Accepting PhD Students

PhD projects

Vision and language, 3D vision

19982020

Research output per year

If you made any changes in Pure these will be visible here soon.

Research Output

Filter
Article
2020

Disentangled human body embedding based on deep hierarchical neural network

Jiang, B., Zhang, J., Cai, J. & Zheng, J., 1 Aug 2020, In : IEEE Transactions on Visualization and Computer Graphics. 26, 8, p. 2560-2575 16 p.

Research output: Contribution to journalArticleResearchpeer-review

JÂA-Net: joint facial action unit detection and face alignment via adaptive attention

Shao, Z., Liu, Z., Cai, J. & Ma, L., 10 Sep 2020, (Accepted/In press) In : International Journal of Computer Vision. 20 p.

Research output: Contribution to journalArticleResearchpeer-review

Large-scale heteroscedastic regression via Gaussian process

Liu, H., Ong, Y-S. & Cai, J., 7 Apr 2020, (Accepted/In press) In : IEEE Transactions on Neural Networks and Learning Systems. 14 p.

Research output: Contribution to journalArticleResearchpeer-review

Portable food-freshness prediction platform based on colorimetric barcode combinatorics and deep convolutional neural networks

Guo, L., Wang, T., Wu, Z., Wang, J., Wang, M., Cui, Z., Ji, S., Cai, J., Xu, C. & Chen, X., 1 Oct 2020, (Accepted/In press) In : Advanced Materials. 8 p.

Research output: Contribution to journalArticleResearchpeer-review

Recovering facial reflectance and geometry from multi-view images

Song, G., Zheng, J., Cai, J. & Cham, T. J., Apr 2020, In : Image and Vision Computing. 96, 11 p., 103897.

Research output: Contribution to journalArticleResearchpeer-review

When Gaussian process meets big data: a review of scalable GPs

Liu, H., Ong, Y-S., Shen, X. & Cai, J., 7 Jan 2020, (Accepted/In press) In : IEEE Transactions on Neural Networks and Learning Systems. 19 p.

Research output: Contribution to journalArticleOtherpeer-review

2019

CNN-Based real-time dense face reconstruction with inverse-rendered photo-realistic face images

Guo, Y., Zhang, J., Cai, J., Jiang, B. & Zheng, J., 1 Jun 2019, In : IEEE Transactions on Pattern Analysis and Machine Intelligence. 41, 6, p. 1294-1307 14 p.

Research output: Contribution to journalArticleResearchpeer-review

20 Citations (Scopus)

Conditional adversarial synthesis of 3D facial action units

Liu, Z., Song, G., Cai, J., Cham, T-J. & Zhang, J., 25 Aug 2019, In : Neurocomputing. 355, p. 200-208 9 p.

Research output: Contribution to journalArticleResearchpeer-review

3 Citations (Scopus)

Decoupled spatial neural attention for weakly supervised semantic segmentation

Zhang, T., Lin, G., Cai, J., Shen, T., Shen, C. & Kot, A. C., Nov 2019, In : IEEE Transactions on Multimedia. 21, 11, p. 2930-2941 12 p., 8705324.

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Efficient video object co-localization with co-saliency activated tracklets

Jerripothula, K. R., Cai, J. & Yuan, J., Mar 2019, In : IEEE Transactions on Circuits and Systems for Video Technology. 29, 3, p. 744-755 12 p., 8290832.

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Exploiting web images for weakly supervised object detection

Tao, Q., Yang, H. & Cai, J., May 2019, In : IEEE Transactions on Multimedia. 21, 5, p. 1135-1146 12 p., 8489885.

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Facial action unit detection using attention and relation learning

Shao, Z., Liu, Z., Cai, J., Wu, Y. & Ma, L., 23 Oct 2019, In : IEEE Transactions on Affective Computing.

Research output: Contribution to journalArticleResearchpeer-review

Keypoint based weakly supervised human parsing

Wu, Z., Lin, G. & Cai, J., Nov 2019, In : Image and Vision Computing. 91, 10 p., 0103801.

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Learning local feature representation from matching, clustering and spatial transform

Mei, J., Jiang, X. & Cai, J., Aug 2019, In : Journal of Visual Communication and Image Representation. 63, 10 p., 102601.

Research output: Contribution to journalArticleResearchpeer-review

Shading-based surface recovery using subdivision-based representation

Deng, T., Zheng, J., Cai, J. & Cham, T-J., 20 Sep 2019, In : Computer Graphics Forum. 38, 1, p. 417-428 12 p.

Research output: Contribution to journalArticleResearchpeer-review

Open Access
File

Understanding and comparing scalable Gaussian process regression for big data

Liu, H., Cai, J., Ong, Y-S. & Wang, Y., Jan 2019, In : Knowledge-Based Systems. 164, p. 324-335 12 p.

Research output: Contribution to journalArticleResearchpeer-review

2 Citations (Scopus)

Unsupervised dense Light Field reconstruction with occlusion awareness

Ni, L., Jiang, H., Cai, J., Zheng, J., Li, H. & Liu, X., Oct 2019, In : Computer Graphics Forum. 38, 7, p. 425-436 12 p.

Research output: Contribution to journalArticleResearchpeer-review

Visibility constrained generative model for depth-based 3D facial pose tracking

Sheng, L., Cai, J., Cham, T-J., Pavlovic, V. & Ngan, K. N., 1 Aug 2019, In : IEEE Transactions on Pattern Analysis and Machine Intelligence. 41, 8, p. 1994-2007 14 p., 8502935.

Research output: Contribution to journalArticleResearchpeer-review

3 Citations (Scopus)

Zero-shot learning via category-specific visual-semantic mapping and label refinement

Niu, L., Cai, J., Veeraraghavan, A. & Zhang, L., Feb 2019, In : IEEE Transactions on Image Processing. 28, 2, p. 965-979 15 p., 8476580.

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)
2018

An adaptive RBF-HDMR modeling approach under limited computational budget

Liu, H., Hervas, J-R., Ong, Y-S., Cai, J. & Wang, Y., Mar 2018, In : Structural and Multidisciplinary Optimization. 57, 3, p. 1233-1250 18 p.

Research output: Contribution to journalArticleResearchpeer-review

15 Citations (Scopus)

An exemplar-based multi-view domain generalization framework for visual recognition

Niu, L., Li, W., Xu, D. & Cai, J., Feb 2018, In : IEEE Transactions on Neural Networks and Learning Systems. 29, 2, p. 259-272 14 p., 7733141.

Research output: Contribution to journalArticleResearchpeer-review

11 Citations (Scopus)

Cope with diverse data structures in multi-fidelity modeling: a Gaussian process method

Liu, H., Ong, Y-S., Cai, J. & Wang, Y., Jan 2018, In : Engineering Applications of Artificial Intelligence. 67, p. 211-225 15 p.

Research output: Contribution to journalArticleResearchpeer-review

18 Citations (Scopus)

LETRIST: Locally Encoded TRansform feature hISTtogram for rotation-invariant texture classification

Song, T., Li, H., Meng, F., Wu, Q. & Cai, J., Jul 2018, In : IEEE Transactions on Circuits and Systems for Video Technology. 28, 7, p. 1565-1579 15 p.

Research output: Contribution to journalArticleResearchpeer-review

35 Citations (Scopus)

Optimizing quality of experience for Adaptive Bitrate streaming via viewer interest inference

Gao, G., Zhang, H., Hu, H., Wen, Y., Cai, J., Luo, C. & Zeng, W., Dec 2018, In : IEEE Transactions on Multimedia. 20, 12, p. 3399-3413 15 p., 8361841.

Research output: Contribution to journalArticleResearchpeer-review

9 Citations (Scopus)

Quality-guided fusion-based co-saliency estimation for image co-segmentation and colocalization

Jerripothula, K. R., Cai, J. & Yuan, J., Sep 2018, In : IEEE Transactions on Multimedia. 20, 9, p. 2466-2477 12 p., 8269367.

Research output: Contribution to journalArticleResearchpeer-review

9 Citations (Scopus)

Recent advances in convolutional neural networks

Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J. & Chen, T., May 2018, In : Pattern Recognition. 77, p. 354-377 24 p.

Research output: Contribution to journalArticleResearchpeer-review

608 Citations (Scopus)

Remarks on multi-output Gaussian process regression

Liu, H., Cai, J. & Ong, Y. S., 15 Mar 2018, In : Knowledge-Based Systems. 144, p. 102-121 20 p.

Research output: Contribution to journalArticleResearchpeer-review

20 Citations (Scopus)

Seeds-based part segmentation by seeds propagation and region convexity decomposition

Meng, F., Li, H., Wu, Q., Ngan, K. N. & Cai, J., Feb 2018, In : IEEE Transactions on Multimedia. 20, 2, p. 310-322 13 p., 8010462.

Research output: Contribution to journalArticleResearchpeer-review

6 Citations (Scopus)

Shading-based surface detail recovery under general unknown illumination

Xu, D., Duan, Q., Zheng, J., Zhang, J., Cai, J. & Cham, T. J., 1 Feb 2018, In : IEEE Transactions on Pattern Analysis and Machine Intelligence. 40, 2, p. 423-436 14 p., 7858760.

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Structure-aware multimodal feature fusion for RGB-D scene classification and beyond

Wang, A., Cai, J., Lu, J. & Cham, T. J., May 2018, In : ACM Transactions on Multimedia Computing, Communications, and Applications. 14, 2, 22 p., 39.

Research output: Contribution to journalArticleResearchpeer-review

Towards efficient resource allocation for heterogeneous workloads in IaaS clouds

Wei, L., Foh, C. H., He, B. & Cai, J., Mar 2018, In : IEEE Transactions on Cloud Computing. 6, 1, p. 264-275 12 p.

Research output: Contribution to journalArticleResearchpeer-review

25 Citations (Scopus)
2017

An adaptive sampling approach for Kriging metamodeling by maximizing expected prediction error

Liu, H., Cai, J. & Ong, Y-S., 2 Nov 2017, In : Computers and Chemical Engineering. 106, p. 171-182 12 p.

Research output: Contribution to journalArticleResearchpeer-review

36 Citations (Scopus)

Delay-optimized file retrieval under LT-based cloud storage

Lu, H., Foh, C. H., Wen, Y. & Cai, J., Oct 2017, In : IEEE Transactions on Cloud Computing. 5, 4, p. 656-666 11 p.

Research output: Contribution to journalArticleResearchpeer-review

Multiple consumer-grade depth camera registration using everyday objects

Deng, T., Cai, J., Cham, T. J. & Zheng, J., Jun 2017, In : Image and Vision Computing. 62, p. 1-7 7 p.

Research output: Contribution to journalArticleResearchpeer-review

2 Citations (Scopus)

QoS-aware resource allocation for video transcoding in clouds

Wei, L., Cai, J., Foh, C. H. & He, B., Jan 2017, In : IEEE Transactions on Circuits and Systems for Video Technology. 27, 1, p. 49-61 13 p., 7508389.

Research output: Contribution to journalArticleResearchpeer-review

35 Citations (Scopus)

Semi-supervised manifold-embedded hashing with joint feature representation and classifier learning

Song, T., Cai, J., Zhang, T., Gao, C., Meng, F. & Wu, Q., Aug 2017, In : Pattern Recognition. 68, p. 99-110 12 p.

Research output: Contribution to journalArticleResearchpeer-review

15 Citations (Scopus)

Using 3D face priors for depth recovery

Chen, C., Pham, H. X., Pavlovic, V., Cai, J., Shi, G., Gao, Y. & Cheng, H., Oct 2017, In : Journal of Visual Communication and Image Representation. 48, p. 16-29 14 p.

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

vCache: supporting cost-efficient Adaptive bitrate streaming

Gao, G., Wen, Y. & Cai, J., 2017, In : IEEE Multimedia. 24, 3, p. 19-27 9 p.

Research output: Contribution to journalArticleResearchpeer-review

9 Citations (Scopus)

vCache: supporting cost-efficient Adaptive Bitrate Streaming via NFV-based virtual caching

Gao, G., Wen, Y. & Cai, J., 2017, In : IEEE Multimedia. 24, 3, p. 19-27 6 p.

Research output: Contribution to journalArticleOtherpeer-review

1 Citation (Scopus)

Visual recognition by earning from Web data via weakly supervised domain generalization

Niu, L., Li, W., Xu, D. & Cai, J., Sep 2017, In : IEEE Transactions on Neural Networks and Learning Systems. 28, 9, p. 1985-1999 15 p.

Research output: Contribution to journalArticleResearchpeer-review

10 Citations (Scopus)
2016

Action recognition in still images with minimum annotation efforts

Yu, Z., Li, C., Wu, J., Cai, J., Do, M. N. & Lu, J., Nov 2016, In : IEEE Transactions on Image Processing. 25, 11, p. 5479-5490 12 p.

Research output: Contribution to journalArticleResearchpeer-review

33 Citations (Scopus)

Beyond pixels: a comprehensive survey from bottom-up to semantic image segmentation and cosegmentation

Zhu, H., Meng, F., Cai, J. & Lu, S., Jan 2016, In : Journal of Visual Communication and Image Representation. 34, p. 12-27 16 p.

Research output: Contribution to journalArticleResearchpeer-review

121 Citations (Scopus)

Compact representation of high-dimensional feature vectors for large-scale image recognition and retrieval

Zhang, Y., Wu, J. & Cai, J., May 2016, In : IEEE Transactions on Image Processing. 25, 5, p. 2407-2419 13 p.

Research output: Contribution to journalArticleResearchpeer-review

12 Citations (Scopus)

Cosegmentation of multiple image groups

Meng, F., Cai, J. & Li, H., May 2016, In : Computer Vision and Image Understanding. 146, p. 67-76 10 p.

Research output: Contribution to journalArticleResearchpeer-review

23 Citations (Scopus)

Image co-segmentation via saliency co-fusion

Jerripothula, K. R., Cai, J. & Yuan, J., Sep 2016, In : IEEE Transactions on Multimedia. 18, 9, p. 1896-1909 14 p.

Research output: Contribution to journalArticleResearchpeer-review

54 Citations (Scopus)

Multiple human identification and cosegmentation: a human-oriented CRF approach with poselets

Zhu, H., Lu, J., Cai, J., Zheng, J., Lu, S. & Thalmann, N. M., Aug 2016, In : IEEE Transactions on Multimedia. 18, 8, p. 1516-1530 15 p.

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Weakly supervised fine-grained categorization with part-based image representation

Zhang, Y., Wei, X. S., Wu, J., Cai, J., Lu, J., Nguyen, V. A. & Do, M. N., Apr 2016, In : IEEE Transactions on Image Processing. 25, 4, p. 1713-1725 13 p.

Research output: Contribution to journalArticleResearchpeer-review

84 Citations (Scopus)
2015

A low complexity interest point detector

Chen, J., Duan, L. Y., Gao, F., Cai, J., Kot, A. C. & Huang, T., Feb 2015, In : IEEE Signal Processing Letters. 22, 2, p. 172-176 5 p., 6891221.

Research output: Contribution to journalArticleResearchpeer-review

7 Citations (Scopus)

Compressive environment matting

Duan, Q., Cai, J. & Zheng, J., Dec 2015, In : Visual Computer. 31, 12, p. 1587-1600 14 p.

Research output: Contribution to journalArticleResearchpeer-review

Open Access
File
4 Citations (Scopus)

Hybrid collision-free medium access (HCFMA) protocol for underwater acoustic networks: Design and Performance Evaluation

Yang, M., Gao, M., Foh, C. H. & Cai, J., Apr 2015, In : IEEE Journal of Oceanic Engineering. 40, 2, p. 292-302 11 p., 6799272.

Research output: Contribution to journalArticleResearchpeer-review

6 Citations (Scopus)