Search Results for author:
Found 155 papers, 34 papers with code
Knowledge Combination to Learn Rotated Detection Without Rotated Annotation
Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations are used instead.
Adaptive Cross Batch Normalization for Metric Learning
In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration as the learnable parameters are being updated.
Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems
Specifically, we fit the GradCAM with a branch with limited fitting capacity, which allows the branch to capture the common rationales and discard the less common discriminative patterns.
BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling
Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem.
Program Generation from Diverse Video Demonstrations
The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence.
Understanding and Improving the Role of Projection Head in Self-Supervised Learning
Most current contrastive learning approaches append a parametrized projection head to the end of some backbone network to optimize the InfoNCE objective and then discard the learned projection head after training.
Identifying Weight-Variant Latent Causal Models
The task of causal representation learning aims to uncover latent higher-level causal representations that affect lower-level observations.
ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers
Besides, we further extend the clustering-guided attention from single-scale to multi-scale, which is conducive to dense prediction tasks.
EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering
In a simple setting similar to CLEVR, we find that CL representations also improve systematic generalization, and even match the performance of representations from a larger, supervised, ImageNet-pretrained model.
Confident Sinkhorn Allocation for Pseudo-Labeling
CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning.
PointInst3D: Segmenting 3D Instances by Points
The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics.
CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification
Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems.
Active Learning by Feature Mixing
We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations.
Distributionally Robust Bayesian Optimization with $φ$-divergences
The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty.
Retrieval Augmented Classification for Long-Tail Visual Recognition
We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module.
Ranked #3 on
Long-tail Learning
on iNaturalist 2018
Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning
This minimizes the interference between parameters for different tasks.
Deep Learning for Hate Speech Detection: A Comparative Study
Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media.
The devil is in the labels: Semantic segmentation from sentences
The resulting merged semantic segmentation dataset of over 2 Million images enables training a model that achieves performance equal to that of state-of-the-art supervised methods on 7 benchmark datasets, despite not using any images therefrom.
Ranked #1 on
Semantic Segmentation
on WildDash
Poseur: Direct Human Pose Regression with Transformers
We propose a direct, regression-based approach to 2D human pose estimation from single images.
Ranked #2 on
Keypoint Detection
on COCO
Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs.
Explainable Deep Few-shot Anomaly Detection with Deviation Networks
Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models.
Ranked #3 on
supervised anomaly detection
on MVTec AD
(using extra training data)
Dynamic Convolution for 3D Point Cloud Instance Segmentation
The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization
The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.
The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas.
Learning for Visual Navigation by Imagining the Success
ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success, e. g. either a sub-goal state that is important to reach before the target, or the goal state itself.
Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge
The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models.
Memory-Augmented Dynamic Neural Relational Inference
This motivates us to propose a memory-augmented dynamic neural relational inference method, which maintains two associative memory pools: one for the interactive relations and the other for the individual entities.
Unshuffling Data for Improved Generalization in Visual Question Answering
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
Deep Depression Prediction on Longitudinal Data via Joint Anomaly Ranking and Classification
A wide variety of methods have been developed for identifying depression, but they focus primarily on measuring the degree to which individuals are suffering from depression currently.
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen
The task of vision-and-language navigation (VLN) requires an agent to follow text instructions to find its way through simulated household environments.
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions.
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset.
Object-and-Action Aware Model for Visual Language Navigation
The first is object description (e. g., 'table', 'door'), each presenting as a tip for the agent to determine the next action by finding the item visible in the environment, and the second is action specification (e. g., 'go straight', 'turn left') which allows the robot to directly predict the next movements without relying on visual perceptions.
Deep Learning for Anomaly Detection: A Review
This paper surveys the research of deep anomaly detection with a comprehensive taxonomy, covering advancements in three high-level categories and 11 fine-grained categories of the methods.
Structured Multimodal Attentions for TextVQA
In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above.
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set.
Visual Question Answering with Prior Class Semantics
We present a novel mechanism to embed prior knowledge in a model for visual question answering.
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest.
Multi-Label Image Classification
Natural Language Inference
+3
Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
Video anomaly detection is of critical practical importance to a variety of real applications because it allows human attention to be focused on events that are likely to be of interest, in spite of an otherwise overwhelming volume of video.
Unshuffling Data for Improved Generalization
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering
Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize.
Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs.
Deep Anomaly Detection with Deviation Networks
Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e. g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail.
Ranked #1 on
Network Intrusion Detection
on NB15-Backdoor
Deep Weakly-supervised Anomaly Detection
Anomaly detection is typically posited as an unsupervised learning task in the literature due to the prohibitive cost and difficulty to obtain large-scale labeled anomaly data, but this ignores the fact that a very small number (e. g.,, a few dozens) of labeled anomalies can often be made available with small/trivial cost in many real-world anomaly detection applications.
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices
One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced.
An Effective Two-Branch Model-Based Deep Network for Single Image Deraining
Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.
Show, Price and Negotiate: A Negotiator with Online Value Look-Ahead
Negotiation, as an essential and complicated aspect of online shopping, is still challenging for an intelligent agent.
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language.
Attention-guided Network for Ghost-free High Dynamic Range Imaging
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
Reinforcement Learning with Attention that Works: A Self-Supervised Approach
Attention models have had a significant positive impact on deep learning across a range of tasks.
Actively Seeking and Learning from Live Data
One of the key limitations of traditional machine learning methods is their requirement for training data that exemplifies all the information to be learned.
Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data.
What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions
We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output.
Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning
For each potential action a distribution of the expected outcomes is calculated, and the value of the potential information gain assessed.
Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks
Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches.
Visual Question Answering as Reading Comprehension
In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language so as to convert VQA into a machine reading comprehension problem.
End-to-End Diagnosis and Segmentation Learning from Cardiac Magnetic Resonance Imaging
In this paper, we propose a learning method to train diagnosis models, where our approach is designed to work with relatively small datasets.
MPTV: Matching Pursuit Based Total Variation Minimization for Image Deconvolution
Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization.
Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Towards Effective Deep Embedding for Zero-Shot Learning
Towards this goal, we present a simple but effective two-branch network to simultaneously map semantic descriptions and visual samples into a joint space, on which visual embeddings are forced to regress to their class-level semantic embeddings and the embeddings crossing classes are required to be distinguishable by a trainable classifier.
Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network
In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture.
Learning Deep Gradient Descent Optimization for Image Deconvolution
Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.
Deep Lipschitz networks and Dudley GANs
To facilitate this, we develop both theoretical and practical building blocks, using which one can construct different neural networks using a large range of metrics, as well as ensure Lipschitz condition and sufficient capacity of the networks.
Real-time Semantic Image Segmentation via Spatial Sparsity
We propose an approach to semantic (image) segmentation that reduces the computational costs by a factor of 25 with limited impact on the quality of results.
Visual Question Answering as a Meta Learning Task
At test time, the method is provided with a support set of example questions/answers, over which it reasons to resolve the given question.
Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human.
Ranked #4 on
Visual Dialog
on VisDial v0.9 val
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.
Ranked #3 on
Visual Navigation
on R2R
Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs.
Self-Paced Kernel Estimation for Robust Blind Image Deblurring
Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process.
Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge.
Ranked #30 on
Visual Question Answering (VQA)
on VQA v2 test-std
Beyond Low Rank: A Data-Adaptive Tensor Completion Method
The prior for the non-low-rank structure is established based on a mixture of Gaussians which is shown to be flexible enough, and powerful enough, to inform the completion process for a variety of real tensor data.
When Unsupervised Domain Adaptation Meets Tensor Representations
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another.
Visually Aligned Word Embeddings for Improving Zero-shot Learning
To overcome this visual-semantic discrepancy, this work proposes an objective function to re-align the distributed word embeddings with visual information by learning a neural network to map it into a new representation called visually aligned word embedding (VAWE).
Visual Question Answering with Memory-Augmented Networks
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.
Multi-Attention Network for One Shot Learning
One-shot learning is a challenging problem where the aim is to recognize a class identified by a single training image.
Bayesian Conditional Generative Adverserial Networks
Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input $z$ to a sample $\mathbf{x}$ that the discriminator seeks to distinguish.
Care about you: towards large-scale human-centric visual relationship detection
In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotation (nearly 10K categories) than the previous released datasets.
Human-Object Interaction Detection
Relationship Detection
+1
The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
To train a method to perform even one of these operations accurately from {image, question, answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best.
From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
Sequential Person Recognition in Photo Albums with a Recurrent Network
In this work, we propose to model the relational information between people as a sequence prediction task.
Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset.
Ranked #11 on
Semantic Segmentation
on PASCAL VOC 2012 test
Infinite Variational Autoencoder for Semi-Supervised Learning
This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data.
Zero-Shot Visual Question Answering
Answering general questions about images requires methods capable of Zero-Shot VQA, that is, methods able to answer questions beyond the scope of the training questions.
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs
As a result, the representation power of intermediate layers can be very weak and the model becomes very redundant with limited performance.
Graph-Structured Representations for Visual Question Answering
This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions.
Visual Question Answering: A Survey of Methods and Datasets
Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities.
FVQA: Fact-based Visual Question Answering
We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.
Ranked #2 on
Visual Question Answering (VQA)
on F-VQA
Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach
In this paper, we present an end-to-end approach to simultaneously learn spatio-temporal features and corresponding similarity metric for video-based person re-identification.
Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification
Person re-identification is to seek a correct match for a person of interest across views among a large number of imposters.
Blind Image Deconvolution by Automatic Gradient Activation
We show here that a subset of the image gradients are adequate to estimate the blur kernel robustly, no matter the gradient image is sparse or not.
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Trace-norm regularization plays an important role in many areas such as machine learning and computer vision.
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
Feature matching is a key problem in computer vision and pattern recognition.
What's Wrong With That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution
The key observation motivating our approach is that "regular object" images, "unusual object" images and "other objects" images exhibit different region-level scores in terms of both the score values and the spatial distributions.
Bridging Category-level and Instance-level Semantic Image Segmentation
(iii) As the performance of semantic category segmentation has a significant impact on the instance-level segmentation, which is the second step of our approach, we train fully convolutional residual networks to achieve the best semantic category segmentation accuracy.
Ranked #52 on
Semantic Segmentation
on PASCAL Context
High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
(i) First, we evaluate different variations of a fully convolutional residual network so as to find the best configuration, including the number of layers, the resolution of feature maps, and the size of field-of-view.
Less is more: zero-shot learning from online textual documents with noise suppression
Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes.
Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
More specifically, we observe that given a set of object proposals extracted from an image that contains the object of interest, an accurate strongly supervised object detector should give high scores to only a small minority of proposals, and low scores to most of them.
Pushing the Limits of Deep CNNs for Pedestrian Detection
In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms.
Learning from Imbalanced Multiclass Sequential Data Streams Using Dynamically Weighted Conditional Random Fields
The present study introduces a method for improving the classification performance of imbalanced multiclass data streams from wireless body worn sensors.
Exploring Context with Deep Structured models for Semantic Segmentation
We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions.
Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution
To address this problem, we propose a novel approach by inspecting the distribution of the detection scores at multiple image regions based on the detector trained from the "regular object" and "other objects".
PersonNet: Person Re-identification with Deep Convolutional Neural Networks
In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification.
Compositional Model based Fisher Vector Coding for Image Classification
To handle this limitation, in this paper we break the convention which assumes that a local feature is drawn from one of few Gaussian distributions.
Structured learning of metric ensembles with application to person re-identification
However, seeking an optimal combination of visual features which is generic yet adaptive to different benchmarks is a unsoved problem, and metric learning models easily get over-fitted due to the scarcity of training data in person re-identification.
Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources
Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach.
Explicit Knowledge-based Reasoning for Visual Question Answering
We describe a method for visual question answering which is capable of reasoning about contents of an image on the basis of information extracted from a large-scale knowledge base.
Fast detection of multiple objects in traffic scenes with a common detection framework
The proposed framework consists of a dense feature extractor and detectors of three important classes.
Cross-convolutional-layer Pooling for Image Recognition
Most of these studies adopt activations from a single DCNN layer, usually the fully-connected layer, as the image representation.
Mining Mid-level Visual Patterns with Deep CNN Activations
The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative.
Image-based Recommendations on Styles and Substitutes
Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance.
Deeply Learning the Messages in Message Passing Inference
The network output dimension for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials.
What value do explicit high level concepts have in vision to language problems?
Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
Depth and Surface Normal Estimation From Monocular Images Using Regression on Deep Features and Hierarchical CRFs
Predicting the depth (or surface normal) of a scene from single monocular color images is a challenging task.
Learning Graph Structure for Multi-Label Image Classification via Clique Generation
Exploiting label dependency for multi-label image classification can significantly improve classification performance.
Robust Multiple Homography Estimation: An Ill-Solved Problem
The estimation of multiple homographies between two piecewise planar views of a rigid scene is often assumed to be a solved problem.
Part-Based Modelling of Compound Scenes From Images
We propose a method to recover the structure of a compound scene from multiple silhouettes.
Efficient SDP Inference for Fully-connected CRFs Based on Low-rank Decomposition
Conditional Random Fields (CRF) have been widely used in a variety of computer vision tasks.
A model-based approach to recovering the structure of a plant from images
We present a method for recovering the structure of a plant directly from a small set of widely-spaced images.
Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).
Learning to rank in person re-identification with metric ensembles
We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets evaluated.
Hashing on Nonlinear Manifolds
In addition, a supervised inductive manifold hashing framework is developed by incorporating the label information, which is shown to greatly advance the semantic retrieval performance.
The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification
This paper, however, advocates that if used appropriately convolutional layer activations can be turned into a powerful image representation which enjoys many advantages over fully-connected layer activations.
Worst-Case Linear Discriminant Analysis as Scalable Semidefinite Feasibility Problems
Our method is also much faster and more scalable than standard interior-point SDP solvers based WLDA.
Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications
Two standard relaxation methods are widely used for solving general BQPs--spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages.
Mid-level Deep Pattern Mining
We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used.
Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors
By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vector Coding (SCFVC).
Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed structured ensemble learning method with spatially pooled features.
Supervised Hashing Using Graph Cuts and Boosted Decision Trees
The proposed framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets.
Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference
We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inference problems.
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data.
Large-margin Learning of Compact Binary Image Encodings
The use of high-dimensional features has become a normal practice in many computer vision applications.
Deconstruction of compound objects from image sets
We propose a method to recover the structure of a compound object from multiple silhouettes.
A Hybrid Loss for Multiclass and Structured Prediction
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs).
Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations
We show that using Marginal Polytope Diagrams allows the number of constraints to be reduced without loosening the LP relaxations.
Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization
Different from most existing multi-class boosting methods, which use the same set of weak learners for all the classes, we train class specified weak learners (i. e., each class has a different set of weak learners).
Contextual Hypergraph Modelling for Salient Object Detection
In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions.
Online Unsupervised Feature Learning for Visual Tracking
Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications.
Efficient pedestrian detection by directly optimize the partial area under the ROC curve
We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning.
Characterness: An Indicator of Text in the Wild
In order to measure the characterness we develop three novel cues that are tailored for character detection, and a Bayesian method for their integration.
A General Two-Step Approach to Learning-Based Hashing
This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
A scalable stage-wise approach to large-margin multi-class loss based boosting
In this work, we propose a scalable and simple stage-wise multi-class boosting method, which also directly maximizes the multi-class margin.
Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty.
Part-Based Visual Tracking with Online Latent Structural Learning
Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking.
Learning Compact Binary Codes for Visual Tracking
A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes.
Fast Approximate L_infty Minimization: Speeding Up Robust Regression
Minimization of the $L_\infty$ norm, which can be viewed as approximately solving the non-convex least median estimation problem, is a powerful method for outlier removal and hence robust regression.
A Fast Semidefinite Approach to Solving Binary Quadratic Problems
Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods.
Asymmetric Pruning for Learning Cascade Detectors
In this work, we present a new approach to train an effective node classifier in a cascade detector.
StructBoost: Boosting Methods for Predicting Structured Output Variables
Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost.
