
SelfSupervised Visual Attention Learning for Vehicle ReIdentification
Visual attention learning (VAL) aims to produce a confidence map as weig...
read it

RNN Training along Locally Optimal Trajectories via FrankWolfe Algorithm
We propose a novel and efficient training method for RNNs by iteratively...
read it

fGAIL: Learning fDivergence for Generative Adversarial Imitation Learning
Imitation learning (IL) aims to learn a policy from expert demonstration...
read it

LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation
Deep learning based LiDAR odometry (LO) estimation attracts increasing r...
read it

TreeRNN: TopologyPreserving Deep GraphEmbedding and Learning
In contrast to the literature where the graph local patterns are capture...
read it

Automatic Building and Labeling of HD Maps with Deep Learning
In a world where autonomous driving cars are becoming increasingly more ...
read it

Learning to Segment 3D Point Clouds in 2D Image Space
In contrast to the literature where local patterns in 3D point clouds ar...
read it

SelfOrthogonality Module: A Network Architecture Plugin for Learning Orthogonal Filters
In this paper, we investigate the empirical impact of orthogonality regu...
read it

GraphPreserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
Graph convolutional networks (GCNs) suffer from the irregularity of grap...
read it

WhiteBox Adversarial Defense via SelfSupervised Data Estimation
In this paper, we study the problem of how to defend classifiers against...
read it

Towards Learning AffineInvariant Representations via DataEfficient CNNs
In this paper we propose integrating a priori knowledge into both design...
read it

Unsupervised Deep Feature Transfer for Low Resolution Image Classification
In this paper, we propose a simple while effective unsupervised deep fea...
read it

RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Recurrent neural networks (RNNs) are particularly wellsuited for modeli...
read it

RNNs Evolving in Equilibrium: A Solution to the Vanishing and Exploding Gradients
Recurrent neural networks (RNNs) are particularly wellsuited for modeli...
read it

Random Tensors and their Normal Distributions
The main purpose of this paper is to introduce the random tensor with no...
read it

Verification of Very LowResolution Faces Using An IdentityPreserving Deep Face SuperResolution Network
Face superresolution methods usually aim at producing visually appealin...
read it

TimeDelay Momentum: A Regularization Perspective on the Convergence and Generalization of Stochastic Momentum for Deep Learning
In this paper we study the problem of convergence and generalization err...
read it

Equilibrated Recurrent Neural Network: Neuronal TimeDelayed SelfFeedback Improves Accuracy and Stability
We propose a novel Equilibrated Recurrent Neural Network (ERNN) to comb...
read it

Deformable Part Networks
In this paper we propose novel Deformable Part Networks (DPNs) to learn ...
read it

LMKLNet: A Fast Localized Multiple Kernel Learning Solver via Deep Neural Networks
In this paper we propose solving localized multiple kernel learning (LMK...
read it

Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks
By lifting the ReLU function into a higher dimensional space, we develop...
read it

BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
Understanding the global optimality in deep learning (DL) has been attra...
read it

Learning Joint Feature Adaptation for ZeroShot Recognition
Zeroshot recognition (ZSR) aims to recognize targetdomain data instanc...
read it

RealTime Visual Tracking: Promoting the Robustness of Correlation Filter Learning
Correlation filtering based tracking model has received lots of attentio...
read it

Efficient Training of Very Deep Neural Networks for Supervised Hashing
In this paper, we propose training very deep neural networks (DNNs) for ...
read it

ZeroShot Learning via Joint Latent Similarity Embedding
Zeroshot recognition (ZSR) deals with the problem of predicting class l...
read it

Sequential Optimization for Efficient HighQuality Object Proposal Generation
We are motivated by the need for a generic object proposal generation al...
read it

Group Membership Prediction
The group membership prediction (GMP) problem involves predicting whethe...
read it

ZeroShot Learning via Semantic Similarity Embedding
In this paper we consider a version of the zeroshot learning problem wh...
read it

A Novel Visual Word Cooccurrence Model for Person Reidentification
Person reidentification aims to maintain the identity of an individual ...
read it

Object Proposal Generation using TwoStage Cascade SVMs
Object proposal algorithms have shown great promise as a first step for ...
read it

PRISM: Person ReIdentification via Structured Matching
Person reidentification (reid), an emerging problem in visual surveill...
read it

Regularization for Multiple Kernel Learning via SumProduct Networks
In this paper, we are interested in constructing general graphbased reg...
read it
Ziming Zhang
is this you? claim profile
Research Scientist at Mitsubishi Electric Research Laboratories (MERL)