Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras.
Ranked #5 on Person Re-Identification on MARS
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction.
Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID).
In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training.
Ranked #4 on Person Re-Identification on PRID2011
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion.
Ranked #2 on Vehicle Re-Identification on VeRi
This paper proposes a Temporal Complementary Learning Network that extracts complementary features of consecutive video frames for video person re-identification.
With back propagation, temporal knowledge can be transferred to enhance the image features and the information asymmetry problem can be alleviated.
Ranked #2 on Person Re-Identification on iLIDS-VID
How to explore the abundant spatial-temporal information in video sequences is the key to solve this problem.
The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest.
Ranked #1 on Person Re-Identification on PRID2011 (using extra training data)
Therefore, we propose a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch.