedding for Dimension Reduction
Even though most of them can achieve satisfactory performance in some certain situations, they fail to fully consider the information from multiple views which are highly relevant but sometimes look different from each other.
A fast online cascaded regression algorithm for face alignment
Traditional face alignment based on machine learning usually tracks the localizations of facial landmarks employing a static model trained offline where all of the training data is available in advance.
Bottom-up Broadcast Neural Network For Music Genre Classification
Music genre recognition based on visual representation has been successfully explored over the last years.
Color Recognition for Rubik's Cube Robot
We finally design a Rubik's cube robot and construct a dataset to illustrate the efficiency and effectiveness of our online methods and to indicate the ineffectiveness of offline method by color drifting in our dataset.
Perceptual Visual Interactive Learning
Supervised learning methods are widely used in machine learning.
Multi-view Reconstructive Preserving Embedding for Dimension Reduction
With the development of feature extraction technique, one sample always can be represented by multiple features which locate in high-dimensional space.
Music Genre Classification with Paralleling Recurrent Convolutional Neural Network
Deep learning has been demonstrated its effectiveness and efficiency in music genre classification.
Hand Gesture Recognition with Leap Motion
The recent introduction of depth cameras like Leap Motion Controller allows researchers to exploit the depth information to recognize hand gesture more robustly.
Rough extreme learning machine: a new classification method based on uncertainty measure
Extreme learning machine (ELM) is a new single hidden layer feedback neural network.
Neural method for Explicit Mapping of Quasi-curvature Locally Linear Embedding in image retrieval
This paper proposed a new explicit nonlinear dimensionality reduction using neural networks for image retrieval tasks.
Three Tiers Neighborhood Graph and Multi-graph Fusion Ranking for Multi-feature Image Retrieval: A Manifold Aspect
Multi-feature fusion ranking can be utilized to improve the ranking list of query.
Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval
Incompatibility of image descriptor and ranking is always neglected in image retrieval.
