• Publications
  • Influence
Domain Adaptive Faster R-CNN for Object Detection in the Wild
TLDR
We build an end-to-end deep learning model based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. Expand
  • 280
  • 77
  • PDF
Semantic Foggy Scene Understanding with Synthetic Data
TLDR
This work addresses the problem of semantic foggy scene understanding (SFSU). Expand
  • 195
  • 58
  • PDF
Fast Optical Flow Using Dense Inverse Search
TLDR
We propose a solution with very low time complexity and competitive accuracy for the computation of dense optical flow estimation for real-time applications. Expand
  • 172
  • 16
  • PDF
Jointly Optimized Regressors for Image Super‐resolution
TLDR
We jointly learn a collection of regressors, which collectively yield the smallest super‐resolving error for all training data. Expand
  • 128
  • 15
  • PDF
Ensemble Projection for Semi-supervised Image Classification
  • Dengxin Dai, L. Gool
  • Mathematics, Computer Science
  • IEEE International Conference on Computer Vision
  • 1 December 2013
This paper investigates the problem of semi-supervised classification. Unlike previous methods to regularize classifying boundaries with unlabeled data, our method learns a new image representationExpand
  • 78
  • 13
  • PDF
Unified Hypersphere Embedding for Speaker Recognition
TLDR
We improve the identification and verification accuracy of a text-independent speaker recognition system without use of extra data or deeper and more complex models by augmenting the training data, finding the optimal dimensionality of embedding space and use of more discriminative loss functions. Expand
  • 48
  • 11
  • PDF
Latent Dictionary Learning for Sparse Representation Based Classification
TLDR
We propose a novel latent dictionary learning (LDL) method to learn a discriminative dictionary and build its relationship to class labels adaptively. Expand
  • 111
  • 10
  • PDF
Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation
TLDR
This letter presents a method for Satellite image classification aiming at the following two objectives: 1) involving visual attention into the satellite image classification; biologically inspired saliency information is exploited in the phase of the image representation, making our method more concentrated on the interesting objects and structures. Expand
  • 144
  • 10
  • PDF
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners
TLDR
We investigate the problem in a realistic setting, which consists of a surround-view camera system with eight cameras, a route planner, and a CAN bus reader. Expand
  • 81
  • 9
  • PDF
Fast Algorithms for Linear and Kernel SVM+
TLDR
The SVM+ approach has shown excellent performance in visual recognition tasks for exploiting privileged information in the training data, and not available during the test stage. Expand
  • 27
  • 9
  • PDF