2015 summer seminar


VIPA 2015 Summer Seminar


Li Sun:

  1. Leveraging Stereo Matching With Learning-Based Confidence Measures
  2. Learning Deep Structured Models
  3. Dependent nonparametric trees for dynamic hierarchical clustering


  1. Semantic part segmentation using compositional model combining shap and appearance
  2. Hypercolumns for object segmentation and Fine-grained localization
  3. Learning to Detect motion boundaries

Jie Lei

  1. Salient Object Detection via Bootstrap Learning
  2. Superpixel-based Video Object Segmentation using Perceptual Organization and Location Prior
  3. Global Refinement of Random Forest


Shan Gao

  1. Supervised Discrete Hashing
  2. Weakly Supervised Object Detection with Convex Clustering
  3. Face Video Retrieval with Image Query via Hashing across Euclidean Space and Riemannian Manifold

Qiao Luan

  1. Recurrent Convolutional Neural Network for Object Recognition
  2. Efficient Object Localization Using Convolutional Networksr
  3. Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks

Jingrun Sun

  1. What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions?Mihir Jain, Jan C. van Gemert, Cees G. M. Snoek
  2. Deep Edge-Aware Filters
  3. Saliency Detection via Cellular Automata


Zunlei Feng

  1. Oriented Edge Forests for Boundary Detection
  2. Second-Order Constrained Parametric Proposals and Sequential Search-Based Structured Prediction for Semantic Segmentation in RGB-D Images
  3. Understanding Classifier Errors by Examining Influential Neighbors

Zhengyang Wang

  1. Neuroaesthetics in Fashion: Modeling the Perception of Fashionability
  2. Modeling Local and Global Deformations in Deep Learning: Epitomic
    Convolution, Multiple Instance Learning, and Sliding Window Detection
  3. Depth from Focus with Your Mobile Phone


BinBin Tang

  1. An Improved Deep Learning Architecture for Person Re-Identification
  2. DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
  3. Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

Keyao Zhang

  1. On the Relationship between Visual Attributes and Convolutional Networks
  2. Expanding Object Detector’s HORIZON: Incremental Learning Framework for Object Detection in Videos
  3. Hashing with Binary Autoencoders

Xinhui Song

  1. DEEP-CARVING : Discovering Visual Attributes by Carving Deep Neural Nets
  2. Going Deeper with Convolutions
  3. Learning a Non-linear Knowledge Transfer Model for Cross-View Action Recognition


Huamou Qiu

  1. Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals
  2. Combination Features and Models for Human Detection
  3. Model Recommendation: Generating Object Detectors from Few Samples

Xingchen Zhou

  1. DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection
  2. DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
  3. Viewpoints and Keypoints