Multi-object tracking with multiple cues and switcher-aware classification

W Feng, B Li, W Ouyang - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
cue is optimal, however, an identity issue happens. This identity issue are handled by including
multiple cues … In this work, we introduce a new method that combines multiple cues and …

Amplifying key cues for human-object-interaction detection

Y Liu, Q Chen, A Zisserman - European Conference on Computer Vision, 2020 - Springer
… image capture) as an auxiliary cue for HOI detection. Our approach is related to a … cue for
HOI detection in static images. In this sense, our method bridges static image HOI detection

Spatial-temporal multi-cue network for continuous sign language recognition

H Zhou, W Zhou, Y Zhou, H Li - Proceedings of the AAAI conference on …, 2020 - ojs.aaai.org
… -cue and intercue, which aims to preserve the uniqueness and explore the collaboration of
multiple cues. … a temporal multi-cue module composed of the intra-cue and inter-cue paths, …

Spatial-temporal multi-cue network for sign language recognition and translation

H Zhou, W Zhou, Y Zhou, H Li - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… from intra-cue and inter-cue perspectives to explore the collaboration of multiple cues. A …
designed to make the best of multi-cue sources for SL recognition and translation. To validate …

When person re-identification meets changing clothes

F Wan, Y Wu, X Qian, Y Chen… - … and pattern recognition …, 2020 - openaccess.thecvf.com
… a specific person (eg, a suspect) across multiple video surveillance … However, the depth cue
is only applicable in indoor … tities and 1-2 clothes per identity). iQIYI-VID [16] is a large scale …

Multi-camera multi-player tracking with deep player identification in sports video

R Zhang, L Wu, Y Yang, W Wu, Y Chen, M Xu - Pattern Recognition, 2020 - Elsevier
… representation for player identity in this paper. A robust multi-player tracker incorporating
with deep player identification is further developed to produce identity-coherent trajectories. …

Guided saliency feature learning for person re-identification in crowded scenes

L He, W Liu - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
… Our approach does not rely on any external cues during the inference term. … To obtain
better representation that only focuses on the person to be re-identified, we use a fully …

Identity-guided human semantic parsing for person re-identification

K Zhu, H Guo, Z Liu, M Tang, J Wang - … , Glasgow, UK, August 23–28, 2020 …, 2020 - Springer
… Most importantly, the identifiable personal belongings (eg, backpacks and reticule), which
are the potentially useful contextual cues for identifying a person, cannot be recognized by …

Unsupervised person re-identification via multi-label classification

D Wang, S Zhang - … computer vision and pattern recognition, 2020 - openaccess.thecvf.com
person may have multiple images in X, the initial label vector is not valid in representing person
identity cues… We use many data argumentation techniques to reinforce M. In other words, …

Cloth-changing person re-identification from a single image with gait prediction and regularization

X Jin, T He, K Zheng, Z Yin, X Shen… - … pattern recognition, 2022 - openaccess.thecvf.com
… To get temporal continuous motion cues from a single image, we design a Gait Sequence
Prediction (GSP) module for Gait-Stream to enrich gait information. Finally, a semantics …