微软邀请21位来自国内外计算机视觉领域学术界、工业界的优秀代表们分享了各自在CVPR 2017发表的最新研究和技术观点。
播放:12997次,课程ID:4230783
微软邀请21位来自国内外计算机视觉领域学术界、工业界的优秀代表们分享了各自在CVPR 2017发表的最新研究和技术观点。
--后摩尔定律时代的多媒体处理
--Style Bank: An Explicit Representation for Neural Image Style Transfer
--Awesome Typography and Awful Rain Removal
--Weakly Supervised Dense Video Captioning
--Image Captioning with Attributes
--Matrix Tri-Factorization with Manifold Regularization for Zero-shot Learning
--Collaborative Deep Reinforcement Learning for Joint Object Search
--Multiple Instance Detection Network with Online Instance Classifier Refinement
--Pyramid Scene Parsing Network
--Surveillance Video Parsing with Single Frame Supervision
--Agent in the Environment
--A Matrix Splitting Method for Composite Function Minimization
--Self-Paced Cotraining
--Fixed-Point Factorized Neural Network
--Consistent-Aware Deep Learning for Person Re-identification in a Camera Network
--Neural Aggregation Network for Video Face Recognition
--Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
--Spatiotemporal Pyramid Network for Video Action Recognition
--A Unified Framework for Event Retrieval, Recognition and Recounting
--Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval
--Cross-Modality Binary Code Learning via Fusion Similarity Hashing
No Teacher