Search Results for author:
Found 9 papers, 7 papers with code
OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain
This paper presents $\mathbf{OLinear}$, a $\mathbf{linear}$-based multivariate time series forecasting model that operates in an $\mathbf{o}$rthogonally transformed domain.
Multivariate Time Series Forecasting
Representation Learning
+1
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement.
Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation
Combining DM with convolutional neural networks (CNNs) enables the former to learn data distribution while the latter corrects fine details.
GIGP: A Global Information Interacting and Geometric Priors Focusing Framework for Semi-supervised Medical Image Segmentation
On the one hand, the distribution discrepancy between limited labeled data and abundant unlabeled data can hinder model generalization.
FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting
To address this, we enhance the vanilla attention mechanism by introducing an additional learnable matrix to the original attention matrix, followed by row-wise L1 normalization.
Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes
Combined with a reflection-aware appearance model, our proposed method achieves robust reconstruction and high-fidelity rendering of scenes featuring both highly specular reflections and intricate geometric structures.
Sub-Adjacent Transformer: Improving Time Series Anomaly Detection with Reconstruction Error from Sub-Adjacent Neighborhoods
By focusing the attention on the sub-adjacent areas, we make the reconstruction of anomalies more challenging, thereby enhancing their detectability.
Audio-Visual Instance Segmentation
In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos.
Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments
Localizing the camera in a known indoor environment is a key building block for scene mapping, robot navigation, AR, etc.
