Sensing and machine learning for automotive perception: A review
Automotive perception involves understanding the external driving environment and the
internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving …
internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving …
Progressive meta-learning with curriculum
Meta-learning offers an effective solution to learn new concepts under scarce supervision
through an episodic-training scheme: a series of target-like tasks sampled from base classes …
through an episodic-training scheme: a series of target-like tasks sampled from base classes …
Point cloud domain adaptation via masked local 3d structure prediction
The superiority of deep learning based point cloud representations relies on large-scale
labeled datasets, while the annotation of point clouds is notoriously expensive. One of the …
labeled datasets, while the annotation of point clouds is notoriously expensive. One of the …
Occlusion-sensitive person re-identification via attribute-based shift attention
Occluded person re-identification is one of the most challenging tasks in security
surveillance. Most existing methods focus on extracting human body features from occluded …
surveillance. Most existing methods focus on extracting human body features from occluded …
AdaDC: Adaptive deep clustering for unsupervised domain adaptation in person re-identification
S Li, M Yuan, J Chen, Z Hu - … on Circuits and Systems for Video …, 2021 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) in person re-identification (re-ID) is a challenging
task, aiming to learn a model with labeled source data and unlabeled target data to …
task, aiming to learn a model with labeled source data and unlabeled target data to …
Complementary attention-driven contrastive learning with hard-sample exploring for unsupervised domain adaptive person re-id
Unsupervised domain adaptive (UDA) methods for person re-identification (Re-ID) aim to
transfer the knowledge of the labeled source domain to the unlabeled target domain without …
transfer the knowledge of the labeled source domain to the unlabeled target domain without …
Self-supervised video representation learning using improved instance-wise contrastive learning and deep clustering
Instance-wise contrastive learning (Instance-CL), which learns to map similar instances
closer and different instances farther apart in the embedding space, has achieved …
closer and different instances farther apart in the embedding space, has achieved …
Isometric propagation network for generalized zero-shot learning
Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few
attributes describing that class but no access to any training sample. A popular strategy is to …
attributes describing that class but no access to any training sample. A popular strategy is to …
Debiased contrastive curriculum learning for progressive generalizable person re-identification
T Gong, K Chen, L Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Domain generalization (DG) in person re-identification (ReID) is an extremely challenging
but essential task, which aims to learn a generalizable model over multiple labeled source …
but essential task, which aims to learn a generalizable model over multiple labeled source …
Semantic driven attention network with attribute learning for unsupervised person re-identification
Unsupervised domain adaptation (UDA) person re-identification (re-ID) aims to transfer
knowledge from a labeled source domain to guide the task proposed on the unlabeled …
knowledge from a labeled source domain to guide the task proposed on the unlabeled …