Quality Assessment of In-the-Wild Videos

Li, Dingquan; Jiang, Tingting; Jiang, Ming

doi:10.1145/3343031.3351028

Cited by 261 publications

(249 citation statements)

References 54 publications

Supporting

Mentioning

245

Contrasting

Order By: Relevance

“…Lastly, we highlight the relationship and difference between our previous work (Li et al 2019a) and this work. The model design in this work is build upon the model in our previous work.…”

Section: Subjective Qualitymentioning

confidence: 77%

“…For details, our proposed model contains three stages to solve these three sub-problems. First, to predict the relative quality, we use our previous HVSinspired VQA model (Li et al 2019a) as the backbone. The relative quality assessor takes the video as input and outputs a relative quality score.…”

Section: Subjective Qualitymentioning

confidence: 99%

“…Some efforts have been made to generate a better feature for VQA in the wild (You and Korhonen 2019;Korhonen 2019;Li et al 2019a). Korhonen (2019) obtains well-behaved low-complexity features for all frames and high-complexity features for representative frames, so that good quality predictions can be achieved by the support vector regression or the random forest regression.…”

Section: Introductionmentioning

confidence: 99%

“…You and Korhonen (2019) learn effective spatio-temporal features with 3D convolutional neural network (3D-CNN) and predict the video quality by a long-short term memory (LSTM) network. Our previous work (Li et al 2019a) borrows intuitions from human visual system (HVS), which extracts content-aware and distortion-sensitive features. Although the above mentioned methods achieve superior performances on the benchmark VQA datasets individually, their performances are poor in cross-dataset evaluation setting (See Table 7).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Jiang

2021

Int J Comput Vis

Self Cite

115

View full text Add to dashboard Cite

Video quality assessment (VQA) is an important problem in computer vision. The videos in computer vision applications are usually captured in the wild. We focus on automatically assessing the quality of in-the-wild videos, which is a challenging problem due to the absence of reference videos, the complexity of distortions, and the diversity of video contents. Moreover, the video contents and distortions among existing datasets are quite different, which leads to poor performance of datadriven methods in the cross-dataset evaluation setting. To improve the performance of quality assessment models, we borrow intuitions from human perception, specifically, content dependency and temporal-memory effects of human visual system. To face the cross-dataset evaluation challenge, we explore a mixed datasets training strategy for training a single VQA model with multiple datasets. The proposed unified framework explicitly includes three stages: relative quality assessor, nonlinear mapping, and dataset-specific perceptual scale alignment, to jointly predict relative quality, perceptual quality, and subjective quality. Experiments are conducted on four publicly available datasets for VQA in the wild, i.e., LIVE-VQC, LIVE-Qualcomm, KoNViD-1k, and CVD2014. The experimental results verify the effectiveness of the mixed datasets training strategy and prove the superior performance of the unified model in comparison with the state-of-the-art models. For reproducible research, we make the PyTorch implementation of our method available at https://github.com/lidq92/MDTVSFA. Keywords Content dependency • In-the-wild videos • Mixed datasets training • Temporal-memory effect • Video quality assessment Communicated by Mei Chen.

show abstract

“…Lastly, we highlight the relationship and difference between our previous work (Li et al 2019a) and this work. The model design in this work is build upon the model in our previous work.…”

Section: Subjective Qualitymentioning

confidence: 77%

Section: Subjective Qualitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Jiang

2021

Int J Comput Vis

Self Cite

115

View full text Add to dashboard Cite

show abstract

“…The higher performance of the TLVQM is then justified by the fact that among the low complexity features, it also considers the motion estimation of key-pixels across frames. [13] 0.54 ± 0.10 0.55 ± 0.10 10.30 ± 0.9 0.64 ± 0.06 0.59 ± 0.07 13.10 ± 0.8 V-CORNIA [14] 0.61 ± 0.09 0.56 ± 0.09 9.70 ± 0.9 0.72 ± 0.04 0.67 ± 0.05 11.83 ± 0.7 V-BLIINDS [12] 0.67 ± 0.09 0.60 ± 0.10 9.20 ± 1.0 0.72 ± 0.05 0.69 ± 0.05 11.76 ± 0.8 HIGRADE [15] 0.71 ± 0.08 0.68 ± 0.08 8.60 ± 1.1 0.63 ± 0.06 0.61 ± 0.07 13.03 ± 0.9 TLVQM [24] 0.77 ± 0.06 0.74 ± 0.07 7.62 ± 1.0 0.78 ± 0.04 0.78 ± 0.04 10.75 ± 0.9 VSFA [11] 0.75 ± 0.09 0.71 ± 0.10 8.31 ± Figure 5 shows the scatter plots on the four databases. They report the MOS with respect to the corresponding predicted scores for all the samples considered in the 100 iterations.…”

Section: Performance On Single Databasesmentioning

confidence: 99%

No-Reference Quality Assessment of In-Capture Distorted Videos

2020

View full text Add to dashboard Cite

We introduce a no-reference method for the assessment of the quality of videos affected by in-capture distortions due to camera hardware and processing software. The proposed method encodes both quality attributes and semantic content of each video frame by using two Convolutional Neural Networks (CNNs) and then estimates the quality score of the whole video by using a Recurrent Neural Network (RNN), which models the temporal information. The extensive experiments conducted on four benchmark databases (CVD2014, KoNViD-1k, LIVE-Qualcomm, and LIVE-VQC) containing in-capture distortions demonstrate the effectiveness of the proposed method and its ability to generalize in cross-database setup.

show abstract

Built‐In Electric Fields Dramatically Induce Enhancement of Osseointegration

Liu

Zhang

Cao

et al. 2017

Adv Funct Materials

View full text Add to dashboard Cite

Rapid and effective osseointegration is a great challenge in clinical practice. Endogenous electronegative potentials spontaneously appear on bone defect sites and mediate healing. Thus, bone healing can potentially be stimulated using physiologically relevant electrical signals in implants. However, it is difficult to directly introduce physiologically relevant electric fields in bone tissue. In this study, built-in electric fields are established between electropositive ferroelectric BiFeO 3 (BFO) nanofilms and electronegative bone defect walls to trigger implant osseointegration and biological healing. Epitaxial growth technique is used to organize the crystal panel at an atomic scale, and ferroelectric polarization of BFO nanofilms matching the amplitude and direction of endogenous electric potentials on bone defect walls is achieved. In the presence of built-in electric fields, implants with BFO nanofilms with downward polarization (BFO+) show rapid and superior osseointegration in the rat femur. The mechanism of this phenotypic osteogenic behavior is further studied by protein adsorption and stem cell behavior in different time points. BFO+ promotes protein adsorption and mesenchymal stem cell (MSC) attachment, spreading, and osteogenic differentiation. Custom-designed PCR array examination shows sequentially initiated Ca 2+ signaling, cell adhesion and spreading, and PI3K-AKT signaling in MSCs. The results of this study provide a novel strategy for the development of implant surface modification technology.

show abstract

Quality Assessment of In-the-Wild Videos

Cited by 261 publications

References 54 publications

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

No-Reference Quality Assessment of In-Capture Distorted Videos

Built‐In Electric Fields Dramatically Induce Enhancement of Osseointegration

Contact Info

Product

Resources

About