Search Results for author:
Found 48 papers, 13 papers with code
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.
DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition
Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data.
Zero-Shot Deep Domain Adaptation
Therefore, the source-domain task of interest solution (e. g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations.
Weakly Supervised Summarization of Web Videos
Casting the problem as a weakly supervised learning problem, we propose a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data.
Learning Compositional Visual Concepts with Mutual Consistency
Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data.
End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching
Finding correspondences between images or 3D scans is at the heart of many computer vision and image retrieval applications and is often enabled by matching local keypoint descriptors.
Tell Me Where to Look: Guided Attention Inference Network
Weakly supervised learning with only coarse labels can obtain visual explanations of deep neural network such as attention maps by back-propagating gradients.
Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only
With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images.
Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition
Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.
Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
In this paper, we solve this key problem of existing methods requiring expensive 3D pose annotations by proposing a new method that matches RGB images to CAD models for object pose estimation.
Re-Identification with Consistent Attentive Siamese Networks
We propose a new deep architecture for person re-identification (re-id).
Sharpen Focus: Learning with Attention Separability and Consistency
Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks.
Learning without Memorizing
Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model.
Incremental Scene Synthesis
We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior, (b) real observations of a scene can be incorporated while observing global consistency, (c) unobserved regions can be hallucinated locally in consistence with previous observations, hallucinations and global priors, and (d) hallucinations are statistical in nature, i. e., different scenes can be generated from the same observations.
Counterfactual Visual Explanations
In this work, we develop a technique to produce counterfactual visual explanations.
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.
Visual Similarity Attention
While there has been substantial progress in learning suitable distance metrics, these techniques in general lack transparency and decision reasoning, i. e., explaining why the input set of images is similar or dissimilar.
Hierarchical Kinematic Human Mesh Recovery
In this work, we address this gap by proposing a new technique for regression of human parametric model that is explicitly informed by the known hierarchical structure, including joint interdependencies of the model.
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up.
Towards Visually Explaining Similarity Models
We show that the resulting similarity models perform, and can be visually explained, better than the corresponding baseline models trained without these constraints.
Ensemble Attention Distillation for Privacy-Preserving Federated Learning
Such decentralized training naturally leads to issues of imbalanced or differing data distributions among the local models and challenges in fusing them into a central model.
A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
Everybody Is Unique: Towards Unbiased Human Mesh Recovery
Next, we present a simple baseline to address this problem that is scalable and can be easily used in conjunction with existing algorithms to improve their performance.
Ranked #1 on
3D Human Shape Estimation
on SSP-3D
(PVE-T metric)
Spatio-Temporal Representation Factorization for Video-based Person Re-Identification
To alleviate these problems, we propose Spatio-Temporal Representation Factorization (STRF), a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID.
Ranked #2 on
Person Re-Identification
on DukeMTMC-VideoReID
Learning Local Recurrent Models for Human Mesh Recovery
We conduct a variety of experiments on standard video mesh recovery benchmark datasets such as Human3. 6M, MPI-INF-3DHP, and 3DPW, demonstrating the efficacy of our design of modeling local dynamics as well as establishing state-of-the-art results based on standard evaluation metrics.
Ranked #45 on
3D Human Pose Estimation
on 3DPW
Towards Generic Interface for Human-Neural Network Knowledge Exchange
Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.
Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis
However, doing this accurately will require a large amount of disease localization annotations by clinical experts, a task that is prohibitively expensive to accomplish for most applications.
SMPL-A: Modeling Person-Specific Deformable Anatomy
In order to obtain accurate target location information, clinicians have to either conduct frequent intraoperative scans, resulting in higher exposition of patients to radiations, or adopt proxy procedures (e. g., creating and using custom molds to keep patients in the exact same pose during both preoperative organ scanning and subsequent treatment.
PseudoClick: Interactive Image Segmentation with Click Imitation
The goal of click-based interactive image segmentation is to obtain precise object segmentation masks with limited user interaction, i. e., by a minimal number of user clicks.
Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized.
Self-supervised Human Mesh Recovery with Cross-Representation Alignment
However, on synthetic dense correspondence maps (i. e., IUV) few have been explored since the domain gap between synthetic training data and real testing data is hard to address for 2D dense representation.
PREF: Predictability Regularized Neural Motion Fields
We propose to regularize the estimated motion to be predictable.
Federated Learning with Privacy-Preserving Ensemble Attention Distillation
We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work.
Forecasting Human Trajectory from Scene History
We categorize scene history information into two types: historical group trajectory and individual-surroundings interaction.
Progressive Multi-view Human Mesh Recovery with Self-Supervision
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e. g., motion capture, sport analysis) and robustness to single-view ambiguities.
Exploring Cycle Consistency Learning in Interactive Volume Segmentation
Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices.
Disguise without Disruption: Utility-Preserving Face De-Identification
We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.
CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation
However, limited by the low dynamic range of conventional cameras, images fail to capture structural details and boundary information in low-light conditions.
IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentation
Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data.
Implicit Modeling of Non-rigid Objects with Cross-Category Signals
To effectively capture the interrelation between these entities and ensure precise, collision-free representations, our approach facilitates signaling between category-specific fields to adequately rectify shapes.
Federated Learning via Input-Output Collaborative Distillation
Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data.
PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
The detection of human parts (e. g., hands, face) and their correct association with individuals is an essential task, e. g., for ubiquitous human-machine interfaces and action recognition.
DaReNeRF: Direction-aware Representation for Dynamic Scenes
However, the straightforward decomposition of 4D dynamic scenes into multiple 2D plane-based representations proves insufficient for re-rendering high-fidelity scenes with complex motions.
Self-supervised 3D Patient Modeling with Multi-modal Attentive Fusion
3D patient body modeling is critical to the success of automated patient positioning for smart medical scanning and operating rooms.
Automating Catheterization Labs with Real-Time Perception
For decades, three-dimensional C-arm Cone-Beam Computed Tomography (CBCT) imaging system has been a critical component for complex vascular and nonvascular interventional procedures.
Self-learning Canonical Space for Multi-view 3D Human Pose Estimation
To facilitate the aggregation of the intra- and inter-view, we define a canonical parameter space, depicted by per-view camera pose and human pose and shape parameters ($\theta$ and $\beta$) of SMPL model, and propose a two-stage learning procedure.
Human Mesh Recovery from Arbitrary Multi-view Images
Human mesh recovery from arbitrary multi-view images involves two characteristics: the arbitrary camera poses and arbitrary number of camera views.
