Advanced Topics in Computer Vision
Location: Building #3, Room 106
Time: Tuesday 10:10am-12pm (even weeks), Thursday 10:10am-12pm (every week)
Feb 23, 2017 Introduction
  • Course Introduction
  • Basics of Deep Neural Networks
Feb 28, 2017 Topic: Visual Recognition
  • Visual Recognition: Task Definition and Challenges
  • Bag-of-words Models
  • Spatial Pyramid Matching & Pyramid Match Kernel
March 2, 2017 Topic: Visual Recognition
  • Vocabulary Tree, Sparse Coding
  • Deep Learning for Visual Recognition: LeNet-5, AlexNet, VGG-16, GoogleNet, ResNet
March 9, 2017 Topic: Pixel Labeling
  • Pixel Labeling: Segmentation, Matting, Parsing
  • Unsupervised Image Segmentation: K-means, Mean-Shift, Normalized Cut
March 14, 2017 Topic: Pixel Labeling
  • Interactive Object Cutout: GraphCut, GrabCut, LazySnapping
  • Image Matting: Poisson Matting, Closed-Form Matting, Robust Color Sampling
March 23, 2017 Topic: Pixel Labeling
  • Image Co-segmentation
  • Image Inpainting / Image Completion
March 28, 2017 Topic: Pixel Labeling
  • Scene Parsing: Sparse Coding
  • Deep Pixel Labeling: FCN, DeepLab, SegNet, CNN-as-RNN
March 30, 2017 Topic: Object Detection
  • V-J Face Detector (Integral Image, AdaBoost, Cascade)
  • HOG+SVM with NMS
  • Deformable Part Model (DPM) for Pedestrian Detection
April 6, 2017 Topic: Object Detection
  • R-CNN
  • Fast R-CNN
  • Faster R-CNN
  • R-FCN
  • Multi-Scale R-CNN
April 11, 2017 Topic: Large-Scale Image Search
  • Dimension Reducation: PCA, CCA, Fisher LDA
  • Nonlinear Methods: MDS, ISOMAP, LLE
  • LPP, graph embedding
April 13, 2017 Topic: Large-Scale Image Search
  • Johnson Lindenstrauss lemma
  • The magic of hashing collision: Bloom Filter
  • Locality-Sensitive Hashing: the concept and proof of sublinear complexity in the STOC98 paper
  • LSH schemes for Hamming space, cosine similarity, Jaccard index (minHash)
April 20, 2017 Topic: Large-Scale Image Search
  • Spectral Hashing
  • ITQ
  • Semi-Supervsied Hashing
  • Supervised Hashing with Kernel
  • Deep Hashing
  • Discrete Hashing
  • Hashing for Large-Scale Machine Learning
April 25, 2017 Paper Presentation
  • Zhao Qijie, End-to-end Learning of Driving Models from Large-Scale Video Datasets, CVPR 2017
  • Song Sijie, Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition, CVPR 2016
  • Zhang Wenhao, Social LSTM: Human Trajectory Prediction in Crowded Spaces, CVPR 2016
April 27, 2017 Paper Presentation
  • Cui Rundong, Weakly Supervised Object Boundaries, CVPR 2016
  • Zhang Yichen, End-to-end Learning of Action Detection from Frame Glimpses in Videos, CVPR 2016
  • Yang Yibo, TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks, CVPR 2016
May 9, 2017 Paper Presentation
  • Yang Lingbo, k*-Nearest Neighbors: From Global to Local, NIPS 2016
  • Gao Xu, Instance-level Video Segmentation from Object Tracks, CVPR 2016
  • Zou Yixiong, End-to-End People Detection in Crowded Scenes, CVPR 2016
May 11, 2017 Topic: Video Computing
  • Introduction of Video Computing Tasks
  • Video Features (STIP, Deep Video, C3D, Trajectory Feature)
  • Deep Learning for Video Classification (multi-stream fusion techniques)
  • An Illustrative System for Video Classification
  • TRECVID Tasks (MED and Instance Search)
May 18, 2017 Topic: Reccurent Deep Networks
  • Unrolling Computational Graph
  • RNN variants (recurrent through output, sequence-input-single-output, teaching forcing, encoder-decoder, bi/quad-directional RNN etc.)
  • Generative RNN modeling
  • Back propagation through time (BPTT)
  • The issue and remedy for long-term dependency in RNN
  • Long short-term memory (LSTM)
  • Applications (image captioning, convLSTM for rainfall prediction, social LSTM)
May 23, 2017 Topic: Autonomous Vehicle
  • Past, Present, and Prospect
  • Funding, Challenges, and Benchmarks
  • DeepLanes
  • CCF-UISEE Traffic Sign Detection
  • End-to-End Driving Model
  • Deep Driving
May 25, 2017 Topic: Autonomous Vehicle
  • Localization by Visual Odometry
  • HMM based Driver Maneuver Prediction
  • Introduction to pytorch
June 1, 2017 Topic: Low-Rank Matrix Learning
  • Sparse Coding
  • Structural Sparsity for Computer Vision Applications
  • Robust PCA
  • Proximal Gradient Method
June 6, 2017 Course Project Presentation
  • Zhao Qijie, YouTube8M Video Classification
  • Yang Yibo, Saliency Detection
  • Song Sijie, Multi-Modality Action Recognition
June 8, 2017 Course Project Presentation
  • Zhang Yichen, Zou Yixiong, Person Re-Id.
  • Yang Lingbo, Gao Xu, Feature Aggregation and Compression
  • Zhang Wenhao, Cui Rundong, Intel & MobileODT Cervical Cancer Screening