位置：成果数据库 > 会议 > 会议详情页
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
  • 所属机构名称：复旦大学
  • 会议名称：ACM Multimedia (ACM MM)
  • 时间：2015.10.1
  • 成果类型：会议
  • 相关项目：海量网络视频中的复杂事件检测技术研究
同会议论文项目
海量网络视频中的复杂事件检测技术研究
期刊论文 4 会议论文 18
同项目会议论文
Real-Time Summarization of User-Generated Videos Based on Semantic Recognition
Fudan-NJUST at MediaEval 2014: Violent Scenes Detection Using Deep Neural Networks
VSD2014: A Dataset for Violent Scenes Detection in Hollywood Movies and Web Videos
Which Looks Like Which: Exploring Inter-Class Relationships in Fine-Grained Visual Categorization
Understanding and Predicting Interestingness of Videos
Multiple Task Learning Using Iteratively Reweighted Least Square
Challenge Huawei Challenge: Fusing Multimodal Features with Deep Neural Networks for Mobile Video An
Optimal Bayesian Hashing for Efficient Face Recognition
EvaluatingTwo-Stream CNN for Video Classification
Fudan-Huawei at MediaEval 2015: Detecting Violent Scenes and Affective Impact in Movies with Deep Le
Predicting Emotions in User-Generated Videos
Benchmarking Violent Scenes Detection in Movies
VCDB: A Large-Scale Database for Partial Copy Detection in Videos
Exploring Inter-feature and Inter-class Relationships with Deep Neural Networks for Video Classifica
Beauty is Here: Evaluating Aesthetics in Videos Using Multimodal Features and Free Training Data
Organizing Video Search Results to Adapted Semantic Hierarchies for Topic-based Browsing
Fudan at MediaEval 2013: Violent Scenes Detection Using Motion Features and Part-Level Attributes