Search Results for author:
Found 19 papers, 7 papers with code
Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis
In this work, we shift the main focus to frequency representations, modeling time-series data fully and directly in the Fourier domain.
See It All: Contextualized Late Aggregation for 3D Dense Captioning
SIA simultaneously decodes two sets of queries-context query and instance query.
Bi-directional Contextual Attention for 3D Dense Captioning
3D dense captioning is a task involving the localization of objects and the generation of descriptions for each object in a 3D scene.
FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction
Multi-agent motion prediction is a crucial concern in autonomous driving, yet it remains a challenge owing to the ambiguous intentions of dynamic agents and their intricate interactions.
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization
Visual localization is the task of estimating a 6-DoF camera pose of a query image within a provided 3D reference map.
MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
The time-series anomaly detection is one of the most fundamental tasks for time-series.
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning
Furthermore, as the relationship between context and motion is important in order to identify the anomalies in complex and diverse scenes, we propose a Context--Motion Interrelation Module (CoMo), which models the relationship between the appearance of the surroundings and motion, rather than utilizing only temporal dependencies or motion information.
Feature Disentanglement Learning with Switching and Aggregation for Video-based Person Re-Identification
In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames.
Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning
Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes.
Tackling Background Distraction in Video Object Segmentation
Semi-supervised video object segmentation (VOS) aims to densely track certain designated objects in videos.
SOS: Score-based Oversampling for Tabular Data
To our knowledge, we are the first presenting a score-based tabular data oversampling method.
Fine-Tuning BERT Models to Classify Misinformation on Garlic and COVID-19 on Twitter
The BERT models fine-tuned with the COVID-19 rumor dataset showed poor performance, with maximum accuracy of 0. 647.
Marvelous Agglutinative Language Effect on Cross Lingual Transfer Learning
As for multilingual language models, it is important to select languages for training because of the curse of multilinguality.
3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications.
Pixel-Level Bijective Matching for Video Object Segmentation
Before finding the best matches for the query frame pixels, the optimal matches for the reference frame pixels are first considered to prevent each reference frame pixel from being overly referenced.
Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable.
Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
We propose an approach to address two issues that commonly occur during training of unsupervised GANs.
Imaginary time, shredded propagator method for large-scale GW calculations
The GW method is a many-body approach capable of providing quasiparticle bands for realistic systems spanning physics, chemistry, and materials science.
Materials Science
