talk-learning

TODO

• 基于视频的时序建模与动作识别<Talk>
  Keywords:ARTNet, TSN, UntrimmedNet

• Squeeze-and-Excitation Networks<Talk>

• 基于光流的视频语义分割和物体检测<Talk>
  Keywords:Opital flow, Feature propagation(特征传播), Feature aggregation

• From Faster R-CNN to Mask R-CNN<Talk>
  Key function: Classification, Location, Mask(per pixel) classification, Lanmarks location

• 理解和利用CNN的内部表征<Talk>
  Outlines: Visualizing the internal units & Weakly supervised localization and class-specific saliency
  Keywords:: 神经元响应，内部表征，物体表征，可视化，可解释性

• 深度图像检索前沿技术与实际应用<Talk>
  Defining Image Retrieval: Given an image query, generate a rank of all similar images.
  Defining instance retrieval: Given a target object of image query, generate a rank of all images containing the target object.
  Retrieval pipeline: Query image—Image Representations—Image Matching—Ranking List—Spatial Re-ranking/Query Expansion

• 自动驾驶中的视觉技术<Talk>
  Levels of Driving: L1-L5
  Techniques(L3): High precision map/LiDAR
  Outlines: Stereo/Motion/Detection&Tracking/Scene Understanding/Localization and Mapping(SLAM)