Search Results for author:
Found 39 papers, 14 papers with code
Leveraging Perfect Multimodal Alignment and Gaussian Assumptions for Cross-modal Transfer
Multimodal alignment aims to construct a joint latent vector space where two modalities representing the same concept map to the same vector.
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric Representations
GIST replaces the standard Neural Style Transfer autoencoding framework with a multiscale image expansion, preserving scene details without the need for post-processing or training.
R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptation
Test-time adaptation (TTA) has emerged as a promising solution to tackle the continual domain shift in machine learning by allowing model parameters to change at test time, via self-supervised learning on unlabeled testing data.
Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input
We observe the poor generalization of state-of-the-art 3D pose lifters in the presence of corruption and establish two techniques to tackle this issue.
Persistent Test-time Adaptation in Recurring Testing Scenarios
Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to environments that change continuously.
Making Vision Transformers Truly Shift-Equivariant
For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures.
MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
To overcome the disadvantage of the point estimation mechanism, we propose a novel approach, dubbed MaskDiff, which models the underlying conditional distribution of a binary mask, which is conditioned on an object region and $K-$shot information.
FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
FedDCT reduces the memory requirements and allows low-end devices to participate in FL.
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks.
Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling
We validate the system on EPIC-KITCHENS and UCF-101 datasets for action recognition, and show that our proposed approach can greatly speed up inference with a tolerable loss of accuracy compared with those from state-of-the-art baselines.
Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examination
In this paper, we propose an accessible vision-based exam and documentation solution called Digitized Neurological Examination (DNE) to expand exam biomarker recording options and clinical applications using a smartphone/tablet.
Multi-modality fusion using canonical correlation analysis methods: Application in breast cancer survival prediction from histology and genomics
We propose a two-stage prediction pipeline using pCCA embeddings generated with deflation for latent variable prediction by combining all the above.
EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
In this work, we propose End-to-end Hardware-aware DNAS (EH-DNAS), a seamless integration of end-to-end hardware benchmarking, and fully automated DNAS to deliver hardware-efficient deep neural networks on various platforms, including Edge GPUs, Edge TPUs, Mobile CPUs, and customized accelerators.
Multimodal Unrolled Robust PCA for Background Foreground Separation
Background foreground separation (BFS) is a popular computer vision problem where dynamic foreground objects are separated from the static background of a scene.
Inverting Adversarially Robust Networks for Image Synthesis
Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors.
Multimodal fusion using sparse CCA for breast cancer survival prediction
Effective understanding of a disease such as cancer requires fusing multiple sources of information captured across physical scales by multimodal data.
Multimodal fusion of imaging and genomics for lung cancer recurrence prediction
Lung cancer has a high rate of recurrence in early-stage patients.
Dense 3D Reconstruction for Visual Tunnel Inspection using Unmanned Aerial Vehicle
In this work, we design a UAV with a single rotating camera to accomplish the task.
Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction.
Feature-less Stitching of Cylindrical Tunnel
Traditional image stitching algorithms use transforms such as homography to combine different views of a scene.
Rotation Equivariance and Invariance in Convolutional Neural Networks
Performance of neural networks can be significantly improved by encoding known invariance for particular tasks.
Interpretable and Globally Optimal Prediction for Textual Grounding using Image Concepts
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining.
Unsupervised Textual Grounding: Linking Words to Image Concepts
Textual grounding, i. e., linking words to objects in images, is a challenging but important task for robotics and human-computer interaction.
Multi-Segment Reconstruction Using Invariant Features
Instead of trying to locate the segment within the sequence through pair-wise matching, we propose a new approach that uses shift-invariant features to estimate both the underlying signal and the distribution of the positions of the segments.
Signal Processing
Tracking objects using 3D object proposals
3D object proposals, quickly detected regions in a 3D scene that likely contain an object of interest, are an effective approach to improve the computational efficiency and accuracy of the object detection framework.
Locating 3D Object Proposals: A Depth-Based Online Approach
Using efficient but robust registration enables us to combine multiple frames of a scene in near real time and generate 3D bounding boxes for potential 3D regions of interest.
Calibration of depth cameras using denoised depth images
Depth sensing devices have created various new applications in scientific and commercial research with the advent of Microsoft Kinect and PMD (Photon Mixing Device) cameras.
Matrix Product State for Higher-Order Tensor Compression and Classification
This paper introduces matrix product state (MPS) decomposition as a new and systematic method to compress multidimensional data represented by higher-order tensors.
Semantic Image Inpainting with Deep Generative Models
In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.
Concatenated image completion via tensor augmentation and completion
The proposed framework performs image completion by concatenating copies of a single image that has missing entries into a third-order tensor, applying a dimensionality augmentation technique to the tensor, utilizing a tensor completion algorithm for recovering its missing entries, and finally extracting the recovered image from the tensor.
Efficient tensor completion for color image and video recovery: Low-rank tensor train
The approach is based on the tensor train (TT) rank, which is able to capture hidden information from tensors thanks to its definition from a well-balanced matricization scheme.
Numerical Analysis Data Structures and Algorithms
DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation
In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate multi-modal and multi-spectral dense correspondences.
SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs
However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.
PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures
In this work, we investigate the problem of automatically inferring the lattice structure of near-regular textures (NRT) in real-world images.
Direct Structure Estimation for 3D Reconstruction
Most conventional structure-from-motion (SFM) techniques require camera pose estimation before computing any scene structure.
DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence
To further improve the matching quality and runtime efficiency, we propose a patch-wise receptive field pooling, in which a sampling pattern is optimized with a discriminative learning.
Weakly Supervised Fine-Grained Image Categorization
Most existing works heavily rely on object / part detectors to build the correspondence between object parts by using object or object part annotations inside training images.
Matrix Product State for Feature Extraction of Higher-Order Tensors
This paper introduces matrix product state (MPS) decomposition as a computational tool for extracting features of multidimensional data represented by higher-order tensors.
Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation
Recent studies on fast cost volume filtering based on efficient edge-aware filters have provided a fast alternative to solve discrete labeling problems, with the complexity independent of the support window size.
