Research
I am broadly interested in artificial intelligence, computer vision, and their applications to other academic fields.
|
|
Memory-Guided Normality Patterns Representation Matching for Unsupervised Video Anomaly Detection
Yiran Tao, Yaosi Hu, Zhenzhong Chen
In submission
We address the UVAD problem with a novel idea that aligns with the essence of UVAD: to directly compare events in videos and detect anomalies based on events’ similarities with others.
|
|
Temporal Weighting Appearance-Aligned Network for Nighttime Video Retrieval
Weijian Ruan*, Yiran Tao*, Linjun Ruan, Xiujun Shu, Yu Qiao
IEEE Signal Processing Letters
We build dataset for a novel task, namely video-based person re-identification during nighttime, and propose a temporal weighting appearance-aligned model to tackle this task.
|
|
Learn to Look Around: Deep Reinforcement Learning Agent for Video Saliency Prediction
Yiran Tao, Yaosi Hu, Zhenzhong Chen
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2021
We propose a deep reinforcement learning agent that generates a window of frames containing the most highly correlated information for saliency prediction for each video frame, which assists backbone models to extract temporal information and promotes their performance.
|
|