Search Results for author:
Found 47 papers, 15 papers with code
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
Although the CRF is a good baseline labeler, we show how an RBM can be added to the architecture to provide a global shape bias that complements the local modeling provided by the CRF.
The Shape-Time Random Field for Semantic Video Labeling
In this work, we incorporate a CRBM prior into a CRF framework and present a new state-of-the-art model for the task of semantic labeling in videos.
Multi-view Convolutional Neural Networks for 3D Shape Recognition
A longstanding question in computer vision concerns the representation of 3D shapes for recognition: should 3D shapes be represented with descriptors operating on their native 3D formats, such as voxel grid or polygon mesh, or can they be effectively represented with view-based descriptors?
Ranked #95 on
3D Point Cloud Classification
on ModelNet40
One-to-many face recognition with bilinear CNNs
We demonstrate the performance of the B-CNN model beginning from an AlexNet-style network pre-trained on ImageNet.
Background Modeling Using Adaptive Pixelwise Kernel Variances in a Hybrid Feature Space
In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussians at each pixel [7], to kernel density estimates at each pixel [1], and more recently to joint domainrange density estimates that incorporate spatial information [6].
Background subtraction - separating the modeling and the inference
In particular, it is essential to have a background likelihood, a foreground likelihood, and a prior at each pixel.
Coherent Motion Segmentation in Moving Camera Videos using Optical Flow Orientations
Our goal is to develop a segmentation algorithm that clusters pixels that have similar real-world motion irrespective of their depth in the scene.
It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos
The human ability to detect and segment moving objects works in the presence of multiple objects, complex background geometry, motion of the observer, and even camouflage.
Face Detection with the Faster R-CNN
The Faster R-CNN has recently demonstrated impressive results on various object detection benchmarks.
Associating Grasp Configurations with Hierarchical Features in Convolutional Neural Networks
We demonstrate that this approach outperforms baseline approaches in cluttered scenarios on the grasping dataset and a point cloud based approach on a grasping task using Robonaut-2.
A Detailed Rubric for Motion Segmentation
The second is to report on new versions of three previously existing data sets that are compatible with this definition.
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy.
End-to-end Face Detection and Cast Grouping in Movies Using Erdős-Rényi Clustering
We introduce a novel verification method, rank-1 counts verification, that has this property, and use it in a link-based clustering scheme.
End-To-End Face Detection and Cast Grouping in Movies Using Erdos-Renyi Clustering
We introduce a novel verification method, rank-1 counts verification, that has this property, and use it in a link-based clustering scheme.
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
Finally, the two input images are warped and linearly fused to form each intermediate frame.
Self-Supervised Relative Depth Learning for Urban Scene Understanding
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth.
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding.
Unsupervised Hard Example Mining from Videos for Improved Object Detection
In this work, we show how large numbers of hard negatives can be obtained {\em automatically} by analyzing the output of a trained detector on video sequences.
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing
In this work, we propose a standalone neural ranking model (SNRM) by introducing a sparsity property to learn a latent sparse representation for each query and document.
Ranked #12 on
Ad-Hoc Information Retrieval
on TREC Robust04
Nonparametric Curve Alignment
Congealing is a flexible nonparametric data-driven framework for the joint alignment of data.
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification
Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data.
Pixel-Adaptive Convolutional Neural Networks
In addition, we also demonstrate that PAC can be used as a drop-in replacement for convolution layers in pre-trained networks, resulting in consistent performance improvements.
Automatic adaptation of object detectors to new domains using self-training
Our results demonstrate the usefulness of incorporating hard examples obtained from tracking, the advantage of using soft-labels via distillation loss versus hard-labels, and show promising performance as a simple method for unsupervised domain adaptation of object detectors, with minimal dependence on hyper-parameters.
A New Confidence Interval for the Mean of a Bounded Random Variable
We present a new method for constructing a confidence interval for the mean of a bounded random variable from samples of the random variable.
SENSE: a Shared Encoder Network for Scene-flow Estimation
We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion estimation, and semantic segmentation.
In Defense of Grid Features for Visual Question Answering
Popularized as 'bottom-up' attention, bounding box (or region) based visual features have recently surpassed vanilla grid-based convolutional features as the de facto standard for vision and language tasks like visual question answering (VQA).
Ranked #18 on
Visual Question Answering (VQA)
on VQA v2 test-std
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years.
Cross-Supervised Object Detection
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects.
Improving Face Recognition by Clustering Unlabeled Faces in the Wild
While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation.
Shot in the Dark: Few-Shot Learning with No Base-Class Labels
To alleviate problems caused by the distribution shift, previous research has explored the use of unlabeled examples from the novel classes, in addition to labeled examples of the base classes, which is known as the transductive setting.
SID-NISM: A Self-supervised Low-light Image Enhancement Framework
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms.
DCVNet: Dilated Cost Volume Networks for Fast Optical Flow
When sampling correspondences to build the cost volume, a large neighborhood radius is required to deal with large displacements, introducing a significant computational burden.
Universal Off-Policy Evaluation
When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy.
Passage Retrieval for Outside-Knowledge Visual Question Answering
We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions.
The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data
In particular, we model the aligned data as a spatio-temporal Poisson point process.
PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation
We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks.
The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields
In this work, we argue that the coupling of camera rotation and camera translation can create complex motion fields that are difficult for a deep network to untangle directly.
Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain Images
Automatic terrain recognition in Mars rover images is an important problem not just for navigation, but for scientists interested in studying rock types, and by extension, conditions of the ancient Martian paleoclimate and habitability.
Inv-SENnet: Invariant Self Expression Network for clustering under biased data
Subspace clustering algorithms are used for understanding the cluster structure that explains the dataset well.
EVAL: Explainable Video Anomaly Localization
We develop a novel framework for single-scene video anomaly localization that allows for human-understandable reasons for the decisions the system makes.
Ranked #16 on
Anomaly Detection
on ShanghaiTech
Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners
To address the MTL challenge, we propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad').
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface
Our paper proposes a direct sparse visual odometry method that combines event and RGB-D data to estimate the pose of agile-legged robots during dynamic locomotion and acrobatic behaviors.
An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training
We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently.
Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video.
Machine Learning for Automated Mitral Regurgitation Detection from Cardiac Imaging
Mitral regurgitation (MR) is a heart valve disease with potentially fatal consequences that can only be forestalled through timely diagnosis and treatment.
Log-Concavity of Multinomial Likelihood Functions Under Interval Censoring Constraints on Frequencies or Their Partial Sums
We show that the likelihood function for a multinomial vector observed under arbitrary interval censoring constraints on the frequencies or their partial sums is completely log-concave by proving that the constrained sample spaces comprise M-convex subsets of the discrete simplex.
