Search Results for author:
Found 27 papers, 15 papers with code
Towards Unsupervised Blind Face Restoration using Diffusion Prior
The models trained on such synthetic degradations, however, cannot deal with inputs of unseen degradations.
Occlusion Resilient 3D Human Pose Estimation
Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences.
AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains
In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract.
Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests
Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception.
Unsupervised 3D Keypoint Discovery with Multi-View Geometry
Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems.
Perspective Aware Road Obstacle Detection
While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases.
On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant.
3D Pose Estimation
Weakly-supervised 3D Human Pose Estimation
+1
Adversarial Parametric Pose Prior
The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes.
Overcoming the Domain Gap in Neural Action Representations
Relating animal behaviors to brain activity is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces.
Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations
A fundamental goal in neuroscience is to understand the relationship between neural activity and behavior.
RoadObstacle21
State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.
Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics
With the recent expanding attention of machine learning researchers and practitioners to fairness, there is a void of a common framework to analyze and compare the capabilities of proposed models in deep representation learning.
SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.
Detecting Road Obstacles by Erasing Them
Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector.
Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation
In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich latent vectors.
Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation
We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras.
Ranked #4 on
3D Human Pose Estimation
on Total Capture
U-Net Fixed-Point Quantization for Medical Image Segmentation
We then apply our quantization algorithm to three datasets: (1) the Spinal Cord Gray Matter Segmentation (GM), (2) the ISBI challenge for segmentation of neuronal structures in Electron Microscopic (EM), and (3) the public National Institute of Health (NIH) dataset for pancreas segmentation in abdominal CT scans.
Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders.
On Adversarial Mixup Resynthesis
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.
Distribution Matching Losses Can Hallucinate Features in Medical Image Translation
When the output of an algorithm is a transformed image there are uncertainties whether all known and unknown class labels have been preserved or changed.
Unsupervised Depth Estimation, 3D Face Rotation and Replacement
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry.
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
Improving Landmark Localization with Semi-Supervised Learning
First, we propose the framework of sequential multitasking and explore it here through an architecture for landmark localization where training with class labels acts as an auxiliary signal to guide the landmark localization on unlabeled data.
Ranked #41 on
Face Alignment
on 300W
Learning to Generate Samples from Noise through Infusion Training
In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Improving Facial Analysis and Performance Driven Animation through Disentangling Identity and Expression
We use a weakly-supervised approach in which identity labels are used to learn the different factors of variation linked to identity separately from factors related to expression.
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision.
