Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos
By Kalpana Seshadrinathan, A. Bovik. IEEE Transactions on Image Processing, 2010
753 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/cac2475bcbb52641ac02e7fe046e808d01e4eaaf
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- A. Bovik
- Lei Zhang
- Ming-Hsuan Yang
- Radu Timofte
- Dacheng Tao
- Luc Van Gool
- Chen Change Loy
- Damon M. Chandler
Citations in the corpus
- Quality Assessment of In-the-Wild Videos (2019, methodology): “Traditional VQAmethods consider structures [47, 48], gradients [21], motion [22, 36], energy [18], saliency [52, 54], or natural video statistics [9, 28, 35, 57].”
- RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment (2012, methodology): “Successful video QA algorithms such as the MOVIE index [28] employ Gabor filters to decompose video data prior to performing QA.”
- Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain (2012, background): “Unlike much of the prior work on image/video quality assessment (QA) [1], [2], [4], [23], [24], we make little direct use of specific perceptual models such as area V1 cortical Fig.”
- FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation (2019, background): “For video denoising algorithms, temporal coherence and flickering removal are crucial aspects in the perceived quality of the results [40, 39].”
- Subjective evaluation of stereoscopic image quality (2013, background): “The squared differences of left and right response amplitudes are divisively normalized (similar to [54]).”
- From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “Many models use low-pass filter or band-pass filter to simulate such a feature [36], [41]–[44].”
- A Completely Blind Video Integrity Oracle (2016, methodology): “We next compared VIIDEO with five FR indices: MSE, MS-SSIM [45], MOVIE [46], VQM [47], ST-MAD [48], one RR index: STRRED [3] and one learning based blind index: V-BLIINDS [8].”
- Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality (2011, background): “1 and is labeled as the DI-IVINE index.”
- Video Quality Assessment on Mobile Devices: Subjective, Behavioral and Objective Studies (2012, methodology): “We also evaluated two FR VQA algorithms – Visual Quality Metric (VQM) [11] and the MOtion-based Video Integrity Evaluation (MOVIE) index [12].”
- Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “, [342, 343]) or are used during optimization procedures (e.”
- Study of Subjective and Objective Quality Assessment of Video (2010, methodology): “However, this difference in performance is not statistically significant and further, MOVIE performs better than Temporal MOVIE on the wireless and IP videos in terms of LCC and on the VQEG database [43].”
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation (2016, methodology): “The metrics compared are PSNR, structural similarity (SSIM) [40] and MOVIE [31] indices.”
- Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing (2013, background): “However, the successful application of either HVS-based approaches or statistical approaches to capture temporal distortions has been limited.”
- Video Denoising, Deblocking, and Enhancement Through Separable 4-D Nonlocal Spatiotemporal Transforms (2012, methodology): “TERMS OF PSNR (dB) AND MOVIE INDEX [46] (THE LOWER THE”
- Blind Prediction of Natural Video Quality (2014, methodology): “Prominent FR-VQA algorithms include MOVIE [6], VSSIM [7], VQM [8], DVQ [9], Tetra VQM [10], ST-MAD [11], and the work in [12] and [13].”
- Objective Video Quality Assessment Methods: A Classification, Review, and Performance Comparison (2011, methodology): “The model described two indices, namely a Spatial MOVIE index that primarily captures spatial distortions and a Temporal MOVIE index that captures temporal distortions.”