The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
A Duality Based Approach for Realtime TV-L 1 Optical Flow
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A reasonable explanation is that the temporal network is actually designed to capture different visual aspects of videos compared to the spatial network, which indicates that the feature distributions are more diverse between those fields (e.g., optical flow and RGB) [20], [24], [25].”
From Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval (2019) · cites this paper as [24]
Citations
Cites
Nonlinear total variation based noise removal algorithms
Rudin, L., Osher, S., & Fatemi, E. (1992) · Physica D Nonlinear Phenomena · doi:10.1016/0167-2789(92)90242-f · Cited by 17,214
Horn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312
Horn, B. K. P., & Schunck, B. G. (1981) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.965761 · Cited by 7,443
chambolle (2004) · doi:10.1023/b:jmiv.0000011321.19549.88 · Cited by 3,227
High Accuracy Optical Flow Estimation Based on a Theory for Warping
Brox, T., Bruhn, A., Papenberg, N., & Weickert, J. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_3 · Cited by 2,634
A computational framework and an algorithm for the measurement of visual motion
Anandan, P. (1989) · International Journal of Computer Vision · doi:10.1007/bf00158167 · Cited by 1,073
Thormaehlen, T., Broszio, H., & Weißenfeld, A. (2004) · Lecture notes in computer science · doi:10.1007/b97865 · Cited by 901
Fast Global Minimization of the Active Contour/Snake Model
Bresson, X., Esedoḡlu, S., Vandergheynst, P., Thiran, J., & Osher, S. (2007) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-007-0002-0 · Cited by 857
A Nonlinear Primal-Dual Method for Total Variation-Based Image Restoration
Chan, T. F.-C., Golub, G. H., & Mulet, P. (1999) · SIAM Journal on Scientific Computing · doi:10.1137/s1064827596299767 · Cited by 849
An Algorithm for Total Variation Minimization and Applications
Chambolle, A. (2004) · Journal of Mathematical Imaging and Vision · doi:10.1023/b:jmiv.0000011325.36760.1e · Cited by 835
Cited by
Sorted by citations
Items 301–400 of 1,002
Illumination-Robust Dense Optical Flow Using Census Signatures
Müller, T., Rabe, C., Rannacher, J., Franke, U., & Mester, R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23123-0_24 · Cited by 46
“The numerical framework sketched in the previous section used the residual function ρ which in [8] or [15] corresponds to the grey-value constancy.”
MethodInfluentialReal-Time Motion Artifact Suppression in TOF Camera Systems
Hussmann, S. H., Hermanski, A., & Edeler, T. (2011) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2010.2102390 · Cited by 46
“By using a graphics-processingunit-based implementation [10], it was possible to produce satisfying results at a frame rate of about 10 frame/s.”
MethodRobust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection
Yang, J., Li, H., Dai, Y., & Tan, R. T. (2016) · 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/cvpr.2016.157 · Cited by 46
“We choose to use 1-norm as the cost function mainly for its robustness [6, 47] and its convenience in optimization.”
MethodPM-PM: PatchMatch With Potts Model for Object Segmentation and Stereo Matching
Xu, S., Zhang, F., He, X., Shen, X., & Zhang, X. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2416654 · Cited by 45
“Potts Model [26]–[28] is a popular supervised segmentation model.”
BackgroundSarabu, A., & Santra, A. K. (2021) · Emerging Science Journal · doi:10.28991/esj-2021-01254 · Cited by 47
“We implement the random shuffle for every iteration for all 60 epochs in the CLSTM. TVL1 optical flow algorithm [25] is employed to generate optical flow frames from videos.”
MethodAn approach to vectorial total variation based on geometric measure theory
Goldlüecke, B., & Cremers, D. (2010) · 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/cvpr.2010.5540194 · Cited by 45
“Since the regularizer can be used as a substitute for vectorial TV in any energy functional, there is a broad spectrum of further applications, see e.g. [3, 9, 12, 19].”
MethodPosterior Expectation of the Total Variation Model: Properties and Experiments
Louchet, C., & Moisan, L. (2013) · SIAM Journal on Imaging Sciences · doi:10.1137/120902276 · Cited by 45
“In the last two decades, the TV prior has been used in a large variety of image processing and computer vision applications: image inpainting [22], interpolation [35], segmentation [20], image quality assessment [8], scale detection [49], cartoon+texture decomposition [4, 5], motion estimation [76], and many others (a…”
Wang, J., & Torresani, L. (2022) · 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/cvpr52688.2022.01366 · Cited by 50
“We include also results obtained with TV-L1 Optical Flow [44] (OF) since optical flow represents the ideal motion cue to use, neglecting cost considerations.”
ResultMotion Compensated Frame Interpolation with a Symmetric Optical Flow Constraint
Rakêt, L. L., Roholm, L., Bruhn, A., & Weickert, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33179-4_43 · Cited by 44
Bätz, M., Eichenseer, A., Seiler, J., Jonscher, M., & Kaup, A. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7350759 · Cited by 44
“For the MISR method at hand, image registration is conducted using the TV-L1based optical flow described in [12, 13], the registered samples are interpolated onto the HR image grid using cubic interpolation, and the well-known Lucy-Richardson deconvolution method is applied for restoration purposes.”
MethodFacial expression recognition on real world face images using intelligent techniques: A survey
Khan, S. A., Hussain, A., & Usman, M. (2016) · Optik · doi:10.1016/j.ijleo.2016.04.015 · Cited by 46
Multiscale gigapixel video: A cross resolution image matching and warping approach
Yuan, X., Fang, L., Dai, Q., Brady, D. J., & Liu, Y. (2017) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2017.7951481 · Cited by 44
“Although robust regularization such as L1 norm [43], sparse descriptor matching term [8, 40], feature correspondences [32], coarse-to-ne mechanism [42] have been proposed to handle large motions, the variational framework is still incompetent in preserving scene structures.”
BackgroundDriver Behavior Analysis via Two-Stream Deep Convolutional Neural Network
Chen, J.-C., Lee, C.-Y., Huang, P., & Lin, C.-R. (2020) · Applied Sciences · doi:10.3390/app10061908 · Cited by 44
“…in OpenCV is firstly applied to obtain vertical and horizontal flow frames between two consecutive frames. to extract the motion information, TVL optical flow [28] with default parameters in OpenCV is firstly applied to obtain vertical and horizontal flow frames between two consecutive frames.”
MethodInfluentialDai, R., Das, S., & Brémond, F. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01281 · Cited by 48
“We find that Two stream RGB + TVL1 [64] achieves high precision on Charades, but at the expense of a high computational cost.”
BackgroundLearning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
Kwon, H., Kim, M., Kwak, S., & Cho, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01282 · Cited by 48
Chan, T. F.-C., & Esser, J. E. (2010) · Cited by 44
Duality TV-L1 flow with fundamental matrix prior
Wedel, A., Pock, T., Braun, J., Franke, U., & Cremers, D. (2008) · 2008 23rd International Conference Image and Vision Computing New Zealand · doi:10.1109/ivcnz.2008.4762119 · Cited by 58
“The main contribution of [5] is the reformulation of the original variational energy functional into a convex dual form, allowing splitting between the data term and the smoothness term in an iterative solving process.”
BackgroundMethodInfluentialSelf-citationMGMAE: Motion Guided Masking for Video Masked Autoencoding
Huang, B., Zhao, Z., Zhang, G., Qiao, Y., & Wang, L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01241 · Cited by 52
“Offline method applies the traditional TVL1 [53] algorithm to extract the dense flows between all adjacent frames in advance.”
MethodReal-time obstacle detection in complex scenarios using dense stereo vision and optical flow
Pantilie, C. D., & Nedevschi, S. (2010) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2010.5625174 · Cited by 43
“Sequential implementations, for increased accuracy dense optical flow algorithms like the one used [15], cannot reach real-time performance.”
Modeling Dynamic 3D Environments by Means of The Stixel World
Pfeiffer, D., & Franke, U. (2011) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2011.942207 · Cited by 43
Klette, R., Krüger, N., Vaudrey, T., Pauwels, K., Hulle, M. M. V., Morales, S., Kandil, F. I., Haeusler, R., Pugeault, N., Rabe, C., et al. (2011) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2011.2148134 · Cited by 43
Investigating the use of motion-based features from optical flow for gait recognition
Mahfouf, Z., Merouani, H. F., Bouchrika, I., & Harrati, N. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.12.040 · Cited by 43
Egocentric Hand Track and Object-Based Human Action Recognition
Kapidis, G., Poppe, R. W., van Dam, E., Noldus, L. P. J. J., & Veltkamp, R. C. (2019) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/smartworld-uic-atc-scalcom-iop-sci.2019.00185 · Cited by 46
“In the 2D case, TSN extracts convolutional features from multiple stacks of either images (RGB stream) or pairs of horizontal and vertical optical flow values (Flow stream) that capture the perceived motion through series of images [41].”
MethodAssembleNet++: Assembling Modality Representations via Attention Connections
Ryoo, M. S., Piergiovanni, A., Kangaspunta, J., & Angelova, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58565-5_39 · Cited by 43
Self-Supervised Learning to Detect Key Frames in Videos
Yan, X., Gilani, S. Z., Feng, M., Zhang, L., Qin, H., & Mian, A. S. (2020) · Sensors · doi:10.3390/s20236941 · Cited by 44
“For the extraction of the optical flow images, we use the TVL1 optical flow algorithm [67] from the OpenCV toolbox.”
MethodInfrared Action Detection in the Dark via Cross-Stream Attention Mechanism
Chen, X., Gao, C., Li, C., Yang, Y., & Meng, D. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3050069 · Cited by 42
Learning a Model-Driven Variational Network for Deformable Image Registration
Jia, X., Thorley, A., Chen, W., Qiu, H., Shen, L., Styles, I. B., Chang, H. J., Leonardis, A., de Marvao, A., O’Regan, D. P., et al. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3108881 · Cited by 49
MiniROAD: Minimal RNN Framework for Online Action Detection
An, J., Kang, H., Han, S. H., Yang, M., & Kim, S. J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00949 · Cited by 46
Online Learning with Self-Organizing Maps for Anomaly Detection in Crowd Scenes
Feng, J., Zhang, C., & Hao, P. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.878 · Cited by 43
“Low level motion information in each frame can be obtained using optical flow technique [10].”
MethodHuman action recognition using histogram of motion intensity and direction from multiple views
Chun, S., & Lee, C.-S. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2015.0233 · Cited by 42
“There has been great progress in dense optical flow estimation with L1 norm regularisation [32, 33], 3D optical flow and spatio-temporal interest points [34], 3D exemplar-based hidden markov models (HMM) [10], optimisation by new descriptors [35], and hierarchical matching [36].”
MethodR-STAN: Residual Spatial-Temporal Attention Network for Action Recognition
Liu, Q., Che, X., & Bie, M. (2019) · IEEE Access · doi:10.1109/access.2019.2923651 · Cited by 42
“But, the extraction of Optical Flow images with TVL1Optical Flow algorithm [40] adopted by the most previous works [15], [30], [39] is really time confusing though which can improve the classification accuracy.”
MethodComprehensive Instructional Video Analysis: The COIN Dataset and Performance Evaluation
Tang, Y., Lu, J., & Zhou, J. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2980824 · Cited by 41
“Here SSN−Flow adopted the optical flows calculated by [78], and SSN−Fusion combined the predicted scores of SSN−RGB and SSN−Flow.”
MethodIntegrating Human Gaze into Attention for Egocentric Activity Recognition
Min, K., & Corso, J. J. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00111 · Cited by 49
“First, we resize each frame to 256× 340 and generate optical flow frames by using the TV-L1 algorithm [39].”
MethodSCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Li, B., Zheng, C., Giancola, S., & Ghanem, B. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20012 · Cited by 41
Illumination-robust variational optical flow using cross-correlation
Molnár, J., Chetverikov, D., & Fazekas, S. (2010) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.07.006 · Cited by 41
A proximity algorithm accelerated by Gauss–Seidel iterations for L1/TV denoising models
Qia, L., Micchelli, C. A., Shen, L., & Xu, Y. (2012) · Inverse Problems · doi:10.1088/0266-5611/28/9/095003 · Cited by 41
“Moreover, it has successful applications in impulsive noise removal [1, 13], computer vision [6], biomedical imaging [17], optical flow and object tracking [19], and shape denoising [19].”
BackgroundOptical flow estimation using learned sparse model
Jia, K., Wang, X., & Tang, X.-O. (2011) · Vision · doi:10.1109/iccv.2011.6126522 · Cited by 48
“Among them, the TV-L1 framework [11, 10] is a popular one, which used total variation (TV) like regularization and a robust L norm in the data term.”
MethodLiu, J., Foged, I. W., & Moeslund, T. B. (2021) · Pattern Analysis and Applications · doi:10.1007/s10044-021-00961-5 · Cited by 41
Automated detection of pneumonia in lung ultrasound using deep video classification for COVID-19
Ebadi, S. E., Krishnaswamy, D., Bolouri, S. E. S., Zonoobi, D., Greiner, R., Meuser-Herr, N., Jaremko, J. L., Kapur, J., Noga, M., & Punithakumar, K. (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100687 · Cited by 41
“We extract optical flow sequences with the TV-L1 algorithm [23].”
A Survey on Time-of-Flight Stereo Fusion
Nair, R., Ruhl, K., Lenzen, F., Meister, S., Schäfer, H., Garbe, C. S., Eisemann, M., Magnor, M. A., & Kondermann, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-44964-2_6 · Cited by 41
Video Object Grounding Using Semantic Roles in Language Description
Sadhu, A., Chen, K., & Nevatia, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01043 · Cited by 36
SOLD: Sub-optimal low-rank decomposition for efficient video segmentation
Li, C., Lin, L., Zuo, W., Yan, S., & Tang, J. (2015) · 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/cvpr.2015.7299191 · Cited by 40
Spatio-Temporal VLAD Encoding for Human Action Recognition in Videos
Duţă, I. C., Ionescu, B. E., Aizawa, K., & Sebe, N. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-51811-4_30 · Cited by 41
“To extract optical flow fields we use the OpenCV implementation of TVL1 algorithm [39].”
MethodLightweight network architecture for real-time action recognition
Kozlov, A., Andronov, V., & Gritsenko, Y. (2020) · ACM Symposium on Applied Computing · doi:10.1145/3341105.3373906 · Cited by 41
“Calculating OF with traditional algorithms, such as TVL1 [55], requires extra resources, but there are several ways to avoid it.”
MethodEnd-to-end deep learning for recognition of ploidy status using time-lapse videos
Lee, C.-I., Su, Y.-R., Chen, C.-H., Chang, T. A., Kuo, E. E.-S., Zheng, W.-L., Hsieh, W.-T., Huang, C.-C., Lee, M., & Liu, M. (2021) · Journal of Assisted Reproduction and Genetics · doi:10.1007/s10815-021-02228-8 · Cited by 40
Maruyama, M., Singh, S., Inoue, K., Roy, P. P., Iwamura, M., & Yoshioka, M. (2022) · IEEE Access · doi:10.1109/access.2024.3494878 · Cited by 43
“In contrast, in the stream for optical flow information, M optical flow images calculated from M + 1 consecutive frame images using TV-L1 algorithm [52] are input to the I3D.”
Donley, J., Tourbabin, V., Lee, J., Broyles, M., Jiang, H., Shen, J., Pantić, M., Ithapu, V. K., & Mehra, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04174 · Cited by 59
“To compensate for the large motion of the camera in egocentric videos, we estimate the 2 × 2 homography H between the current video frame and the previous video frame using optical flow [17]. b is a deep feature that can distinguish between head appearances of different people.”
MethodVideo summarization via spatio-temporal deep architecture
Zhong, S.-H., Wu, J., & Jiang, J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.12.040 · Cited by 40
A Convolutional Neural Network for Compound Micro-Expression Recognition
Zhao, Y., & Xu, J. (2019) · Sensors · doi:10.3390/s19245553 · Cited by 40
“In this section, we used the Total Variation-L1 (TV-L1) optical flow algorithm [40] to calculate the motion information between the onset frame and the apex frame.”
MethodFine-Grained Instance-Level Sketch-Based Video Retrieval
Xu, P., Liu, K., Xiang, T., Hospedales, T. M., Ma, Z., Guo, J. H., & Song, Y.-Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3014491 · Cited by 39
“Secondly, use this selected frame as a start frame to compute L pairs of consecutive optical flows using the GPU implementation of TV-L1 [49] in OpenCV.”
MethodGwosdek, P., Zimmer, H., Grewenig, S., Bruhn, A., & Weickert, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35740-4_29 · Cited by 39
Temporal Difference Networks for Video Action Recognition
Ng, J. Y.-H., & Davis, L. S. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00176 · Cited by 36
“For the temporal stream networks, we compute the optical flow with the TV-L1 algorithm [41] using the OpenCV”
MethodLearning deep representations for video-based intake gesture detection
Rouast, P. V., & Adam, M. T. P. (2020) · Figshare · Cited by 38
Zhao, T., Han, J., Yang, L., Wang, B., & Zhang, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01473-9 · Cited by 38
Müller, R. W., & Pfeifroth, U. (2022) · Atmospheric measurement techniques · doi:10.5194/amt-15-1537-2022 · Cited by 38
An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Weng, Y., Pan, Z., Han, M., Chang, X., & Zhuang, B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19830-4_21 · Cited by 41
High-Accuracy Total Variation With Application to Compressed Video Sensing
Hosseini, M. S., & Plataniotis, K. N. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2332755 · Cited by 37
Local/global scene flow estimation
Quiroga, J., Frédéric Devernay, A., & Crowley, J. L. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738793 · Cited by 37
“To compute the scene flow we introduce in (6) an auxiliary flow u (following [15]) and solve for the 3D motion field v that minimizes”
MethodLearning Deep Representations for Video-Based Intake Gesture Detection
Rouast, P. V., & Adam, M. T. P. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2942845 · Cited by 42
“All models are learned end-to-end, optical flow is precomputed using Dual TV-L [46].”
MethodTransfer Learning For Videos: From Action Recognition To Sign Language Recognition
Sarhan, N., & Frintrop, S. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191289 · Cited by 37
“We generate optical flow frames from the RGB data based on the “Dual TV-L1” optical flow algorithm in [20].”
MethodLearning optical flow from still images
Aleotti, F., Poggi, M., & Mattoccia, S. (2021) · 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/cvpr46437.2021.01495 · Cited by 36
“For a long time, optical flow has been cast as a continuous optimization problem through variational frameworks [16, 3, 67].”
BackgroundFast and exact solution of Total Variation models on the GPU
Pock, T., Unger, M., Cremers, D., & Bischof, H. (2008) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2008.4563099 · Cited by 37
“Examples include real-time optical flow computation [34], medical image registration [27], 3D reconstruction [20], range image fusion [35] and image segmentation [30].”
BackgroundSelf-citationSide Information and Noise Learning for Distributed Video Coding Using Optical Flow and Clustering
Luong, H. V., Rakêt, L. L., Huang, X., & Forchhammer, S. O. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2215621 · Cited by 36
Optical Flow via Locally Adaptive Fusion of Complementary Data Costs
Kim, T. H., Lee, H. S., & Lee, K. M. (2013) · IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.415 · Cited by 46
“To address this problem, quadratic relaxation method is widely used [2, 26, 21].”
BackgroundMethodLiu, J., Foged, I. W., & Moeslund, T. B. (2022) · Sensors · doi:10.3390/s22020619 · Cited by 39
“When it comes to the optical flow intensity in a person’s bounding box from the t th to ( t + itv − 1 ) th frame ( itv equals to 210 here), for each frame two optical flows in horizontal and vertical directions are extracted by the TV-L1 algorithm [64] realized in a tool called MMAction [65].”
MethodCreating Fluid Animation from a Single Image using Video Database
Okabe, M., Anjyor, K., & Onai, R. (2011) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2011.02062.x · Cited by 36
Recognizing Emotions From an Ensemble of Features
Tariq, U., Lin, K.-H., Li, Z., Zhou, X., Wang, Z., Le, V., Huang, T. S., Lv, X., & Han, T. X. (2012) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2012.2194701 · Cited by 36
“The authors used the software from [29] for optic”
MethodAdaptive correction procedure for TVL1 image deblurring under impulse noise
Bai, M., Zhang, X., & Shao, Q. (2016) · Inverse Problems · doi:10.1088/0266-5611/32/8/085004 · Cited by 36
“These lead to the successful applications of the TVL1 model in medical imaging [19], computer vision [9], optical flow and object tracking [38].”
MethodGate-Shift-Fuse for Video Action Recognition
Sudhakaran, S., Escalera, S., & Lanz, O. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268134 · Cited by 35
“that performs TV-L1 [73], a popular optical flow extraction technique.”
MethodDense multibody motion estimation and reconstruction from a handheld camera
Roussos, A., Russell, C., Garg, R., & Agapito, L. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402535 · Cited by 35
“We follow the paradigm of the large displacement optical flow method [32], which avoids the loss of detail inherent to common coarse-to-fine approaches [41, 5].”
MethodLearning Spatiotemporal Attention for Egocentric Action Recognition
Lu, M., Liao, D., & Li, Z.-N. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00543 · Cited by 34
“We compute optical flow using TV-L1 algorithm [38], and we truncate the flow values to the range of [-20, 20] and scale them to [-1, 1].”
MethodFine-Grained Action Recognition on a Novel Basketball Dataset
Gu, X., Xue, X., & Wang, F. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053928 · Cited by 35
“In our experiments, we extract frames from videos at 25 fps, and employ the TVL1 algorithm [28] to extract the optical flow.”
MethodCounting Bites and Recognizing Consumed Food from Videos for Passive Dietary Monitoring
Qiu, J., Lo, F. P.-W., Jiang, S., Tsai, Y.-Y., Sun, Y., & Lo, B. P. L. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3022815 · Cited by 36
“As bite counting relies on capturing motion of taking a bite, we also calculated optical flows using the TV-L1 algorithm [67] as an additional modality for bite counting.”
MethodHutchinson, M., & Gadepally, V. N. (2021) · IEEE Access · doi:10.1109/access.2021.3115476 · Cited by 46
“Many methods exist for computing this feature: the Lucas–Kanade method [152], the Horn–Schunck method [153], the TV-L 1 approach [154], the Farneback method [146], and others [155].”
MethodRobust Optical Flow Estimation
Pérez, J. S., Monzón, N., & de la Nuez, A. S. (2013) · Image Processing On Line · doi:10.5201/ipol.2013.21 · Cited by 35
“[11], which has also been implemented on an IPOL article [9].”
Virtual reality in training artificial intelligence-based systems: a case study of fall detection
Bui, V., & Alaei, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13080-y · Cited by 34
“Since the algorithm operates on optical flow images, the same Dual TVL1 Optical Flow algorithm proposed by the authors was used to compute the sequence of optical flow images from our generated fall scenarios [55].”
MethodQuantifying Progression of Multiple Sclerosis via Classification of Depth Videos
Kontschieder, P., Dorn, J. F., Morrison, C. P., Corish, R., Zikic, D., Sellen, A. J., D’Souza, M., Kamm, C. P., Burggraaff, J., Tewarie, P. K. B., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10470-6_54 · Cited by 34
Active matching for visual tracking
Chli, M., & Davison, A. J. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.07.010 · Cited by 34
Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation
Hornáček, M., Besse, F., Kautz, J., Fitzgibbon, A. W., & Rother, C. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9_15 · Cited by 34
“TV = A Duality Based Approach for Realtime TV-L1 Optical Flow [31].”
MethodRegularization Strategies for Discontinuity-Preserving Optical Flow Methods
Monzón, N., Salgado, A., & Sánchez, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2526903 · Cited by 14
“[11] relying on a dual formulation, which yields a very efficient numerical scheme.”
BackgroundMethodYu, Y., Xu, M., & Gu, J. J. (2019) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5409 · Cited by 36
“Given an image sequence, the duality based TV-L1 estimation algorithm [67, 68] is used to calculate the pixel-based optical flow vector g.”
MethodEquivalent Classification Mapping for Weakly Supervised Temporal Action Localization
Zhao, T., Han, J., Yang, L., & Zhang, D. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3178957 · Cited by 35
“The optical flow is calculated via the TV-L1 [48] algorithm.”
Method3D Scene Geometry Estimation from 360° Imagery: A Survey
da Silveira, T. L. T., Pinto, P. G. L., Murrugarra-Llerena, J., & Jung, C. R. (2022) · ACM Computing Surveys · doi:10.1145/3519021 · Cited by 34
“In another line of work, Bagnato et al. [171], extend the Total Variation L1-Regularized [172] approach for real-time optical flow.”
BackgroundA Knowledge-Based Hierarchical Causal Inference Network for Video Action Recognition
Liu, Y., Liu, F., Jiao, L., Bao, Q., Li, L., Guo, Y., & Chen, P. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3386339 · Cited by 33
“3 video datasets, save them with the short edge set to 256 pixels, and use the TV1 method [81] to extract optical flow images.”
MethodDemetz, O., Hafner, D., & Weickert, J. (2013) · British Machine Vision Conference · doi:10.5244/c.27.50 · Cited by 41
Muller, T., Rannacher, J., Rabe, C., & Franke, U. (2011) · doi:10.1109/cvpr.2011.5995633 · Cited by 33
“In [20], the authors split the energy functional in Eq.”
BackgroundMethodInfluentialStructure and motion from scene registration
Basha, T., Avidan, S., Hornung, A., & Matusik, W. (2012) · 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/cvpr.2012.6247830 · Cited by 31
As-Rigid-As-Possible Stereo under Second Order Smoothness Priors
Zhang, C., Li, Z., Cai, R., Chao, H., & Rui, Y. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10605-2_8 · Cited by 33
“, first order priors [2][3][4], second-order priors [1][5] and segment-based priors [6][7][8][9].”
A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos
Gleason, J., Ranjan, R., Schwarcz, S. L., Castillo, C. D., Cheng, J.-C., & Chellappa, R. (2019) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2019.00021 · Cited by 33
Measuring Surface Velocity of Water Flow by Dense Optical Flow Method
Wu, H., Zhao, R., Gan, X., & Ma, X. (2019) · Water · doi:10.3390/w11112320 · Cited by 33
Real-Time Surveillance System for Analyzing Abnormal Behavior of Pedestrians
Kim, D., Kim, H., Mok, Y., & Paik, J. (2021) · Applied Sciences · doi:10.3390/app11136153 · Cited by 33
A Robust Edge-Preserving Stereo Matching Method for Laparoscopic Images
Xia, W., Chen, E. C. S., Pautler, S., & Peters, T. M. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3147414 · Cited by 33
“Following the fast algorithm [35], Eqn.”
MethodInfluentialMultimodal Distillation for Egocentric Action Recognition
Radevski, G., Grujicic, D., Blaschko, M. B., Moens, M., & Tuytelaars, T. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00481 · Cited by 32
“We use optical flow obtained using TV-L 1 [60].”
MethodIllumination invariant optical flow using neighborhood descriptors
Ali, S., Daul, C., Galbrun, E., & Blondel, W. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.12.003 · Cited by 32
“The minimization of the energy function E(u) usng a primal-dual model in convex optimization has been well estabished in the literature of variational optical flow [7,8,42].”
BackgroundMethodInfluentialIllumination Robust Optical Flow Model Based on Histogram of Oriented Gradients
Rashwan, H. A., Mohamed, M. A., García, M. Á., Mertsching, B., & Puig, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40602-7_38 · Cited by 32
Duţă, I. C., Uijlings, J., Ionescu, B. E., Aizawa, K., Hauptmann, A. G., & Sebe, N. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4795-6 · Cited by 32
“There is a large number of approaches for extracting the optical flow fields, from relatively classic methods, such as [14, 27] to relatively recent approaches like [5, 6, 13, 54], which use complex algorithms to compute the motion information.”
MethodPandey, P., Prathosh, A. P., Kohli, M., & Pritchard, J. (2020) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v34i01.5383 · Cited by 32
Registration and Fusion of Close-Range Multimodal Wheat Images in Field Conditions
Dandrifosse, S., Carlier, A., Dumont, B., & Mercatoris, B. (2021) · Remote Sensing · doi:10.3390/rs13071380 · Cited by 32
Abnormal Behavior Detection in Uncrowded Videos with Two-Stream 3D Convolutional Neural Networks
Mehmood, A. (2021) · Applied Sciences · doi:10.3390/app11083523 · Cited by 32
“To address this issue further, the TVL-1 optical flow algorithm [52] was chosen due to its strength in changing light conditions.”
MethodMulti-Scale Structure-Aware Network for Weakly Supervised Temporal Action Detection
Yang, W., Zhang, T., Mao, Z., Zhang, Y., Tian, Q. C., & Wu, F. H. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3089361 · Cited by 32
“And TV-L1 optical flow [64] is used to generate optical frames.”
Method
Metadata
- Authors
- Zach, C., Pock, T., & Bischof, H.
- Affiliations
- VRVis GmbH (Austria) (AT)
- Graz University of Technology (AT)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2007-09-21
- Pages
- 214-223
- OpenAlex
- W1578985305
- Cited by
- 1,658
- References
- 27
- Citations by year
- 2026: 44 · 2025: 62 · 2024: 83 · 2023: 111 · 2022: 107 · 2021: 188 · 2020: 152 · 2019: 149 · 2018: 112 · 2017: 98 · 2016: 88 · 2015: 99 · 2014: 70 · 2013: 59 · 2012: 56
- FWCI
- 27.93
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Springer eBooks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- optical flow, total variation regularization, GPU acceleration, real-time video processing, variational methods, discontinuity preservation
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
