SFU Multimedia Lab was founded in the early 1990’s by the late Dr. Jacques Vaisey, as the Image Communication Laboratory. Over the years, it has evolved into the Multimedia Lab, to reflect the breadth of the research being undertaken. Our work spans multimedia signal processing, compression, communications, multimedia ergonomics, analytics, and AI. Our research has won numerous recognitions and has impacted research directions, technology trends and international standards, particularly in image and video compression. We strive to attract top students from around the world and to offer them the best possible training grounded in strong foundations. Our students have won numerous national and international awards, and are highly sought after by employers.
Multimedia Signal Processing
Images, video, speech, audio, point clouds, light and sound fields… useful information is buried in these signals. We study and develop methods to efficiently sample and represent these signals, remove noise from them, compress them, and recover their missing pieces.
Multimedia Intelligence
Beyond low-level multimedia processing, we explore how to interptret and extract meaningful insights from complex multimedia signals using machine learning and artificial intelligence techniques. We also study and develop methods for distributing such computations across multiple sensors, devices, and clouds.
Multimedia Communications
With the likes of Netflix, Spotify, and Zoom, multimedia communications have become mainstream. But achieving dependable real-time transfer of multimedia signals is still full of challenges. We create techniques for error-resilient coding, power and resource management, and error control, to enable efficient and reliable multimedia communications.
Multimedia Ergonomics
The word ergonomics probably makes you think about comfortable chairs. But physical objects are not the only things we interact with. You likely spend a good portion of each day looking at images or video, listening to music, or browsing websites. Are these digital objects comfortable? We want to understand how people interact with digital objects, especially multimedia signals, in order to facilitate better user experience and interaction with our digital environment.
RECENT PUBLICATIONS
B. Azizian and I. V. Bajić, “Prompt-guided prefiltering for VLM image compression,” ICME 2026, Bangkok, Thailand. [arXiv]
A. de Andrade, A. Harell, and I. V. Bajić, “Lossy common information in a learnable Gray-Wyner network,” ICLR 2026, Rio de Janeiro, Brazil. [arXiv]
M. Khairi Atani, A. Harell, H. Choi, R. Yang, F. Racapé, and I. V. Bajić, "How universal are SAM2 features?" PCS 2025, Aachen, Germany. [arXiv]
H. Fu, J. Liang, Z. Fang, J. Han, “SELIC: Semantic-Enhanced Learned Image Compression via High-Level Textual Guidance”, ICME 2025, Nantes, France. [arXiv]
A. Harell, Y. Foroutan, N. Ahuja, P. Datta, B. Kanzariya, V. S. Somayazulu, O. Tickoo, A. de Andrade, and I. V. Bajić, “Rate-distortion theory in coding for machines and its application,” TPAMI 2025. [arXiv]
C. Dinesh, G. Cheung, S. Bagheri, and I. V. Bajić, "Efficient signed graph sampling via balancing & Gershgorin disc perfect alignment," TPAMI 2025. [arXiv]
H. Fu, F. Liang, J. Liang, Y. Wang, Z. Fang, G. Zhang, and J. Han, “Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation,” TIP 2024. [arXiv]
H. Fu, J. Liang, Z. Fang, J. Han, F. Liang, and G. Zhang, “WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model,” ECCV 2024, Milano, Italy. [arXiv]
NEWS
Alon Harell wins inaugural IEEE SPS Scholarship, Nov. 2023. [IEEE]
Dr. Hyomin Choi wins Governor General's Gold Medal, Jun. 2023. [SFU News]
SFU Multimedia Lab paper wins the 2023 IEEE TCSVT Best Paper Award, May 2023. [IEEE CASS website]
SFU Multimedia Lab paper wins IEEE MSA-TC Best Paper Award, May 2023. [Certificate]
SFU Multimedia Lab paper receives Best Paper Runner-Up Award at MMSP 2022, Sep. 2022. [Certificate]
Prof. Jie Liang elected Fellow of the Canadian Academy of Engineering, Jun. 2022. [CAE website]
Dr. Chinthaka Dinesh wins Governor General's Gold Medal, Jun. 2022. [SFU News]
SFU Multimedia Lab paper among Best Student Paper Finalists at Asilomar 2020, Nov. 2020. [Asilomar 2020]
SFU Multimedia Lab student's paper among Best Paper Finalists at IEEE ICME 2020, another student wins Outstanding Reviewer Award, Jul. 2020. [ICME 2020]
SFU Multimedia Lab paper wins Best Student Paper Award at IEEE ICIP 2019, Oct. 2019.[Certificate]
PEOPLE
Anderson de Andrade
Ph.D. Student
Bardia Azizian
Ph.D. Student
Ivan V. Bajić
Professor
Samantha Betts
Research Associate
Haisheng Fu
Post-Doctoral Fellow
Hadi Hadizadeh
Senior Research Scientist
Atousa Hajshirmohammadi
University Lecturer
Alon Harell
Ph.D. Student
Lester He
M.A.Sc. Student
Masoud Khairi Atani
M.A.Sc. Student
Jie Liang
Professor
Soroush Oraki
Ph.D. Student
Qihan Xu
Ph.D. Student
Runyu Yang
Post-Doctoral Fellow
Shibai Yin
Visiting Scholar
Rashid Zamanshoar Heris
Ph.D. Student
SELECTED PUBLICATIONS
2026
- Y. Liu, S. Yin, and I. V. Bajić, "Multi-scale implicit diffusion model with high-frequency uncertainty guidance and global structure consistency," Applied Soft Computing, vol. 188, article no. 114135, 2026. [DOI]
- B. Azizian and I. V. Bajić, “Prompt-guided prefiltering for VLM image compression,” to be presented at ICME, Bangkok, Thailand, Jul. 2026. [arXiv] [GitHub]
- A. de Andrade, A. Harell, and I. V. Bajić, “Lossy common information in a learnable Gray-Wyner network,” to be presented at ICLR, Rio de Janeiro, Brazil, Apr. 2026. [arXiv] [GitHub]
2025
- A. Wister, E. Pinigina, J. Liang, and I. Linkov, "AI-enabled Resilience Modeling for Brain Health, Frontiers in Molecular Medicine," Frontiers in Molecular Medicine, vol. 5, Sept. 2025. [DOI]
- A. Harell, Y. Foroutan, N. Ahuja, P. Datta, B. Kanzariya, V. S. Somayazulu, O. Tickoo, A. de Andrade, and I. V. Bajić, “Rate-distortion theory in coding for machines and its application,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 47, no. 7, pp. 5501-5519, July 2025. [IEEEXplore] [arXiv]
- C. Dinesh, G. Cheung, S. Bagheri, and I. V. Bajić, "Efficient signed graph sampling via balancing & Gershgorin disc perfect alignment," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2330-2348, April 2025. [IEEEXplore] [arXiv]
- R. Yang and I. V. Bajić, "Bit allocation transfer for perceptual quality enhancement of VVC intra coding," Proc. Picture Coding Symposium, Aachen, Germany, Dec. 2025. [arXiv]
- M. Khairi Atani, A. Harell, H. Choi, R. Yang, F. Racapé, and I. V. Bajić, "How universal are SAM2 features?" Proc. Picture Coding Symposium, Aachen, Germany, Dec. 2025.[arXiv]
- C.-L. Wu, H. Choi, and I. V. Bajić, "Semantics-guided genrative image compression," Proc. IEEE ICIP, pp. 1324-1329, Anchorage, AK, USA, Sep. 2025. [IEEEXplore] [arXiv] [GitHub]
- I. V. Bajić, "Rate-accuracy bounds in visual coding for machines," Proc. IEEE MIPR, pp. 193-199, San Jose, CA, USA, Aug. 2025. [IEEEXplore] [arXiv]
- H. Fu, J. Liang, Z. Fang, J. Han, “SELIC: Semantic-Enhanced Learned Image Compression via High-Level Textual Guidance," Proc. IEEE ICME, Jul. 2025. [IEEEXplore] [arXiv]
- C. Shiranthika, H. Hadizadeh, P. Saeedi, and I. V. Bajić, "SplitFedZip: Learned compression for data transfer reduction in split-federated learning," AAAI FLUID Workshop, Mar. 2025. [arXiv]
2024
- C. Shiranthika, H. Hadizadeh, P. Saeedi, and I. V. Bajić, "Adaptive asynchronous split federated learning for medical image segmentation," IEEE Access, vol. 12, pp. 182496-182515, 2024. [IEEEXplore]
- H. Hadizadeh and I. V. Bajić, “Learned scalable video coding for humans and machines,” EURASIP J. Image and Video Processing, vol. 2024, article no. 41, Special Issue on Visual Coding for Humans and Machines, Nov. 2024. [DOI] [arXiv] [GitHub]
- B. Azizian and I. V. Bajić, “Privacy preserving autoencoder for collaborative object detection,” IEEE Trans. Image Processing, vol. 33, pp. 4937-4951, Oct. 2024. [IEEEXplore] [arXiv] [GitHub]
- F. Chen, T. Lan, J. Liang, and R. Zhang, "Toward bridging gaps in patient navigation: A study on the adoption of artificial intelligence technologies," Medicine Advances, vol. 2, no. 3, Sept. 2024, pp. 274-283. [DOI]
- H. Fu, F. Liang, J. Liang, Y. Wang, Z. Fang, G. Zhang, and J. Han, "Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation," IEEE Trans. Image Processing, vol. 33, pp. 4702-4715, Aug. 2024. [IEEEXplore]
- M. Ulhaq and I. V. Bajić, “Learned compression of encoding distributions,” Proc. IEEE ICIP, pp. 3716-3722, Abu Dhabi, UAE, Oct. 2024. [arXiv] [IEEEXplore] (Top 5% Paper)
- H. Hadizadeh and I. V. Bajić, “Learned multimodal compression for autonomous driving,” Proc. IEEE MMSP, Purdue University, IN, USA, Oct. 2024. [arXiv] [IEEEXplore]
- H. Fu, J. Liang, Z. Fang, J. Han, F. Liang, and G. Zhang, “WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model,” European Conference on Computer Vision (ECCV 2024), Milano, Italy, Sept.-Oct. 2024. [arXiv]
- H. Hadizadeh, S. F. Yeganli, B. Rashidi, and I. V. Bajić, “Mutual information analysis in multimodal learning systems,” Proc. IEEE MIPR, pp. 390-395, San Jose, CA, USA August 2024. [arXiv] [IEEEXplore]
- A. de Andrade and I. V. Bajić, “Towards task-compatible compressible representations,” Proc. IEEE ICME Workshop on Coding for Machines, Niagara Falls, Canada, July 2024. [arXiv] [IEEEXplore] [GitHub]
- S. R. Alvar and I. V. Bajić, “Compressive feature selection for remote visual multi-task inference,” Proc. IEEE ICME Workshop on Coding for Machines, Niagara Falls, Canada, July 2024. [arXiv] [IEEEXplore]
- M. Ulhaq and I. V. Bajić, “Scalable human-machine point cloud compression,” Proc. Picture Coding Symposium, Taichung, Taiwan, June 2024. [arXiv] [IEEEXplore]
- H. Fu, F. Liang, J. Liang, Z. Fang, G. Zhang, and J. Han, “Efficient Learned Image Compression with Selective Kernel Residual Module and Channel-wise Causal Context Model,” Proc. IEEE ICASSP, Seul, Korea, Jun. 2024. [IEEEXplore]
- H. Fu, F. Liang, J. Liang, Z. Fang, G. Zhang, and J. Han, “Learned Image Compression with Dual-Branch Encoder and Conditional Information Coding,” Proc. Data Compression Conference, Utah, USA, Mar. 2024. [IEEEXplore]
2023
- H. Naderi and I. V. Bajić, “Adversarial attacks and defenses on 3D point cloud classification: A survey,” IEEE Access, vol. 11, pp. 144274-144295, Dec. 2023. [IEEEXplore]
- H. Fu, F. Liang, J. Liang, B. Li, G. Zhang, and J. Han, "Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Scaling, and Post-Quantization Filtering," IEEE Trans. on Circuits and Systems for Video Technology, vol. 33, no. 8, pp. 4309 - 4321, Aug. 2023. [arXiv]
- I. V. Bajić, M. Mrak, F. Dufaux, E. Magli and T. Chen, “Multimedia Signal Processing: A History of the Multimedia Signal Processing Technical Committee,” IEEE Signal Processing Magazine, vol. 40, no. 4, pp. 72-79, Jun. 2023. [IEEEXplore]
- C. Shiranthika, P. Saeedi, and I. V. Bajić, “Decentralized learning in healthcare: A review of emerging techniques,” IEEE Access, vol. 11, pp. 54188-54209, Jun. 2023. [IEEEXplore]
- H. Fu, F. Liang, J. Lin, B. Li, M. Akbari, J. Liang, G. Zhang, D. Liu, C. Tu, and J. Han, "Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules," IEEE Trans. Image Processing, vol. 32, pp. 2063-2076, Apr. 2023. [arXiv]
- C. Dinesh, G. Cheung, and I. V. Bajić, “Point cloud sampling via graph balancing and Gershgorin disc alignment,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 868-886, Jan. 2023. [IEEEXplore] [arXiv]
- C. Shiranthika, Z. Hafezi Kafshgari, P. Saeedi, and I. V. Bajić, “SplitFed resilience to packet loss: Where to split, that is the question,” Proc. MICCAI Workshop on Distributed, Collaborative and Federated Learning, Vancouver, BC, Canada, Oct. 2023. [arXiv] (Spotlight Paper)
- Y. Foroutan, A. Harell, A. de Andrade, and I. V. Bajić, “Base layer efficiency in scalable human-machine coding,” Proc. IEEE ICIP, Kuala Lumpur, Malaysia, Oct. 2023. [arXiv]
- K. Uyanik, S. F. Yeganli, and I. V. Bajić, “Grad-FEC: Unequal loss protection of deep features in collaborative intelligence,” Proc. IEEE ICIP, Kuala Lumpur, Malaysia, Oct. 2023. [arXiv]
- M. Ulhaq and I. V. Bajić, “Learned point cloud compression for classification,” Proc. IEEE MMSP, Poitiers, France, Sept. 2023. [IEEEXplore] [arXiv] [GitHub]
- A. de Andrade, A. Harell, Y. Foroutan, and I. V. Bajić, “Conditional and residual methods in scalable coding for humans and machines,” Proc. IEEE ICME Workshop on Coding for Machines, Brisbane, Australia, Jul. 2023. [IEEEXplore] [arXiv] [GitHub]
- A. Harell, Y. Foroutan, and I. V. Bajić, “VVC+M: Plug and play scalable image coding for humans and machines,” Proc. IEEE ICME Workshop on Coding for Machines, Brisbane, Australia, Jul. 2023. [IEEEXplore] [arXiv]
- H. Hadizadeh and I. V. Bajić, “LCCM-VC: Learned conditional coding modes for video compression,” Proc. IEEE ICASSP Workshop on Humans, Machines and Multimedia - Quality of Experience and Beyond, Rhodes Island, Greece, Jun. 2023. [IEEEXplore] [arXiv] [GitHub]
- B. Li, J. Liang, H. Fu, J. Han, "ROI-based Deep Image Compression with Swin Transformers,” Proc. IEEE ICASSP, Rhodes Island, Greece, Jun. 2023. [IEEEXplore]
- Z. Hafezi Kafshgari, I. V. Bajić and P. Saeedi, “Smart split-federated learning over noisy channels for embryo image segmentation,” Proc. IEEE ICASSP, Rhodes Island, Greece, Jun. 2023. [IEEEXplore]
- R. Zamanshoar Heris and I. V. Bajić, “Multi-task learning for screen content image coding,” Proc. IEEE ISCAS, Monterey, CA, USA, May 2023. [IEEEXplore] [arXiv] [GitHub] (IEEE MSA-TC Best Paper Award)
- Z. Hafezi Kafshgari, C. Shiranthika, P. Saeedi, and I. V. Bajić, “Quality-adaptive split-federated learning for segmenting medical images with inaccurate annotations,” Proc. IEEE ISBI, Cartagena de Indias, Colombia, Apr. 2023. [IEEEXplore] [arXiv] (Best Paper Runner-up)
2022
- N. Shlezinger and I. V. Bajić, “Collaborative inference for AI-Empowered IoT devices,” IEEE Internet of Things Magazine, vol. 5, no. 4, pp. 92-98, Dec. 2022. [IEEEXplore] [arXiv]
- Y. Yang, A. Wang, D. Bu, Z. Feng, and J. Liang, "AS-Net: An attention-aware downsampling network for point clouds oriented to classification tasks," Journal of Visual Communication and Image Representation, vol. 89, article no. 103639, Nov. 2022. [DOI]
- S. R. Alvar, M. Ulhaq, H. Choi, and I. V. Bajić, “Joint image compression and denoising via latent-space scalability,” Front. Signal Process., Sec. Image Processing, Sep. 2022. [DOI]
- B. Li, L. Ye, J. Liang, Y. Wang, J. Han, "Region-of-Interest and Channel Attention-based Joint Optimization of Image Compression and Computer Vision," Neurocomputing, vol. 500, pp. 13-25, Aug. 2022. [PDF]
- J. Jin, X. Zhang, L. Meng, W. Lin, J. Liang, H. Zhang, and Y. Zhao, "Auto-Weighted Layer Representation Based View Synthesis Distortion Estimation for 3-D Video Coding," IEEE Trans. Multimedia, vol. 25, pp. 5775 5788, Aug. 2022. [IEEEXplore]
- W. Dong, T. Zhang, J. Qu, S. Xiao, J. Liang, and Y. Li, "Laplacian Pyramid Dense Network for Hyperspectral Pansharpening," IEEE Trans. Geoscience and Remote Sensing, vol. 60, pp. 1-13, May 2022. [IEEEXplore]
- B. Li, J. Liang, and J. Han, "Variable-Rate Deep Image Compression with Vision Transformers," IEEE Access, vol. 10, pp. 50323-50334, May 2022. [IEEEXplore]
- H. Choi and I. V. Bajić, “Scalable image coding for humans and machines,” IEEE Trans. Image Processing, vol. 31, pp. 2739-2754, Mar. 2022. [IEEEXplore] [arXiv] [GitHub]
- C. Dinesh, G. Cheung, and I. V. Bajić, “Point cloud video super-resolution via partial point coupling and graph smoothness,” IEEE Trans. Image Processing, vol. 31, pp. 4117-4132, Jun. 2022. [IEEEXplore]
- T. Tanaka, H. Choi, and I. V. Bajić, “Updating a dataset of labelled objects on raw video sequences with unique object IDs,” Data in Brief, vol. 41, article no. 107892, Apr. 2022. [DOI]
- S. Li, L. Bariah, S. Muhaidat, A. Wang, and J. Liang, "Outage Analysis of NOMA-Enabled Backscatter Communications with Intelligent Reflecting Surfaces," IEEE Internet of Things Journal, Feb. 2022. [IEEE]
- X. Shang, G. Wang, J. Liang, X. Zhao, H. Han, and Y. Zuo, "Color-Sensitivity-based Rate-Distortion Optimization for H.265/HEVC," IEEE Trans. on Circuits and Systems for Video Technology, vol. 32, no. 2, pp. 802-812, Feb. 2022. [IEEEXplore]
- Y. Wu, H. Qi, J. Liang, K. Peng, and A. Wang, "Virtual structured-light 3D point cloud compression with geometric reshaping," Journal of Electronic Imaging, Feb. 2022. [PDF]
- H. Fu, F. Liang, J. Liang, B. Li, G. Zhang, J. Han, “Learned Image Compression with Inception Residual Blocks and Multi-Scale Attention Module,” Proc. Picture Coding Symposium, San Jose, CA, USA, Dec. 2022. [IEEEXplore]
- B. Azizian and I. V. Bajić, “Privacy-preserving feature coding for machines,” Proc. Picture Coding Symposium, San Jose, CA, USA, Dec. 2022. [IEEEXplore] [arXiv]
- A. Harell, A. de Andrade, and I. V. Bajić, “Rate-distortion in image coding for machines,” Proc. Picture Coding Symposium, San Jose, CA, USA, Dec. 2022. [IEEEXplore] [arXiv]
- H. Choi and I. V. Bajić, “Scalable video coding for humans and machines,” Proc. IEEE MMSP'22, Shanghai, China, Sep. 2022. [IEEEXplore] [arXiv] (Best Paper - Honorable Mention)
- S. R. Alvar, K. Uyanik, and I. V. Bajić, “License plate privacy in collaborative visual analysis of traffic scenes,” Proc. IEEE MIPR'22, Aug. 2022. [IEEEXplore] [arXiv]
- T. Tanaka, A. Harell, and I. V. Bajić, “Does video compression impact tracking accuracy?” Proc. IEEE ISCAS'22, pp. 1517-1521, May-June 2022. [IEEEXplore] [arXiv]
- C. Dinesh, S. Bagheri, G. Cheung, and I. V. Bajić, “Linear-time sampling on signed graphs via Gershgorin disc perfect alignment,” Proc. IEEE ICASSP'22, pp. 5942-5946, May 2022. [IEEEXplore] (SPS Travel Grant)
2021
- X. Fan, J. Lei, J. Liang, Y. Fang, and Q. Huang, "Stereoscopic Image Retargeting Based on Deep Convolutional Neural Network," IEEE Trans. Circuits and Systems for Video Technology, vol. 3, no. 12, pp. 4759-4770, Dec. 2021. [IEEEXplore]
- T. Tang, A. Wang, S. Muhaidat, S. Li, M. Li, and J. Liang, "MDC-NOMA: Multiple Description Coding-based Non-orthogonal Multiple Access for Image transmission," IEEE Systems Journal, vol. 15, no. 3, pp. 3632 3641, Sept. 2021. [IEEEXplore]
- A. Harell, R. Jones, S. Makonin, and I. V. Bajić, “TraceGAN: Synthesizing appliance power signatures using generative adversarial networks,” IEEE Trans. Smart Grid, vol. 12, no. 5, pp. 4553-4563, Sept. 2021. [IEEEXplore] [arXiv]
- X. Fan, J. Lei, J. Liang, Y. Fang, X. Cao, and N. Ling, "Unsupervised Stereoscopic Image Retargeting via View Synthesis and Stereo Cycle Consistency Losses," Neurocomputing, vol. 447, pp. 161-171, Aug. 2021. [PDF]
- H. Fu, F. Liang, B. Lei, Q. Zhang, J. Liang, C. Tu, and G. Zhang, "An Extended Context-Based Entropy Hybrid Modeling for Image Compression," Signal Processing: Image Communication, vol. 95, paper ID 116244, Jul. 2021. [PDF]
- R. A. Cohen, H. Choi, and I. V. Bajić, “Lightweight compression of intermediate neural network features for collaborative intelligence,” IEEE Open J. Circuits Syst., vol. 2, pp. 350-362, May 2021. (Special Section on IEEE ICME 2020) [IEEEXplore] [arXiv]
- M. Akbari, J. Liang, J. Han, and C. Tu, "Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks," IEEE Trans. Multimedia, vol. 23, pp. 3013-3021, Mar. 2021. [IEEEXplore]
- H. Choi and I. V. Bajić, “Affine transformation-based deep frame prediction,” IEEE Trans. Image Processing, vol. 30, pp. 3321-3334, Feb. 2021. [IEEEXplore] [arXiv] (TIP Featured Article)
- S. R. Alvar and I. V. Bajić, “Pareto-optimal bit allocation for collaborative intelligence,” IEEE Trans. Image Processing, vol. 30, pp. 3348-3361, Feb. 2021. [IEEEXplore] [arXiv]
- H. Choi, E. Hosseini, S. R. Alvar, R. A. Cohen, and I. V. Bajić, “A dataset of labelled objects on raw video sequences,” Data in Brief, vol. 34, article no. 106701, Feb. 2021. [DOI] (Known as the "SFU dataset" in MPEG AI: VCM and FCM)
- Z. A. Bhotto, R. Jones, S. Makonin, and I. V. Bajić, “Short-term demand prediction using an ensemble of linearly-constrained estimators,” IEEE Trans. Power Systems, vol. 36, no. 4, pp. 3163-3175, Jul. 2021. [IEEEXplore]
- H. Hadizadeh and I. V. Bajić, “Soft video multicasting using adaptive compressed sensing,” IEEE Trans. Multimedia, vol. 23, pp. 12-25, Jan. 2021. [IEEEXplore] [arXiv] (TMM Featured Article)
- S. R. Alvar and I. V. Bajić, “Scalable privacy in multi-task image compression,” Proc. IEEE VCIP'21, Munich, Germany, Dec. 2021. [IEEEXplore]
- A. Dhondea, R. A. Cohen, and I. V. Bajić, “DFTS2: Deep feature transmission simulation for collaborative intelligence,” Proc. IEEE VCIP'21, Munich, Germany, Dec. 2021. [IEEEXplore] [arXiv] [GitHub]
- H. Choi and I. V. Bajić, “Latent-space scalability for multi-task collaborative intelligence,” Proc. IEEE ICIP'21, pp. 3562-3566, Anchorage, AK, Sep. 2021. [IEEEXplore] [arXiv] (Extended version published under the title "Scalable image coding for humans and machines" in TIP 2022 arXiv)
- A. Dhondea, R. A. Cohen, and I. V. Bajić, “CALTeC: Content-adaptive linear tensor completion for collaborative intelligence,” Proc. IEEE ICIP'21, pp. 2179-2183, Anchorage, AK, Sep. 2021. [IEEEXplore] [arXiv] [GitHub]
- J. Lin, D. Liu, J. Liang, H. Li, F. Wu, "A deeply modulated scheme for variable-rate video compression,” Proc. IEEE ICIP'21, pp. 3722-3726, Anchorage, AK, Sep. 2021. [IEEEXplore]
- T. Woinoski and I. V. Bajić, “Swimmer stroke rate estimation from overhead race video,” Proc. IEEE ICME Workshop on Artifical Intelligence in Sports (AI-Sports), Shenzhen, China, Jul. 2021. [IEEEXplore] [arXiv]
- I. V. Bajić, “Latent space inpainting for loss-resilient collaborative object detection,” Proc. IEEE ICC'21, Montreal, Canada, Jun. 2021. [IEEEXplore] [arXiv]
- M. Ulhaq and I. V. Bajić, “Latent space motion analysis for collaborative intelligence,” Proc. IEEE ICASSP'21, pp. 8498-8502, Toronto, Canada, Jun. 2021. [IEEEXplore] [arXiv]
- I. V. Bajić, W. Lin, and Y. Tian, “Collaborative intelligence: Challenges and opportunities,” Proc. IEEE ICASSP'21, pp. 8493-8497, Toronto, Canada, Jun. 2021. [IEEEXplore] [arXiv]
- S. Lee and I. V. Bajić, “Information flow through U-Nets,” Proc. IEEE ISBI'21, pp. 812-816, Nice, France, Apr. 2021. [IEEEXplore] [arXiv]
- J. Lin, D. Liu, J. Liang, H. Li, and F. Wu, “Modulated Variable-Rate Deep Video Compression,” Data Compression Conference (DCC), Utah, Mar. 2021. [IEEEXplore]
- M. Akbari, J. Liang, J. Han, C. Tu, “Learned Bi-Resolution Image Coding using Generalized Octave Convolutions,” AAAI Conference on Artificial Intelligence, Feb. 2021, Vancouver, Canada. [AAAI]
2020
- C. Dinesh, G. Cheung, and I. V. Bajić, “3D point cloud denoising via feature graph Laplacian regularization,” IEEE Trans. Image Processing, vol. 29, pp. 4143-4158, Dec. 2020. [IEEEXplore]
- S. Li, L. Bariah, S. Muhaidat, P. Sofotasios, J. Liang, and A. Wang, "SWIPT-Enabled Cooperative NOMA with mth Best Relay Selection," IEEE Open Journal of the Communications Society, vol. 1, pp. 1798 - 1807, Nov. 2020. [IEEEXplore]
- J. Guo, X. Gong, J. Liang, W. Wang, and X. Que, "EAAT: Environment-Aware Adaptive Transmission for Split-Screen Video Streaming," IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 11, pp. 4355-4367, Nov. 2020. [IEEEXplore]
- Y. Wu, Y. Wang, J. Liang, I. Bajic, and A. Wang, "Light field all-in-focus image fusion based on spatially-guided angular information Corresponding," Journal of Visual Communication and Image Representation, vol. 72, paper ID 102878, Oct. 2020. [PDF]
- W. Dong, J. Liang, and S. Xiao, "Saliency Analysis and Gaussian Mixture Model-Based Detail Extraction Algorithm for Hyperspectral Pansharpening," IEEE Trans. Geoscience and Remote Sensing, vol. 58, no. 8, pp. 5462 - 5476, Aug. 2020. [IEEEXplore]
- J. Jin, J. Liang, Y. Zhao, C. Lin, C. Yao, and L. Meng, "Pixel-Level View Synthesis Distortion Estimation for 3-D Video Coding," IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 7, pp. 2229-2239, Jul. 2020. [IEEEXplore]
- W. Dong, S. Xiao, J. Liang, and J. Qu, "Fusion of Hyperspectral and Panchromatic Images Using Structure Tensor and Matting Model," Neurocomputing, vol. 399, pp. 237-246, July 2020. [PDF]
- H. Choi and I. V. Bajić, “Deep frame prediction for video coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 7, pp. 1843-1855, Jul. 2020. [IEEEXplore] [arXiv] (TCSVT Best Paper Award)
- C. Dinesh, S. Makonin, and I. V. Bajić, “Residential power forecasting based on affinity aggregation spectral clustering,” IEEE Access, vol. 8, pp. 99431-99444, May 2020. [IEEEXplore]
- P. Li, F. Yang, J. Zhang, Y. guan, A. Wang, and J. Liang, "Synthesis Distortion-Aware Hybrid Digital Analog Transmission for 3D Videos," IEEE Access, vol. 8, pp. 85128-85139, Apr. 2020. [IEEEXplore]
- T. Wen, W. Cai, A. Wang, J. Liang, and L. Zhao, "HDA Video Transmission Scheme for DASH," IEEE Access, vol. 8, pp. 58345 58356, Mar. 2020. [IEEEXplore]
- H. Fu, F. Liang, B. Lei, N. Bian, Q. Zhang, M. Akbari, J. Liang, and C. Tu, "Improved hybrid layered image compression using deep learning and traditional codecs," Signal Processing: Image Communication, vol. 82, article no. 115774, Mar. 2020. [PDF]
- L. Bragilevsky and I. V. Bajić, “Tensor completion methods for collaborative intelligence,” IEEE Access, vol. 8, pp. 41162-41174, Feb. 2020. [IEEEXplore]
- M. Li, S. Muhaidat, B. Selim, P. Sofotasios, M. Dianati, P. Yoo, J. Liang, and A. Wang, "Effects of Residual Hardware Impairments on Secure NOMA-Based Cooperative Systems," IEEE Access, vol. 8, pp. 2524-2536, Jan. 2020. [IEEEXplore]
- S. Li, A. Wang, H. Shangguan,Y. Wu, D. Li, Y. Wu, and J. Liang, "Super resolution of single depth image based on multi-dictionary learning with edge feature regularization," Multimedia Tools and Applications, pp. 1-22, Jan. 2020. [PDF]
- M. Li, O. Alhussein, P. Sofotasios, S. Muhaidat, P. Yoo, J. Liang, and A. Wang, "Censor-Based Cooperative Multi-Antenna Spectrum Sensing with Imperfect Reporting Channels," IEEE Trans. Sustainable Computing, vol. 5, no. 1, pp. 48-60, Jan. 2020. [IEEEXplore]
- M. Ulhaq and I. V. Bajić, “ColliFlow: A Library for Executing Collaborative Intelligence Graphs,” NeurIPS'20 demo, Vancouver, Canada, Dec. 2020. [GitHub]
- H. Choi and I. V. Bajić, “A lightweight model for deep frame prediction in video coding,” Proc. Asilomar Conf. Signals, Systems, and Computers, pp. 1122-1126, Pacific Grove, CA, Nov. 2020. [IEEEXplore] (Student Paper Contest Finalist)
- C. Dinesh, G. Cheung, F. Wang, and I. V. Bajić, “Sampling of 3D point cloud via Gershgorin disc alignment,” Proc. IEEE ICIP'20, pp. 2736-2740, Abu Dhabi, UAE, Oct. 2020. [IEEEXplore]
- R. A. Cohen, H. Choi, and I. V. Bajić, “Lightweight compression of neural network feature tensors for collaborative intelligence,” Proc. IEEE ICME'20, pp. 1-6, London, UK, Jul. 2020. [IEEEXplore]
- M. Akbari, J. Liang, J. Han, C. Tu, "Learned Variable-Rate Image Compression with Residual Divisive Normalization," Proc. IEEE ICME'20, July 2020, London, UK [arXiv] (Best Paper Finalist)
- H. Choi, R. A. Cohen, and I. V. Bajić, “Back-and-forth prediction for deep tensor compression,” Proc. IEEE ICASSP'20, pp. 4467-4471, Barcelona, Spain, May 2020. [arXiv]
- C. Dinesh, G. Cheung, and I. V. Bajić, “Super-resolution of 3D color point clouds via fast graph total variation,” Proc. IEEE ICASSP'20, pp. 1983-1987, Barcelona, Spain, May 2020. [IEEEXplore]
- S. R. Alvar and I. V. Bajić, “Bit allocation for multi-task collaborative intelligence,” Proc. IEEE ICASSP'20, pp. 4342-4346, Barcelona, Spain, May 2020. [arXiv]
- T. Woinoski, A. Harell, and I. V. Bajić, “Towards automated swimming analytics using deep neural networks,” AAAI Workshop on AI in Team Sports, New York, NY, Feb. 2020. [arXiv]
2019
- J. Fu, I. V. Bajić, and R. G. Vaughan, “Datasets for face and object detection in fisheye images,” Data in Brief, vol. 27, article no. 104752, Dec. 2019. [DOI]
- C. Dinesh, S. Makonin, and I. V. Bajić, “Residential power forecasting using load identification and graph spectral clustering,” IEEE Trans. Circuits and Systems II: Express Briefs, vol. 66, no. 11, pp. 1900-1904, Nov. 2019. [IEEEXplore]
- H. Wu, A. Wang, J. Liang, S. Li, and P. Li, "DCSN-Cast: Deep compressed sensing network for wireless video multicast," Signal Processing: Image Communication, vol. 76, pp. 56-67, Aug. 2019. [PDF]
- J. Zhang, A. Wang, J. Liang, H. Wang, S. Li, and X. Zhang, "Distortion Estimation-based Adaptive Power Allocation for Hybrid Digital-Analog Video Transmission," IEEE Trans. Circuits and Systems for Video Technology, vol. 29, no. 6, pp. 1806-1818, Jun. 2019. [IEEEXplore]
- J. Jin, J. Liang, Y. Zhao, C. Lin, C. Yao, and A. Wang, "A Depth-Bin-Based Graphical Model for Fast View Synthesis Distortion Estimation," IEEE Trans. Circuits and Systems for Video Technology, vol. 29, no. 6, pp. 1754-1766, Jun. 2019. [IEEEXplore]
- X. Shang, J. Liang, G. Wang, H. Zhao, C. Wu, and C. Lin, "Color-Sensitivity-based Combined PSNR for Objective Video Quality Assessment," IEEE Trans. Circuits and Systems for Video Technology, vol. 29, no. 5, pp. 1239-1250, May 2019. [IEEEXplore]
- M. Gaur, S. Makonin, I. V. Bajić, and A. Majumdar, “Performance evaluation of techniques for identifying abnormal energy consumption in buildings,” IEEE Access, vol. 7, pp. 62721-62733, May 2019. [IEEEXplore]
- H. Hadizadeh, A. R. Heravi, I. V. Bajić, and P. Karami, “A perceptual distinguishability predictor for JND-noise-contaminated images,” IEEE Trans. Image Processing, vol. 28, no. 5, pp. 2242-2256, May 2019. [IEEEXplore]
- L. Zhao, H. Bai, J. Liang, B. Zeng, A. Wang, and Y. Zhao, "Simultaneous color-depth super-resolution with conditional generative adversarial networks," Pattern Recognition, vol. 88, pp. 356-369, Apr. 2019. [PDF]
- L. Zhao, H. Bai, J. Liang, A. Wang, B. Zeng, and Y. Zhao, "Local activity-driven structural-preserving filtering for noise removal and image smoothing," Signal Processing, vol. 157, pp. 62-72, Apr. 2019. [PDF]
- X. Shang, G. Wang, X. Zhao, Y. Zuo, J. Liang, and I. V. Bajić, “Weighting quantization matrices for HEVC/H.265-coded RGB videos,” IEEE Access, vol. 7, pp. 36019-36032, Apr. 2019. [IEEEXplore]
- M. Ulhaq and I. V. Bajić, “Shared mobile-cloud inference for collaborative intelligence,” demo at NeurIPS'19, Vancouver, BC, Dec. 2019. [arXiv]
- E. Ideli, B. Sharpe, I. V. Bajić, and R. G. Vaughan, “Visually assisted time-domain speech enhancement,” Proc. IEEE GlobalSIP'19, Ottawa, ON, Nov. 2019. [IEEEXplore]
- C. Dinesh, G. Cheung, and I. V. Bajić, “3D point cloud color denoising using convex graph-signal smoothness priors,” Proc. IEEE MMSP'19, pp. 1-6, Kuala Lumpur, Malaysia, Sep. 2019. [IEEEXplore]
- J. Lin, M. Akbari, H. Fu, Q. Zhang, S. Wang, J. Liang, D. Liu, F. Liang, G. Zhang, and C. Tu, “Learned Variable-Rate Multi-Frequency Image Compression using Modulated Generalized Octave Convolution,” Proc. IEEE MMSP'19, pp. 1-6, Kuala Lumpur, Malaysia, Sep. 2019. [arXiv]
- S. R. Alvar and I. V. Bajić, “Multi-task learning with compressible features for collaborative intelligence,” Proc. IEEE ICIP'19, pp. 1705-1709, Taipei, Taiwan, Sep. 2019. [arXiv] [code] (Best Student Paper Award)
- B. Li, J. Liang, and Y. Wang, “Compression Artifact Removal with Stacked Multi-Context Channel-wise Attention Network,” Proc. IEEE ICIP'19, pp. 3601-3605, Taipei, Taiwan, Sep. 2019. [IEEEXplore] (Spotlight Paper - top 10%)
- C. Dinesh, G. Cheung, and I. V. Bajić, “3D point cloud super-resolution via graph total variation on surface normals,” Proc. IEEE ICIP'19, pp. 4390-4394, Taipei, Taiwan, Sep. 2019. [arXiv] (Spotlight Paper - top 10%)
- M. Akbari, J. Liang, J. Han, "DSSLIC: Deep Semantic Segmentation-based Layered Image Compression," Proc. IEEE ICASSP'19, Brighton, UK, May 2019, pp. 2042-2046. [arXiv] [GitHub]
- A. Harell, S. Makonin, and I. V. Bajić, “WaveNILM: A causal neural network for power disaggregation from the complex power signal,” Proc. IEEE ICASSP'19, pp. 8335-8339, Brighton, UK, May 2019. [arXiv] [GitHub]
- J. Fu, S. R. Alvar, I. V. Bajić, and R. G. Vaughan, “FDDB-360: Face detection in 360-degree fisheye images,” Proc. IEEE MIPR'19, pp. 15-19, San Jose, CA, Mar. 2019. [arXiv] [data]
- B. Li, M. Akbari, J. Liang, and Y.Wang, "Deep Learning-based Image Compression with Trellis Coded Quantization," Proc. Data Compression Conference (DCC), Utah, USA, Mar. 2020. [arXiv]