Enhanced Bi-Prediction With Convolutional Neural Network for High-Efficiency Video Coding
The DOI matches its Crossref record; 47 of the 48 references it cites were found in a registry or an index.
Abstract
In this paper, we propose an enhanced bi-prediction scheme based on the convolutional neural network (CNN) to improve the rate-distortion performance in video compression. In contrast to the traditional bi-prediction strategy which computes the linear superposition as the predictive signals with pixel-to-pixel correspondence, the proposed scheme employs CNN to directly infer the predictive signals in a data-driven manner. As such, the predicted blocks are fused in a nonlinear fashion to improve the coding performance. Moreover, the patch-to-patch inference strategy with CNN also improves the prediction accuracy since the patch-level information for the prediction of each individual pixel can be exploited. The proposed enhanced bi-prediction scheme is further incorporated into the high-efficiency video coding standard, and the experimental results exhibit a significant performance improvement under different coding configurations.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Moreover, the skip connection [19] is introduced into our network to avoid the long-term memory [20] of the input features.”
BackgroundSelf-citationAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The Adam algorithm [44] is used to update the coefficients W (i) and b(i) in the network with the minimization of the loss function.”
MethodDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Unit (ReLU) [13] and Parametric ReLU (PReLU) [14], which was also analyzed in [15] and [16].”
BackgroundSelf-citation(2010) · Cited by 14,134
(2010) · International Conference on Machine Learning · Cited by 13,995
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
Overview of the High Efficiency Video Coding (HEVC) Standard
Sullivan, G. J., Ohm, J.-R., Han, W.-J., & Wiegand, T. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2221191 · Cited by 8,263 · cited 9×
“264/AVC [1] and HEVC [2], performs motion-compensation from two reference frame lists.”
MethodInfluentialOverview of the H.264/AVC video coding standard
Wiegand, T., Sullivan, G. J., Bjontegaard, G., & Luthra, A. (2003) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2003.815165 · Cited by 8,184 · cited 1×
“B I-PREDICTION, which serves as an indispensable module in the state-of-the-art video coding standards such as H.264/AVC [1] and HEVC [2], performs motion-compensation from two reference frame lists.”
BackgroundAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870 · cited 4×
“[20], [27] deepened the network architecture to enhance the non-linear representation ability, which achieves better performance in SR problem.”
BackgroundInfluentialLearning a Deep Convolutional Network for Image Super-Resolution
Dong, C., Loy, C. C., He, K., & Tang, X. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_13 · Cited by 5,494 · cited 1×
“[26] first introduced the deep learning into super-resolution problem.”
Background
Research works printed but not linked: 2
- 2018, Trained Models in the Caffe Platform
- bossen, 2011, Common Test Conditions and Software Reference Configurations
Cited by
Artificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793
“They have been applied to optimise a range of coding tools including intra prediction [219, 222], motion estimation [297], transforms [221], quantization [298], entropy coding [220] and loop filtering [299].”
MethodImage and Video Compression With Neural Networks: A Review
Ma, S., Zhang, X., Jia, C., Zhao, Z., Wang, S., & Wang, S. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2910119 · Cited by 459
“In addition, considering the limitation of the traditional bidirectional prediction using simple average of two prediction hypothesises, we further improve its efficiency by utilizing a six-layer CNN with 13×13 receptive field size to infer the inter prediction block in a nonlinear fashion [91], [92], which achieves 2.”
MethodSelf-citationBVI-DVC: A Training Database for Deep Video Compression
Ma, D., Zhang, F., & Bull, D. R. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3108943 · Cited by 163
“Image and video compression based on deep neural networks has become a popular research topic offering evident enhancements over conventional coding tools for: intra prediction [22, 23], motion estimation [24, 25], transforms [26, 27], quantisation [28], entropy coding [29, 30], post-processing [31, 32] and loop filte…”
BackgroundDeep Learning-Based Video Coding: A Review and a Case Study
Liu, D., Li, Y., Lin, J., Li, H., & Wu, F. (2021) · ACM Computing Surveys · doi:10.1145/3368405 · Cited by 192
“[148] propose a method to enhance the prediction quality.”
MethodMachine learning based video coding optimizations: A survey
Zhang, Y., Kwong, S., & Wang, S. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.096 · Cited by 88
Self-citationMFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
Ma, D., Zhang, F., & Bull, D. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3043064 · Cited by 84
Deep Frame Prediction for Video Coding
Choi, H., & Bajić, I. V. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2924657 · Cited by 72
“Other studies that have looked at the use of neural networks in motion compensation include [25]–[27].”
InfluentialImage Encryption Algorithm Combining Chaotic Image Encryption and Convolutional Neural Network
Feng, L., Du, J., Fu, C., & Song, W. (2023) · Electronics · doi:10.3390/electronics12163455 · Cited by 58
Enhancing VVC Through Cnn-Based Post-Processing
Zhang, F., Feng, C., & Bull, D. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102912 · Cited by 52
“Numerous work has been published that integrates CNN models with intra prediction [10, 11], inter prediction [12, 13], transforms [14], quantisation [15], entropy coding [16], loop filters [17, 18], postprocessing [19, 20] and format adaptation [21–24].”
BackgroundDigital Retina: A Way to Make the City Brain More Efficient by Visual Coding
Gao, W., Ma, S., Duan, L., Tian, Y., Xing, P., Wang, Y., Wang, S., Jia, H., & Huang, T. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3104305 · Cited by 53
Self-citationCompact Temporal Trajectory Representation for Talking Face Video Compression
Chen, B., Wang, Z., Li, B., Wang, S., & Ye, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3271130 · Cited by 58
“Recently, deep learning techniques have been introduced to replace or enhance video coding tools, including intra/inter prediction [14], [15], [16], entropy coding [17], interpolation filtering [18], and in-loop filtering [19], achieving competitive RD performance.”
Self-citationLiu, D., Chen, Z., Liu, S., & Wu, F. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2945057 · Cited by 44
“…prediction, several works focus on the task of fractional-pixel interpolation [23], [33], [34], while other works deal with bi-directional motion compensation [35], motion compensation refinement [36], combined intra/inter prediction [37], or directly extrapolating a frame for reference [38].”
BackgroundDeep Network-Based Frame Extrapolation With Reference Frame Alignment
Huo, S., Liu, D., Li, B., Ma, S., Wu, F., & Gao, W. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2995243 · Cited by 41
“In [26], Zhao et al. presented an enhanced bi-prediction with CNN in MC, where a trained CNN is used to enhance the traditional average bi-directional prediction according to the content in video.”
MethodSelf-citationA Robust Quality Enhancement Method Based on Joint Spatial-Temporal Priors for Video Coding
Meng, X., Deng, X., Zhu, S., Zhang, X., & Zeng, B. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3019919 · Cited by 43
Self-citationDeep Learning-Based Chroma Prediction for Intra Versatile Video Coding
Zhu, L., Zhang, Y., Wang, S., Kwong, S., Jin, X., & Qiao, Y. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3035356 · Cited by 37
Self-citationDeep Video Prediction Network-Based Inter-Frame Coding in HEVC
Lee, J.-K., Kim, N., Cho, S.-H., & Kang, J. (2020) · IEEE Access · doi:10.1109/access.2020.2993566 · Cited by 34
“Zhao et al. propose a bi-directional (B) motion prediction technique using CNN VPN to infer a prediction block [6].”
MethodDeep Affine Motion Compensation Network for Inter Prediction in VVC
Jin, D., Lei, J., Peng, B., Li, W., Ling, N., & Huang, Q. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3107135 · Cited by 32
Affine Transformation-Based Deep Frame Prediction
Choi, H., & Bajić, I. V. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3060803 · Cited by 30
“In order to minimize residuals after inter prediction, [8], [9] proposed networks that learn interpolation filters, while [10]–[12] developed refinement networks using motion compensated patches as input.”
CVEGAN: A perceptually-inspired GAN for Compressed Video Enhancement
Ma, D., Zhang, F., & Bull, D. (2024) · Signal Processing Image Communication · doi:10.1016/j.image.2024.117127 · Cited by 37
“been used to optimise tools including: intra prediction [23, 24], motion estimation [25, 26], transforms [27, 28], quantisation [29], entropy coding [30, 31], post-processing (PP) [32, 33], in-loop filtering (ILF) [34, 35] and format adaptation [36–38].”
MethodViSTRA2: Video coding using spatial resolution and effective bit depth adaptation
Zhang, F., Afonso, M., & Bull, D. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116355 · Cited by 33
Mao, J., & Yu, L. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2954853 · Cited by 26
“Some researchers use CNN-based patch-to-patch fusion to tackle pixel-wise motion by utilizing patch-level information to predict each individual pixel [14], [37].”
BackgroundMethodInfluentialRecent Advances on HEVC Inter-Frame Coding: From Optimization to Implementation and Beyond
Zhang, Y., Zhang, C., Fan, R., Ma, S., Chen, Z., & Kuo, C. ‐. J. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2954474 · Cited by 32
“In [189], a CNN-based bi-prediction model was presented, in which the predictive signal can be automatically inferred in an end-to-end manner, and the non-linear mapping leads to better fusion in the bi-prediction process than conventional block-wise translational motion mapping.”
MethodSelf-citationCross Modal Compression: Towards Human-comprehensible Semantic Compression
Li, J., Jia, C., Zhang, X., Ma, S., & Gao, W. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475558 · Cited by 28
“Also, the submodules in video compression frameworks are investigated by embedding the DNNs in the them, including intra prediction [20], inter prediction [48], loop filter [18], quantization [2] and entropy encoding [28].”
Self-citationCombining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
Wang, D., Xia, S., Yang, W., & Liu, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3068638 · Cited by 28
“proposed a method [27] to enhance the inter-prediction quality by utilizing a CNN to combine two prediction blocks rather than a linear combination.”
MethodInteractive Face Video Coding: A Generative Compression Framework
Chen, B., Wang, Z., Li, B., Wang, S., Wang, S., & Ye, Y. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3563762 · Cited by 36
“Moreover, enabled by deep learning techniques, a variety of video coding tools, such as intra / inter prediction [31], [32], entropy coding [33], interpolation filtering [34], and in-loop filtering [35], [36], are further enhanced for better RD performance.”
Self-citationNeural Network Based Rate Control for Versatile Video Coding
Mao, Y., Wang, M., Ni, Z., Wang, S., & Kwong, S. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3262303 · Cited by 21
Self-citationConvolutional neural network based low complexity HEVC intra encoder
Wang, Z., & Li, F. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09231-8 · Cited by 21
Murn, L., Blasi, S., Smeaton, A., & Mrak, M. (2021) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3089439 · Cited by 21
“Several methods based on CNNs have been proposed that either improve the input to the interpolation process, by fusing the reference blocks in bi-prediction in a non-linear way [11], [12], or the output of the process, utilising the neighbouring reconstructed region to refine the prediction [13].”
MethodTsiavos, V., & Kitsios, F. (2025) · Telecommunications Policy · doi:10.1016/j.telpol.2025.103021 · Cited by 48
Recent trending on learning based video compression: A survey
Hoang, T. M., & Zhou, J. (2021) · Cognitive Robotics · doi:10.1016/j.cogr.2021.08.003 · Cited by 25
Residual in Residual Based Convolutional Neural Network In-loop Filter for AVS3
Lin, K., Jia, C., Zhao, Z., Wang, L., Wang, S., Ma, S., & Gao, W. (2019) · Picture Coding Symposium · doi:10.1109/pcs48520.2019.8954561 · Cited by 17
“Deep learning based methods have emerged recently to replace conventional coding tools including intra prediction [11], inter prediction [12], [13], inloop filter [14] and so on.”
MethodSelf-citationLow-Complexity Error Resilient HEVC Video Coding: A Deep Learning Approach
Wang, T., Li, F., Qiao, X., & Cosman, P. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3043124 · Cited by 17
“[34] used a CNN to infer predictive signals, thus the residual between the predicted and raw picture was reduced and the coding efficiency improved.”
MethodSpeeding Up VP9 Intra Encoder With Hierarchical Deep Learning-Based Partition Prediction
Paul, S., Norkin, A., & Bovik, A. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3011270 · Cited by 17
Neural Network-Based Enhancement to Inter Prediction for Video Coding
Wang, Y., Xiaopeng Fan, B., Xiong, R., Zhao, D., & Gao, W. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3063165 · Cited by 16
NR-CNN: Nested-Residual Guided CNN In-loop Filtering for Video Coding
Lin, K., Jia, C., Zhang, X., Wang, S., Ma, S., & Gao, W. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3502723 · Cited by 16
“Plenty of deep learning based coding tools in terms of intra prediction [12, 26], 102:3 inter prediction [14, 43, 51, 52], and in-loop filtering [4, 15–17, 21, 23, 28, 36, 40, 50] have been studied recently and outperform conventional methods with respect to the coding efficiency.”
MethodSelf-citationDeep Multi-Domain Prediction for 3D Video Coding
Lei, J., Shi, Y., Pan, Z., Liu, D., Jin, D., Chen, Y., & Ling, N. (2021) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2021.3090261 · Cited by 15
Spatio-Temporal Convolutional Neural Network for Enhanced Inter Prediction in Video Coding
Merkle, P., Winken, M., Pfaff, J., Schwarz, H., Marpe, D., & Wiegand, T. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3446228 · Cited by 15
“In [34], Zhao et al. propose a CNN-based fusion scheme.”
BackgroundMethod4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
Hu, Q., Zheng, Z., Zhong, H., Fu, S., Song, L., Zhang, X., Zhai, G., & Wang, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00090 · Cited by 59
“[1, 3, 4, 14, 31, 36, 38, 41, 42, 44, 59, 71, 72, 75] have demonstrated strong RD performance.”
Self-citationCommunicating pictures – the future
Bull, D., & Zhang, F. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-820353-8.00022-0 · Cited by 14
MPAI-EEV: Standardization Efforts of Artificial Intelligence Based End-to-End Video Coding
Jia, C., Ye, F., Dong, F., Lin, K., Chiariglione, L., Ma, S., Sun, H., & Gao, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3310188 · Cited by 15
“1) Inter Predictive Refinement Network: To realize higher predictive coding efficiency, one key research direction is to promote the quality of the reference frames [26], [27].”
BackgroundSelf-citationPark, W., & Kim, M. (2020) · IEEE Access · doi:10.1109/access.2020.3046040 · Cited by 14
Enhancing Cloud-Based Video Streaming Efficiency using Neural Networks
Darwich, M., Khalil, K., Ismail, Y., & Bayoumi, M. (2023) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins57856.2023.10189314 · Cited by 11
HPC: Hierarchical Progressive Coding Framework for Volumetric Video
Zheng, Z., Zhong, H., Hu, Q., Zhang, X., Song, L., Zhang, Y., & Wang, Y. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681107 · Cited by 26
“In recent years, deep learning-based image and video compression methods[1–3, 12, 25, 26, 31, 35, 36, 39–41, 43, 56, 60, 61, 70, 71, 76] have been widely applied, achieving good rate-distortion (RD) performance on 2D videos.”
Self-citationDisparity-Aware Reference Frame Generation Network for Multiview Video Coding
Lei, J., Zhang, Z., Pan, Z., Liu, D., Liu, X., Chen, Y., & Ling, N. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3183436 · Cited by 11
“Zhao et al. [31] developed an enhanced bi-prediction scheme with CNN for motion compensation, where the nonlinear fusion is performed on bi-directional prediction blocks.”
MethodIntra-Inter Prediction for Versatile Video Coding Using a Residual Convolutional Neural Network
Merkle, P., Winken, M., Pfaff, J., Schwarz, H., Marpe, D., & Wiegand, T. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897324 · Cited by 10
“In [10], the averaging of the two predictors in bi-prediction is replaced by a CNN-based fusion.”
MethodReview and Evaluation of End-to-End Video Compression with Deep-Learning
Yasin, H. M., & Ameen, S. Y. (2021) · International Conference of Modern Trends in Information and Communication Technology Industry (MTICTI) · doi:10.1109/mticti53925.2021.9664790 · Cited by 10
Deep Intra Prediction by Jointly Exploiting Local and Non-Local Similarities
Lei, M., Zhang, J., Wang, S., Wang, S., & Ma, S. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3220434 · Cited by 9
“Due to the success of DNN in low-level vision tasks, there are a series of works incorporating deep learning to image and video compression [14], [15], [16], [17], [18], [19].”
BackgroundSelf-citationDeep Video Compression for P-frame in Sub-sampled Color Spaces
Lin, R., Zhang, P., Wang, M., Wang, S., & Kwong, S. (2022) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas48785.2022.9937560 · Cited by 7
“Regarding inter prediction, the deep learning is cooperated to improve the motion estimation precision [8] [9].”
MethodSelf-citationCloud Gaming Video Coding Optimization Based on Camera Motion-Guided Reference Frame Enhancement
Wang, Y., Wang, H., Wang, K., & Zhang, W. (2022) · Applied Sciences · doi:10.3390/app12178504 · Cited by 6
Attention-Based Bi-Prediction Network for Versatile Video Coding (VVC) over 5G Network
Choi, Y.-J., Lee, Y., Kim, J., Jeong, S., Choi, J. S., & Kim, B. (2023) · Sensors · doi:10.3390/s23052631 · Cited by 6
“Until now, the deep learning-based works for inter bi-prediction [28,29] aimed to increase the performance of traditional bi-prediction in HEVC.”
BackgroundMethodInfluentialEfficient Super-Resolution for Compression Of Gaming Videos
Wang, Y., Murn, L., Herranz, L., Yang, F., Mrak, M., Zhang, W., Wan, S., & Blanch, M. G. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096031 · Cited by 6
“Some researchers employ deep learning networks to optimize existing video coding standards [2, 3, 4, 5, 6, 7].”
BackgroundAttention-Based Inter-Prediction for Versatile Video Coding
Tran, Q. N., & Yang, S. (2023) · IEEE Access · doi:10.1109/access.2023.3303510 · Cited by 6
“Various deep tools, such as encoding optimization tools [39], [40], [41], picture prediction tools [42], [43], [44], and in-loop or post-filtering tools [45] [46], have been considered in the literature.”
BackgroundTian, W., Luo, F., & Shen, K. (2024) · Machine Vision and Applications · doi:10.1007/s00138-024-01539-x · Cited by 6
A Stacking Ensemble Learning Model for Mobile Traffic Prediction
Li, Z., Cai, D., Wang, J., Fu, J., Qin, L., & Fu, D. (2020) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc49849.2020.9238996 · Cited by 5
“In order to verify the advancement of this model, this paper makes comparison with the linear regression model (LRM) [7], ESN [16], DBN-SVM [17], DBN-ELM [18], RNN [19], LSTM [20] and CNN [21].”
MethodJoint reference frame synthesis and post filter enhancement for Versatile Video Coding
Bao, W., Zhang, Y., Jia, J., Chen, Z., & Liu, S. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104433 · Cited by 5
Learned Image Compression with Large Capacity and Low Redundancy of Latent Representation
Meng, X., Zhu, S., Ma, S., & Zeng, B. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222075 · Cited by 4
“These modules are often individually optimized [4, 5, 6, 7, 8, 9, 10] targeting a high performance as well as a low complexity.”
BackgroundSelf-citationReinforcement Learning for Rate-Distortion Optimized Hierarchical Prediction Structure
Lee, J.-K., Kim, N., & Kang, J. (2023) · IEEE Access · doi:10.1109/access.2023.3249284 · Cited by 4
“There have been several studies using deep learning to reduce temporal redundancy and improve coding efficiency, by producing more accurate motion vectors and reference blocks [3], [4], [5], [6].”
BackgroundMethodTowards Hybrid-Optimization Video Coding
Huo, S., Liu, D., Zhang, H., Li, L., Ma, S., Wu, F., & Gao, W. (2024) · ACM Computing Surveys · doi:10.1145/3652148 · Cited by 10
Self-citationAdaptive lossless compression of skeleton sequences
Lin, W., Shinde, T. S., Dai, W., Liu, M., He, X., Tiwari, A. K., & Xiong, H. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.115659 · Cited by 4
Current Frame Priors Assisted Neural Network for Intra Prediction
Zhang, H., Song, L., Huang, Y., & Xie, R. (2021) · IEEE Access · doi:10.1109/access.2021.3102114 · Cited by 2
Deep Motion Vector Prediction for Versatile Video Coding
Li, L., Wu, K., Wei, H., Liu, J., Fang, Y., & Zheng, H. (2021) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc54389.2021.9674239 · Cited by 2
A Lightweight Model for Deep Frame Prediction in Video Coding
Choi, H., & Bajić, I. V. (2020) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf51394.2020.9443427 · Cited by 1
Deep Inter Prediction for Versatile Video Coding (VVC)
Aisha, Q. U. A., Choi, Y.-J., Kim, J., Lim, S.-C., Choi, J. S., & Kim, B. (2024) · Journal of Multimedia Information System · doi:10.33851/jmis.2024.11.3.175 · Cited by 1
Deep Reference Frame for Versatile Video Coding with Structural Re-parameterization
Gui, C., Zhang, Y., Bao, W., Chen, Z., Wang, H., & Liu, S. (2024) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip63160.2024.10849929 · Cited by 1
“…an increasing number of researchers integrating neural network based tools into existing coding frameworks [3]–[11], with studies exploring its application in inter prediction through bi-prediction [12], [13], fractional interpolation [14], [15], and reference frame interpolation [3], [16], [17].”
Neural Generation of Blocks for Video CodingPreprint
Probell, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02748
“Prior work applying neural network techniques to video compression have focused on processing full video frames [7] [8] [9], object recognition [10], modeling motion and residuals in a latent space [11], improvements to bi-prediction [12], postprocessing images [13], or integrated convolutional neural networks to lear…”
2019 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 29
(2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2959179
Attention-based Bi-Prediction Network with Knowledge Distillation for Versatile Video Coding (VVC)Preprint
Choi, Y.-J., Lee, Y., Kim, J.-H., Jeong, S., Choi, J.-S., & Kim, B. (2022) · Research Square · doi:10.21203/rs.3.rs-1993799/v1
Visual style conversion strategy for visual media based on MGADNN algorithm
Qi, M. (2024) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-247194
“Moreover, the experimental results also confirm this theory that the proposed enhanced bidirectional prediction scheme, when incorporated into an efficient video coding standard, exhibits significant performance improvement under different encoding configurations [10].”
Efficiency Across Datasets: Insights into Video Compression Techniques
Sreeram, A., Chandra, B., Swetha, G., & Bagade, S. (2024) · International Conference on Image Processing and Capsule Networks (ICIPCN) · doi:10.1109/icipcn63822.2024.00011
“While Zhao et al. [5] substituted CNN for the bi-prediction strategy in HEVC to increase coding efficiency, [6] Cui et al. suggested an intra-prediction method employing CNN in HEVC to improve compression performance.”
MethodEnhancing the Compressed Video Quality through a Neural Network Approach
Panneerselvam, K., Rajalakshmi, K., & Sornalatha, P. (2025) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl65848.2025.10933189
Nuthakki, R., Vaka, N. V. S., Nagam, G., Gundabatthula, S. R., & Nakka, S. (2025) · i-manager’s Journal on Electronics Engineering · doi:10.26634/jele.15.2.21734 · Cited by 1
Enhanced Image Security by Integrating Discrete Cosine Transform and Convolutional Neural Network
Kumar, G., & Dinker, A. G. (2025) · International Conference on Networks and Cryptology (NETCRYPT) · doi:10.1109/netcrypt65877.2025.11102656
“Convolutional layers were used to extract features from the original image and inverse convolutional layers were used to reconstruct the feature map in the CNN based technique put out by Zhao et al. [10].”
Mining Temporal Priors for Template-Generated Video Compression
Xing, F., Zhang, Y., Wang, M., Man, H., Zhang, Y., Wang, S., Xiaopeng Fan, B., & Gao, W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3599239
“In addition to traditional tools, a series of deep prediction tools [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51] have been proposed to study non-translational motion [40], sub-pixel motion compensation [41], motion vector prediction [42], [43], [44], [45], [46] and virtual…”
Self-citationAttention Based Deep Reference Frame Enhancement for VVC Inter Prediction
Xu, L., Liu, Z., & Liang, F. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249174
“Studies [6] and [7] both use Convolution Neural Networks (CNN) to enhance prediction blocks.”
Metadata
- Authors
- Zhao, Z., Wang, S., Wang, S., Zhang, X., Ma, S., & Yang, J.
- Affiliations
- Peking University (CN)
- City University of Hong Kong (HK)
- University of Southern California (US)
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2019-11
- Volume
- 29
- Issue
- 11
- Pages
- 3291-3301
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W2896406755
- Cited by
- 75
- References
- 48
- Citations by year
- 2025: 9 · 2024: 9 · 2023: 10 · 2022: 7 · 2021: 17 · 2020: 14 · 2019: 9
- FWCI
- 7.16
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Circuits and Systems for Video Technology (publishedVersion)
- Funders
- National Natural Science Foundation of China (61632001, 61421062, 61520106004, 61571017)
- National Basic Research Program of China (2015CB351800)
- Hong Kong RGC Early Career Scheme (9048122 (CityU 21211018))
- City University of Hong Kong (7200539/CS)
- Peking University
- Microsoft
- Topics
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Data Compression Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Keywords
- HEVC, convolutional neural networks, video compression, rate-distortion performance, motion prediction, data-driven prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.