Search Results for author:
Found 165 papers, 57 papers with code
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
To evaluate the effectiveness of our approach, we establish an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
De-coupling and De-positioning Dense Self-supervised Learning
Dense Self-Supervised Learning (SSL) methods address the limitations of using image-level feature representations when handling images with multiple objects.
Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain.
NOPE: Novel Object Pose Estimation from a Single Image
The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects.
Rigidity-Aware Detection for 6D Object Pose Estimation
To address this, we propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid.
Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation
Here, we argue that this conflicts with the averaging nature of the PnP problem, leading to gradients that may encourage the network to degrade the accuracy of individual correspondences.
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
Specifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles, which strengthen the tracker's robustness to motion variations and the template noise caused by the template update strategy.
Module-Wise Network Quantization for 6D Object Pose Estimation
Many edge applications, such as collaborative robotics and spacecraft rendezvous, can benefit from 6D object pose estimation, but must do so on embedded platforms.
CLIP the Gap: A Single Domain Generalization Approach for Object Detection
Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain.
Learning Transformations To Reduce the Geometric Shift in Object Detection
The performance of modern object detectors drops when the test distribution differs from the training one.
TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information, such as scene context, semantic relationships, gaze direction, and object dissimilarity.
TempSAL - Uncovering Temporal Information for Deep Saliency Prediction
Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information such as scene context, semantic relationships, gaze direction, and object dissimilarity.
AttEntropy: Segmenting Unknown Objects in Complex Scenes using the Spatial Attention Entropy of Semantic Segmentation Transformers
In other words, vision transformers trained to segment a fixed set of object classes generalize to objects well beyond this set.
DSI2I: Dense Style for Unpaired Image-to-Image Translation
Unpaired exemplar-based image-to-image (UEI2I) translation aims to translate a source image to a target image domain with the style of a target image exemplar, without ground-truth input-translation pairs.
LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation
Object location priors have been shown to be critical for the standard 6D object pose estimation setting, where the training and testing objects are the same.
DrapeNet: Garment Generation and Self-Supervised Draping
Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets.
Contact-aware Human Motion Forecasting
In this paper, we tackle the task of scene-aware 3D human motion forecasting, which consists of predicting future human poses given a 3D scene and a past human motion.
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.
3D Pose Based Feedback for Physical Exercises
To evaluate our approach, we introduce a dataset with 3 different physical exercises.
Fast Adversarial Training with Adaptive Step Size
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.
Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction
We introduce the task of action-driven stochastic human motion prediction, which aims to predict multiple plausible future motions given a sequence of action labels and a short motion history.
Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions
Knowledge distillation facilitates the training of a compact student network by using a deep teacher one.
MulT: An End-to-End Multitask Learning Transformer
At the heart of our approach is a shared attention mechanism modeling the dependencies across the tasks.
Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy
In essence, this strategy ignores the fact that two crops may truly contain different image information, e. g., background and small objects, and thus tends to restrain the diversity of the learned representations.
Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions
It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects.
MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World
Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM.
Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction.
Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects
In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images.
Robust Binary Models by Pruning Randomly-initialized Networks
In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
This lets us show that the decay in generalization performance of adversarial training is a result of the model's attempt to fit hard adversarial instances.
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.
Learning Transferable Adversarial Perturbations
While effective, deep neural networks (DNNs) are vulnerable to adversarial attacks.
Dyadic Human Motion Prediction
To evaluate this, and because no existing motion prediction datasets depict two closely-interacting subjects, we introduce the LindyHop600K dance dataset.
What Stops Learning-based 3D Registration from Working in the Real World?
We summarise our findings into a set of guidelines and demonstrate their effectiveness by applying them to different baseline methods, DCP and IDAM.
Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases
The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible.
Ranked #1 on
Surface Reconstruction
on ANIM
Estimating Image Depth in the Comics Domain
Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy.
Ranked #1 on
Depth Estimation
on eBDtheque
An Analysis of Super-Net Heuristics in Weight-Sharing NAS
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware.
Improving Adversarial Defense with Self-supervised Test-time Fine-tuning
Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples.
Generating Smooth Pose Sequences for Diverse Human Motion Prediction
Recent progress in stochastic motion prediction, i. e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some body parts.
Ranked #2 on
Human Pose Forecasting
on AMASS
(ADE metric)
Multi-level Motion Attention for Human Motion Prediction
Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities.
Attention-based Domain Adaptation for Single Stage Detectors
While domain adaptation has been used to improve the performance of object detectors when the training and test data follow different distributions, previous work has mostly focused on two-stage detectors.
Distilling Image Classifiers in Object Detectors
Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher.
DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows
We demonstrate the effectiveness of our approach using an ESPNet trained on the Cityscapes dataset as segmentation model, an affine Normalizing Flow as density estimator and use blue noise to ensure homogeneous sampling.
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.
Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes.
Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware.
Robust Differentiable SVD
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.
Modeling Object Dissimilarity for Deep Saliency Prediction
Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level ones, such as attention and gaze direction for entire objects.
Wide-Depth-Range 6D Object Pose Estimation in Space
6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting.
Progressive Correspondence Pruning by Consensus Learning
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences.
Learning to Generate the Unknowns for Open-set Domain Adaptation
In this setting, existing techniques focus on the challenging task of isolating the unknown target samples, so as to avoid the negative transfer resulting from aligning the source feature distributions with the broader target one that encompasses the additional unknown classes.
Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers
While these methods were shown to be vulnerable to adversarial attacks, as most deep networks for visual recognition tasks, the existing attacks for VOT trackers all require perturbing the search region of every input frame to be effective, which comes at a non-negligible cost, considering that VOT is a real-time task.
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.
Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will encounter at test time.
Human Detection and Segmentation via Multi-view Consensus
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data.
Long Term Motion Prediction Using Keyposes
Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving.
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Despite the recent advances in multiple object tracking (MOT), achieved by joint detection and tracking, dealing with long occlusions remains a challenge.
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.
Counting People by Estimating People Flows
Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images.
PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike.
A Closed-Form Solution to Local Non-Rigid Structure-from-Motion
A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express local, differential constraints between pairs of images, from which the surface normal at any point can be obtained by solving a system of polynomial equations.
3D Registration for Self-Occluded Objects in Context
While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2. 5D sensor in a scene.
Self-supervised Segmentation via Background Inpainting
While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.
Better Patch Stitching for Parametric Surface Reconstruction
We introduce an approach that explicitly encourages global consistency of the local mappings.
Motion Prediction Using Temporal Inception Module
We argue that the diverse temporal scales are important as they allow us to look at the past frames with different receptive fields, which can lead to better predictions.
Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations
We achieve state of the art performance on LINEMOD, and OccludedLINEMOD in without real-pose setting, even outperforming methods that rely on real annotations during training on Occluded-LINEMOD.
History Repeats Itself: Human Motion Prediction via Motion Attention
Human motion prediction aims to forecast future human poses given a past motion.
GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss
We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes.
Volumetric Transformer Networks
We design our VTN as an encoder-decoder network, with modules dedicated to letting the information flow across the feature channels, to account for the dependencies between the semantic parts.
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
We analyze the influence of adversarial training on the loss landscape of machine learning models.
Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features
In this paper, we identify the proximity of the latent representations of different classes in fine-grained recognition networks as a key factor to the success of adversarial attacks.
Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration
While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results.
Domain Adaptive Multibranch Networks
We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition.
ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets, typically done via a scoring function.
Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems
In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware.
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured.
Contextually Plausible and Diverse 3D Human Motion Prediction
We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses.
Training Provably Robust Models by Polyhedral Envelope Regularization
Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks.
Indirect Local Attacks for Context-aware Semantic Segmentation Networks
Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information.
Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.
Shape Reconstruction by Learning Differentiable Surface Representations
Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations.
Estimating People Flows to Better Count Them in Crowded Scenes
In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing.
Single-Stage 6D Object Pose Estimation
Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task.
Field typing for improved recognition on heterogeneous handwritten forms
Offline handwriting recognition has undergone continuous progress over the past decades.
Learning Trajectory Dependencies for Human Motion Prediction
In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.
Ranked #6 on
Human Pose Forecasting
on Human3.6M
Learning Variations in Human Motion via Mix-and-Match Perturbation
In this paper, we introduce an approach to stochastically combine the root of variations with previous pose information, which forces the model to take the noise into account.
Self-supervised Training of Proposal-based Segmentation via Background Prediction
While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.
Backpropagation-Friendly Eigendecomposition
Eigendecomposition (ED) is widely used in deep networks.
Recurrent U-Net for Resource-Constrained Segmentation
State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs.
Detecting the Unexpected via Image Resynthesis
In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time.
Neural Scene Decomposition for Multi-Person Motion Capture
To this end, we introduce a self-supervised approach to learning what we call a neural scene decomposition (NSD) that can be exploited for 3D pose estimation.
Overcoming Multi-Model Forgetting
We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, due to the overwriting of shared parameters.
Evaluating the Search Phase of Neural Architecture Search
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks.
Interpretable BoW Networks for Adversarial Example Detection
The reason behind the prediction for a new sample can then be interpreted by looking at the visual representation of the most highly activated codeword.
Segmentation-driven 6D Object Pose Estimation
The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm.
Ranked #4 on
6D Pose Estimation using RGB
on YCB-Video
GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
We fuse these features with those extracted in parallel from the 3D body, so as to model the cloth-body interactions.
Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation
As evidenced by our results on standard hand segmentation benchmarks and on our own dataset, our approach outperforms these other, simpler recurrent segmentation techniques, as well as the state-of-the-art hand segmentation one.
Context-Aware Crowd Counting
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.
Ranked #1 on
Crowd Counting
on Venice
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
As evidenced by our experiments, our approach outperforms both training the compact network from scratch and performing knowledge distillation from a teacher.
Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation
The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis.
VIENA2: A Driving Anticipation Dataset
Action anticipation is critical in scenarios where one needs to react before the action is finalized.
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
Our approach builds on the observation that foreground and background classes are not affected in the same manner by the domain shift, and thus should be treated differently.
Learning Factorized Representations for Open-set Domain Adaptation
To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace.
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
The presented algorithms can be applied to any labelling problem using a dense CRF with sparse higher-order potentials.
Deep Attentional Structured Representation Learning for Visual Recognition
Structured representations, such as Bags of Words, VLAD and Fisher Vectors, have proven highly effective to tackle complex visual recognition tasks.
Geometry-aware Deep Network for Single-Image Novel View Synthesis
By contrast, in this paper, we propose to exploit the 3D geometry of the scene to synthesize a novel view.
Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.
Ranked #27 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation
In this paper, we explicitly model the scale changes and reason in terms of people per square-meter.
Learning to Reconstruct Texture-less Deformable Surfaces from a Single View
Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured.
Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.
Learning Monocular 3D Human Pose Estimation from Multi-view Images
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets.
Statistically Motivated Second Order Pooling
Our approach is motivated by a statistical analysis of the network's activations, relying on operations that lead to a Gaussian-distributed final representation, as inherently used by first-order deep networks.
Residual Parameter Transfer for Deep Domain Adaptation
The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none.
Learning to Find Good Correspondences
We develop a deep architecture to learn to find good correspondences for wide-baseline stereo.
Compression-aware Training of Deep Networks
In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks.
Soft Correspondences in Multimodal Scene Parsing
We propose to address this issue, by formulating multimodal semantic labeling as inference in a CRF and introducing latent nodes to explicitly model inconsistencies between two modalities.
Deep Subspace Clustering Networks
We present a novel deep neural network architecture for unsupervised subspace clustering.
Ranked #3 on
Image Clustering
on Extended Yale-B
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation
Our experiments demonstrate the benefits of our classifier heatmaps and of our two-stream architecture on challenging urban scene datasets and on the YouTube-Objects benchmark, where we obtain state-of-the-art results.
Joint Dimensionality Reduction and Metric Learning: A Geometric Take
To be tractable and robust to data noise, existing metric learning algorithms commonly rely on PCA as a pre-processing step.
Adaptive Low-Rank Kernel Subspace Clustering
In this paper, we present a kernel subspace clustering method that can handle non-linear models.
Indoor Scene Parsing With Instance Segmentation, Semantic Labeling and Support Relationship Inference
In particular, while some of them aim at segmenting the image into regions, such as object or surface instances, others aim at inferring the semantic labels of given regions, or their support relationships.
Imposing Hard Constraints on Deep Networks: Promises and Limitations
Imposing constraints on the output of a Deep Neural Net is one way to improve the quality of its predictions while loosening the requirements for labeled training data.
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network.
Encouraging LSTMs to Anticipate Actions Very Early
In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos.
Second-order Convolutional Neural Networks
By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image.
Memory Efficient Max Flow for Multi-label Submodular MRFs
Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable $X_i$ is represented by $\ell$ nodes (where $\ell$ is the number of labels) arranged in a column.
Boundary-aware Instance Segmentation
In this context, existing methods typically propose candidate objects, usually as bounding boxes, and directly predict a binary mask within each such proposal.
Efficient Linear Programming for Dense CRFs
To this end, we develop a proximal minimization framework, where the dual of each proximal problem is optimized via block coordinate descent.
Learning the Number of Neurons in Deep Networks
In this paper, we introduce an approach to automatically determining the number of neurons in each layer of a deep network during learning.
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
Most recent approaches to monocular 3D human pose estimation rely on Deep Learning.
Ranked #238 on
3D Human Pose Estimation
on Human3.6M
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
We outperform the state-of-the-art methods that, as us, rely only on RGB frames as input for both action recognition and anticipation.
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
Hence, weak supervision using only image tags could have a significant impact in semantic segmentation.
Learning to Co-Generate Object Proposals With a Deep Structured Network
In particular, we introduce a deep structured network that jointly predicts the objectness scores and the bounding box locations of multiple object candidates.
Semantic-Aware Depth Super-Resolution in Outdoor Scenes
Despite much progress, state-of-the-art techniques suffer from two drawbacks: (i) they rely on the assumption that intensity edges coincide with depth discontinuities, which, unfortunately, is only true in controlled environments; and (ii) they typically exploit the availability of high-resolution training depth maps, which can often not be acquired in practice due to the sensors' limitations.
Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods
This lets us formulate dimensionality reduction as the problem of finding a projection that yields a low-dimensional manifold either with maximum discriminative power in the supervised scenario, or with maximum variance of the data in the unsupervised one.
Structured Prediction of 3D Human Pose with Deep Neural Networks
Most recent approaches to monocular 3D pose estimation rely on Deep Learning.
Ranked #272 on
3D Human Pose Estimation
on Human3.6M
Beyond Sharing Weights for Deep Domain Adaptation
To this end, we introduce a two-stream architecture, where one operates in the source domain and the other in the target domain.
Robust Multi-body Feature Tracker: A Segmentation-free Approach
Feature tracking is a fundamental problem in computer vision, with applications in many computer vision tasks, such as visual SLAM and action recognition.
Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models
Capturing the 3D motion of dynamic, non-rigid objects has attracted significant attention in computer vision.
Structural Kernel Learning for Large Scale Multiclass Object Co-Detection
To exploit the correlations between objects, we build a fully-connected CRF on the candidates, which explicitly incorporates both geometric layout relations across object classes and similarity relations across multiple images.
Cutting Edge: Soft Correspondences in Multimodal Scene Parsing
In this paper, we address the problem of data misalignment and label inconsistencies, e. g., due to moving objects, in semantic labeling, which violate the assumption of existing techniques.
Structured Depth Prediction in Challenging Monocular Video Sequences
To this end, we first study the problem of depth estimation from a single image.
Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering
By contrast, nonparametric approaches, which bypass any learning phase and directly transfer the labels from the training data to the query images, can readily exploit new labeled samples as they become available.
Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data
The Shape Interaction Matrix (SIM) is one of the earliest approaches to performing subspace clustering (i. e., separating points drawn from a union of subspaces).
Ranked #2 on
Motion Segmentation
on Hopkins155
Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs
State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution.
When VLAD met Hilbert
Vectors of Locally Aggregated Descriptors (VLAD) have emerged as powerful image/video representations that compete with or even outperform state-of-the-art approaches on many challenging visual recognition tasks.
Riemannian Coding and Dictionary Learning: Kernels to the Rescue
While sparse coding on non-flat Riemannian manifolds has recently become increasingly popular, existing solutions either are dedicated to specific manifolds, or rely on optimization problems that are difficult to solve, especially when it comes to dictionary learning.
Indoor Scene Structure Analysis for Single Image Depth Estimation
We tackle the problem of single image depth estimation, which, without additional knowledge, suffers from many ambiguities.
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
To encode the geometry of the manifold in the mapping, we introduce a family of provably positive definite kernels on the Riemannian manifold of SPD matrices.
Optimizing Over Radial Kernels on Compact Manifolds
We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification.
A Framework for Shape Analysis via Hilbert Space Embedding
We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold.
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
We then use the proposed framework to identify positive definite kernels on two specific manifolds commonly encountered in computer vision: the Riemannian manifold of symmetric positive definite matrices and the Grassmann manifold, i. e., the Riemannian manifold of linear subspaces of a Euclidean space.
Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize.
Kernel Coding: General Formulation and Special Cases
In contrast, here, we study the problem of performing coding in a high-dimensional Hilbert space, where the classes are expected to be more easily separable.
From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices
In particular, we search for a projection that yields a low-dimensional manifold with maximum discriminative power encoded via an affinity-weighted similarity measure based on metrics on the manifold.
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Modeling videos and image-sets as linear subspaces has proven beneficial for many visual recognition tasks.
Domain Adaptation on the Statistical Manifold
Here, we propose to make better use of the structure of this manifold and rely on the distance on the manifold to compare the source and target distributions.
Discrete-Continuous Depth Estimation from a Single Image
The unary potentials in this graphical model are computed by making use of the images with known depth.
Bregman Divergences for Infinite Dimensional Covariance Matrices
We introduce an approach to computing and comparing Covariance Descriptors (CovDs) in infinite-dimensional spaces.
Mirror Surface Reconstruction from a Single Image
In such conditions, our differential geometry analysis provides a theoretical proof that the shape of the mirror surface can be uniquely recovered if the pose of the reference target is known.
Continuous Inference in Graphical Models with Polynomial Energies
In this paper, we tackle the problem of performing inference in graphical models whose energy is a polynomial function of continuous variables.
Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation
Estimating 3D pose from monocular images is a highly ambiguous problem.
Factorized Latent Spaces with Structured Sparsity
Recent approaches to multi-view learning have shown that factorizing the information into parts that are shared across all views and parts that are private to each view could effectively account for the dependencies and independencies between the different input modalities.
