Search Results for author:
Found 9 papers, 4 papers with code
Intriguing Properties of Positional Encoding in Time Series Forecasting
Motivated by these findings, we introduce two new PEs: Temporal Position Encoding (T-PE) for temporal tokens and Variable Positional Encoding (V-PE) for variable tokens.
Learning Novel View Synthesis from Heterogeneous Low-light Captures
Unfortunately, synthesizing novel views remains to be a challenge for input views with heterogeneous brightness level captured under low-light condition.
End-To-End Underwater Video Enhancement: Dataset and Model
To fill this gap, we construct the Synthetic Underwater Video Enhancement (SUVE) dataset, comprising 840 diverse underwater-style videos paired with ground-truth reference videos.
Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature.
UIEDP:Underwater Image Enhancement with Diffusion Prior
To address this issue, we propose UIE with Diffusion Prior (UIEDP), a novel framework treating UIE as a posterior distribution sampling process of clear images conditioned on degraded underwater inputs.
A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning
To address this issue, in this paper, we discover the correlation between feature discriminability and dimensional structure (DS) by analyzing and observing features extracted from simple and hard tasks.
A survey on facial image deblurring
The purpose of facial image deblurring is to recover a clear image from a blurry input image, which can improve the recognition accuracy, etc.
Timestamp-Supervised Action Segmentation from the Perspective of Clustering
Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model.
