Search Results for author:
Found 15 papers, 7 papers with code
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image
To address these challenges, we propose a novel completion-based method, named DEPTHOR, featuring advances in both the training strategy and model architecture.
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy.
Graph Feedback Bandits on Similar Arms: With and Without Graph Structures
In this paper, we study the stochastic multi-armed bandit problem with graph feedback.
A generalizable framework for unlocking missing reactions in genome-scale metabolic networks using deep learning
Specifically, CLOSEgaps maps metabolic networks as hypergraphs and learns their hyper-topology features to identify missing reactions and gaps by leveraging hypothetical reactions.
DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition
In the first branch, a Domain Temporal Encoder is employed to capture temporal features for both the source and target domains.
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\mathrm{M^2}$DF)
In each view, we fuse the prompt embedding as consistent information with visual and the global or local temporal context to overcome the overlapping distribution of classes and outliers.
Forced Exploration in Bandit Problems
This paper aims to design a multi-armed bandit algorithm that can be implemented without using information about the reward distribution while still achieving substantial regret upper bounds.
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CP$\mathbf{M^2}$C)
Although some multi-modal works use labels as supplementary to construct prototypes of support videos, they can not use this information for query videos.
Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
The second module (MLT) focuses on the Multiple-level feature of the support prototype and query sample to mine more information for the alignment, which operates on different level features.
ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization
In the subsequent stage, we apply pixel-level data augmentation techniques to generate corrupted normal images and their corresponding pixel labels.
Ranked #75 on
Anomaly Detection
on MVTec AD
(using extra training data)
Non-aligned supervision for Real Image Dehazing
In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network.
EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentation
However, segmentation networks pay too much attention to the main visual difference between foreground and background, and ignores the detailed edge information, which leads to a reduction in the accuracy of edge segmentation.
TranSiam: Fusing Multimodal Visual Features Using Transformer for Medical Image Segmentation
These differences will affect the results of the automatic segmentation methods.
Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.
ROSE: Real One-Stage Effort to Detect the Fingerprint Singular Point Based on Multi-scale Spatial Attention
Detecting the singular point accurately and efficiently is one of the most important tasks for fingerprint recognition.
