Affective image content analysis: Two decades review and new perspectives

S Zhao, X Yao, J Yang, G Jia, G Ding… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
Images can convey rich semantics and induce various emotions in viewers. Recently, with
the rapid advancement of emotional intelligence and the explosive growth of visual data …

Occluded prohibited items detection: An x-ray security inspection benchmark and de-occlusion attention module

Y Wei, R Tao, Z Wu, Y Ma, L Zhang, X Liu - Proceedings of the 28th ACM …, 2020 - dl.acm.org
Security inspection often deals with a piece of baggage or suitcase where objects are
heavily overlapped with each other, resulting in an unsatisfactory performance for prohibited …

Autodir: Automatic all-in-one image restoration with latent diffusion

Y Jiang, Z Zhang, T Xue, J Gu - European Conference on Computer Vision, 2024 - Springer
We present AutoDIR, an innovative all-in-one image restoration system incorporating latent
diffusion. AutoDIR excels in its ability to automatically identify and restore images suffering …

An end-to-end visual-audio attention network for emotion recognition in user-generated videos

S Zhao, Y Ma, Y Gu, J Yang, T **ng, P Xu… - Proceedings of the …, 2020 - ojs.aaai.org
Emotion recognition in user-generated videos plays an important role in human-centered
computing. Existing methods mainly employ traditional two-stage shallow pipeline, ie …

WSCNet: Weakly supervised coupled networks for visual sentiment classification and detection

D She, J Yang, MM Cheng, YK Lai… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
Automatic assessment of sentiment from visual content has gained considerable attention
with the increasing tendency of expressing opinions online. In this paper, we solve the …

Affective computing for large-scale heterogeneous multimedia data: A survey

S Zhao, S Wang, M Soleymani, D Joshi… - ACM Transactions on …, 2019 - dl.acm.org
The wide popularity of digital photography and social networks has generated a rapidly
growing volume of multimedia data (ie, images, music, and videos), resulting in a great …

Specific class center guided deep hashing for cross-modal retrieval

Z Shu, Y Bai, D Zhang, J Yu, Z Yu, XJ Wu - Information sciences, 2022 - Elsevier
Hashing approaches show excellent retrieval efficiency and low storage usage in search
tasks. In general, most existing deep hashing approaches mainly focus on constructing the …

Looking into gait for perceiving emotions via bilateral posture and movement graph convolutional networks

Y Zhai, G Jia, YK Lai, J Zhang, J Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Emotions can be perceived from a person's gait, ie, their walking style. Existing methods on
gait emotion recognition mainly leverage the posture information as input, but ignore the …

PDANet: Polarity-consistent deep attention network for fine-grained visual emotion regression

S Zhao, Z Jia, H Chen, L Li, G Ding… - Proceedings of the 27th …, 2019 - dl.acm.org
Existing methods on visual emotion analysis mainly focus on coarse-grained emotion
classification, ie assigning an image with a dominant discrete emotion category. However …

Deep cross-modal hashing with hashing functions and unified hash codes jointly learning

RC Tu, XL Mao, B Ma, Y Hu, T Yan… - … on Knowledge and …, 2020 - ieeexplore.ieee.org
Due to their high retrieval efficiency and low storage cost, cross-modal hashing methods
have attracted considerable attention. Generally, compared with shallow cross-modal …