Search Results for author:
Found 12 papers, 5 papers with code
IFQA: Interpretable Face Quality Assessment
Existing face restoration models have relied on general assessment metrics that do not consider the characteristics of facial regions.
Spatio-channel Attention Blocks for Cross-modal Crowd Counting
Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings.
Loss-based Sequential Learning for Active Domain Adaptation
To solve these, we fully utilize pseudo labels of the unlabeled target domain by leveraging loss prediction.
Re-Aging GAN: Toward Personalized Face Age Transformation
Learned personalized age features are identity information that is recalibrated according to the target age.
Associative Partial Domain Adaptation
Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle.
Domain Adaptation without Source Data
Our key idea is to leverage a pre-trained model from the source domain and progressively update the target model in a self-learning manner.
Key Instance Selection for Unsupervised Video Object Segmentation
After M-th frame, we select K IDs based on video saliency and frequency of appearance; then only these key IDs are tracked through the remaining frames.
Cascaded Pyramid Network for 3D Human Pose Estimation Challenge
Over the past decade, there has been a growing interest in human pose estimation.
Doubly Nested Network for Resource-Efficient Inference
Slicing doubly nested network gives a working sub-network.
Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint
Up to now, only limited research has been conducted on cross-modal retrieval of suitable music for a specified video or vice versa.
Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
A fully connected layer is used to select the key frames and key segments, while the convolutional layer is used to describe them.
SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training.
