Search Results for author:
Found 40 papers, 22 papers with code
MoST: Motion Style Transformer between Diverse Action Contents
While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents.
UFO: Unidentified Foreground Object Detection in 3D Point Cloud
The evaluation includes a new approach to measure the performance on our goal, i. e. both localization and OOD detection of UFOs.
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding
In the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query.
Three Factors to Improve Out-of-Distribution Detection
In the problem of out-of-distribution (OOD) detection, the usage of auxiliary data as outlier data for fine-tuning has demonstrated encouraging performance.
Balanced Energy Regularization Loss for Out-of-distribution Detection
Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data.
Confidence-Based Feature Imputation for Graphs with Partially Known Features
To overcome this limitation, we introduce a novel concept of channel-wise confidence in a node feature, which is assigned to each imputed channel feature of a node for reflecting certainty of the imputation.
RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
In this paper, we propose a robustness benchmark for image-text matching models to assess their vulnerabilities.
Audio Bank: A High-Level Acoustic Signal Representation for Audio Event Recognition
Automatic audio event recognition plays a pivotal role in making human robot interaction more closer and has a wide applicability in industrial automation, control and surveillance systems.
Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis
While 3D-based GAN techniques have been successfully applied to render photo-realistic 3D images with a variety of attributes while preserving view consistency, there has been little research on how to fine-control 3D images without limiting to a specific category of objects of their properties.
Font Representation Learning via Paired-glyph Matching
For the discriminative representation of a font from others, we propose a paired-glyph matching-based font representation learning model that attracts the representations of glyphs in the same font to one another, but pushes away those of other fonts.
Meta-node: A Concise Approach to Effectively Learn Complex Relationships in Heterogeneous Graphs
To tackle this challenge, we propose a novel concept of meta-node for message passing that can learn enriched relational knowledge from complex heterogeneous graphs without any meta-paths and meta-graphs by explicitly modeling the relations among the same type of nodes.
Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning
To tackle the learning of whole-body motion, long-range temporal dynamics, and person-to-person interactions, we design a global and local attention mechanism, where, global body motions and local joint motions pay attention to each other.
Position-aware Location Regression Network for Temporal Video Grounding
The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects.
Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation
A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL).
Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning
In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling.
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification
The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes.
Ranked #20 on
Long-tail Learning
on ImageNet-LT
Influence-Balanced Loss for Imbalanced Visual Classification
In this paper, we propose a balancing training method to address problems in imbalanced data learning.
Ranked #46 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model.
Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders
Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored.
An ensemble of Density based Geometric One-Class Classifier and Genetic Algorithm
However, existing H-RTGL based OCC classifiers have limitations that (i) most of them cannot reflect density of target class and (ii) that considering density has primitive interval generation method, and (iii) there exists no systematic procedure for hyperparameter of H-RTGL based OCC classifier, which influences classification performance of classifier.
Class-Attentive Diffusion Network for Semi-Supervised Classification
In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier.
AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks
Existing fine-tuning methods use a single learning rate over all layers.
Differentiable Forward and Backward Fixed-Point Iteration Layers
FPI\_NN is intuitive, simple, and fast to train, while FPI_GD can be used for efficient training of energy networks that have been recently studied.
Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.
Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture.
Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators
We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators.
Neuro-Optimization: Learning Objective Functions Using Neural Networks
With a carefully-designed objective function, mathematical optimization can be quite helpful in solving many problems.
A Comprehensive Overhaul of Feature Distillation
We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function.
Ranked #38 on
Knowledge Distillation
on ImageNet
Skeleton-based Action Recognition of People Handling Objects
In this paper, to address this problem, we propose a new framework for recognizing object-related human actions by graph convolutional networks using human and object poses.
Ranked #1 on
Action Recognition
on IRD
Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
Our strategy alleviates the problem of gradient vanishing in low-level layers and robustly trains the low-level layers to fit the ReID dataset, thereby increasing the performance of ReID tasks.
Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neurons.
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier.
Context-aware Deep Feature Compression for High-speed Visual Tracking
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.
Ranked #15 on
Visual Object Tracking
on VOT2017/18
Simultaneous Detection and Removal of High Altitude Clouds From an Image
Interestingly, shape of the high-altitude clouds serves as a beacon for weather forecasting, so its detection is of vital importance.
Palettenet: Image recolorization with given color palette
PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette.
Attentional Correlation Filter Network for Adaptive Visual Tracking
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.
Anti-Glare: Tightly Constrained Optimization for Eyeglass Reflection Removal
Absence of a clear eye visibility not only degrades the aesthetic value of an entire face image but also creates difficulties in many computer vision tasks.
Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning
In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale.
Visual Tracking Using Attention-Modulated Disintegration and Integration
In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types.
Visual Path Prediction in Complex Scenes With Crowded Moving Objects
In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects.
