M
Mingwen Wang
Researcher at Jiangxi Normal University
Publications - 12
Citations - 50
Mingwen Wang is an academic researcher from Jiangxi Normal University. The author has contributed to research in topics: Object detection & Eye tracking. The author has an hindex of 4, co-authored 12 publications receiving 35 citations.
Papers
More filters
Journal ArticleDOI
Real-Time Deep Tracking via Corrective Domain Adaptation
TL;DR: This paper proposes to transfer the deep feature, which is learned originally for image classification to the visual tracking domain, via some “grafted” auxiliary networks, which improves the tracking performance significantly both on accuracy and efficiency.
Proceedings ArticleDOI
Deep tracking with objectness
TL;DR: The proposed algorithm, termed Deep-Track with Objectness (DTO), naturally combines the state-of-the-art deep-learning-based detectors and trackers, which essentially share a large part of the network.
Book ChapterDOI
Learning Hough Transform with Latent Structures for Joint Object Detection and Pose Estimation
TL;DR: A novel max-margin Hough transform with latent structure for joint object detection and pose estimation and adopts a multiple instance learning approach to handle the lack of correspondence among training instances with noisy bounding-box labels.
Journal ArticleDOI
Modeling Monolingual Character Alignment for Automatic Evaluation of Chinese Translation
TL;DR: It is shown that it is important to allow different characters to match in the evaluation of Chinese translations and that the IHMM is a reasonable approach for the alignment of Chinese characters.
Journal ArticleDOI
Learning Discriminative Representations for Semantic Cross Media Retrieval
TL;DR: Two effective methods are proposed to mine semantic correlations in crossmodal semantic features that can be retrieved across different modalities based on a flexible “feature up-lifting and down projecting” mechanism.