Search Results for author:
Found 32 papers, 10 papers with code
TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown.
HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization
By integrating historical context, our framework enhances the synergy between long-term and short-term information, improving the quality of anchor features crucial for classification and localization.
Face Reconstruction Transfer Attack as Out-of-Distribution Generalization
Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance.
3D-HGS: 3D Half-Gaussian Splatting
Photo-realistic image rendering from scene 3D reconstruction is a fundamental problem in 3D computer vision.
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers
Solving image and video jigsaw puzzles poses the challenging task of rearranging image fragments or video frames from unordered sequences to restore meaningful images and video sequences.
MagicMirror: Fast and High-Quality Avatar Generation with a Constrained Search Space
We introduce a novel framework for 3D human avatar generation and personalization, leveraging text prompts to enhance user engagement and customization.
Inferring Relational Potentials in Interacting Systems
In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory.
Enhancing Transformer Backbone for Egocentric Video Action Segmentation
Therefore, it is necessary to improve transformers to enhance the robustness of action segmentation models.
Cross-view Action Recognition via Contrastive View-invariant Representation
Cross view action recognition (CVAR) seeks to recognize a human action when observed from a previously unseen viewpoint.
Explainable Anomaly Detection in Images and Videos: A Survey
This paper provides the first survey concentrated on explainable visual anomaly detection methods.
Geometry of Score Based Generative Models
We demonstrate that looking from geometric perspective enables us to answer many of these questions and provide new interpretations to some known results.
Divide and Compose with Score Based Generative Models
Towards the direction of having more control over image manipulation and conditional generation, we propose to learn image components in an unsupervised manner so that we can compose those components to generate and manipulate images in informed manner.
SAIF: Sparse Adversarial and Imperceptible Attack Framework
Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal.
Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection
There are limited works showing the efficacy of unsupervised Out-of-Distribution (OOD) methods on complex medical data.
Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective
Human interpretation of the world encompasses the use of symbols to categorize sensory inputs and compose them in a hierarchical manner.
Learning Disentangled Representations of Videos with Missing Data
Missing data poses significant challenges while learning representations of video sequences.
Key Frame Proposal Network for Efficient Pose Estimation in Videos
Human pose estimation in video relies on local information by either estimating each frame independently or tracking poses across frames.
Learning Disentangled Representations of Video with Missing Data
Missing data poses significant challenges while learning representations of video sequences.
Towards Visually Explaining Variational Autoencoders
We present methods to generate visual attention from the learned latent space, and also demonstrate such attention explanations serve more than just explaining VAE predictions.
SoS-RSC: A Sum-of-Squares Polynomial Approach to Robustifying Subspace Clustering Algorithms
This paper addresses the problem of subspace clustering in the presence of outliers.
DYAN: A Dynamical Atoms-Based Network for Video Prediction
The ability to anticipate the future is essential when making real time critical decisions, provides valuable information to understand dynamic natural scenes, and can help unsupervised video representation learning.
MoNet: Moments Embedding Network
In addition, we propose a novel sub-matrix square-root layer, which can be used to normalize the output of the convolution layer directly and mitigate the dimensionality problem with off-the-shelf compact pooling methods.
Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos
This paper considers the multi-camera motion segmentation problem using unsynchronized videos.
Multi-camera Multi-Object Tracking
For multi-camera system tracking problem, efficient data association across cameras, and at the same time, across frames becomes more important than single-camera system tracking.
Solving Temporal Puzzles
Many physical phenomena, within short time windows, can be explained by low order differential relations.
Subspace Clustering With Priors via Sparse Quadratically Constrained Quadratic Programming
This paper considers the problem of recovering a subspace arrangement from noisy samples, potentially corrupted with outliers.
Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold
In this paper we propose a new framework to compare and classify temporal sequences.
A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets
To ensure a fair comparison, all of the approaches were implemented using a unified code library that includes 11 feature extraction algorithms and 22 metric learning and ranking techniques.
Person Re-identification in Appearance Impaired Scenarios
Our experiments on the original and the appearance impaired datasets demonstrate the benefits of incorporating dynamics-based information with appearance-based information to re-identification algorithms.
Self Scaled Regularized Robust Regression
Linear Robust Regression (LRR) seeks to find the parameters of a linear mapping from noisy data corrupted from outliers, such that the number of inliers (i. e. pairs of points where the fitting error of the model is less than a given bound) is maximized.
A Convex Optimization Approach to Robust Fundamental Matrix Estimation
This paper considers the problem of recovering a subspace arrangement from noisy samples, potentially corrupted with outliers.
Robust Anomaly Detection Using Semidefinite Programming
This paper presents a new approach, based on polynomial optimization and the method of moments, to the problem of anomaly detection.
