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 501–600 of 1,002
A photogrammetry-based variational optimization method for river surface velocity measurement
Huang, K., Chen, H., Xiang, T., Lin, Y., Liu, B., Wang, J., Liu, D., & Xu, C. (2021) · Journal of Hydrology · doi:10.1016/j.jhydrol.2021.127240 · Cited by 23
Implementation of the Centroid Method for the Correction of Turbulence
Meinhardt-Llopis, E., & Micheli, M. (2014) · Image Processing On Line · doi:10.5201/ipol.2014.105 · Cited by 23
“Any general optical flow algorithm can be used in our application; for example Horn–Schunck [10, 14], Lucas–Kanade [2] or TV –L(1) [23, 19].”
MethodLearning Semantic Motion Patterns for Dynamic Scenes by Improved Sparse Topical Coding
Fu, W., Wang, J., Li, Z., Lu, H., & Ma, S. (2012) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2012.133 · Cited by 23
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
Guan, S., Li, H., & Zheng, W. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00039 · Cited by 23
“TVL-1 [1]) treat the estimation problem as a energy function minimization problem, making strong assumptions on the pixel-level information such as brightness and spatial smoothness [2].”
BackgroundMethodKalman Filtering of Patches for Frame-Recursive Video Denoising
Arias, P., & Morel, J. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00243 · Cited by 23
“For our experiments, we used the implementation [34] of the TV-L1 optical flow introduced in [41].”
MethodActivity Recognition From Newborn Resuscitation Videos
Meinich-Bache, Ø., Austnes, S. L., Engan, K., Austvoll, I., Eftestøl, T. C., Myklebust, H., Kusulla, S., Kidanto, H. L., & Ersdal, H. L. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2978252 · Cited by 23
Shao, Z., Cheng, Y., Li, F., Zhou, Y., Lu, X., Xie, Y., & Ma, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3581162 · Cited by 28
Dynamic scene understanding by improved sparse topical coding
Fu, W., Wang, J., Lu, H., & Ma, S. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.11.013 · Cited by 22
“Given an input video, optical flow features are extracted for each pair of consecutive frames using the method proposed in [17].”
MethodHanda, A., Chli, M., Strasdat, H., & Davison, A. J. (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.2010.5539788 · Cited by 22
“For instance, highly impressive results have been achieved in fully dense optical flow using variational optimisation, achieving realtime operation on the latest GPU processors [19].”
BackgroundRecapNet: Action Proposal Generation Mimicking Human Cognitive Process
Wang, T., Chen, Y., Lin, Z., Zhu, A., Li, Y., Snoussi, H., & Wang, H. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2965196 · Cited by 21
“The optical flow is computed with TV-L1 algorithm [58].”
MethodVideo frame interpolation via optical flow estimation with image inpainting
Liu, X., Liu, H., & Lin, Y. (2020) · International Journal of Intelligent Systems · doi:10.1002/int.22285 · Cited by 22
“To overcome the shortcomings of L 2 norm in the CLG optical flow estimation model that is sensitive to image noise, L 1 norm constraint on optical flow is introduced 30 to make the estimation model more robust against noise.”
MethodPramono, R. R. A., Fang, W., & Chen, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3113570 · Cited by 23
Attention-Driven Appearance-Motion Fusion Network for Action Recognition
Liu, S., & Ma, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3148588 · Cited by 22
“The TV-L1 [49] method is a specific optical flow solver, which has been applied successfully to action recognition.”
MethodAdaptive Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Zhai, Y., Wang, L., Tang, W., Zhang, Q., Zheng, N., Doermann, D., Yuan, J., & Hua, G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3189662 · Cited by 24
“The optical flow is estimated via the TV-L1 algorithm [71].”
MethodMotion Field Estimation from Alternate Exposure Images
Sellent, A., Eisemann, M., Goldlüecke, B., Cremers, D., & Magnor, M. A. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.218 · Cited by 22
“A discussion of the sensitivity on the parameter choice is given in Section 6.”
BackgroundLetelier, J. A., Herrera, P., Mujica, N., & Ortega, J. H. (2016) · Experiments in Fluids · doi:10.1007/s00348-015-2109-1 · Cited by 22
“An efficient method given by Zach et al. (2007), which uses the duality-based method proposed by Chambolle (2004), solves Eq.”
BackgroundMethodInfluentialMulti-View and Multi-Modal Action Recognition with Learned Fusion
Ardianto, S., & Hang, H. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659539 · Cited by 21
“The optical flow information was generated from the RGB video based on the motion vectors produced by the TVL1 optical flow algorithm [9].”
MethodReal-Time End-to-End Action Detection with Two-Stream Networks
Ali, A., & Taylor, G. W. (2018) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2018.00015 · Cited by 29
CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds
Nielsen, A. H., Iosifidis, A., & Karstoft, H. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3062936 · Cited by 25
“L 1 optical flow method introduced by [37] to capture cloud motions on multiple scales spatially based on two subsequent raw satellite images.”
MethodHuman Action Recognition by Discriminative Feature Pooling and Video Segment Attention Model
Moniruzzaman, M., Yin, Z., He, Z., Qin, R., & Leu, M. C. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3058050 · Cited by 22
Gradient Boundary Histograms for Action Recognition
Shi, F., Laganière, R., & Petriu, E. M. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.152 · Cited by 22
“The MBH is based on the Farnebäck’s optical flow method [3], and MBH uses dualitybased TV L1 approach [25].”
MethodConvex Optimization with Abstract Linear Operators
Diamond, S., & Boyd, S. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.84 · Cited by 22
Seeing and Hearing Egocentric Actions: How Much Can We Learn?
Cartas, A., Luque, J., Radeva, P. I., Segura, C., & Dimiccoli, M. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00548 · Cited by 21
Action Coherence Network for Weakly-Supervised Temporal Action Localization
Zhai, Y., Wang, L., Tang, W., Zhang, Q., Zheng, N., & Hua, G. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3073235 · Cited by 22
“The optical flow is estimated with TV-L1 algorithm [70], and only forward optical flow is computed.”
MethodLebert, J., Ravi, N., Kensah, G., & Christoph, J. (2022) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2022.787627 · Cited by 21
Shallow multi-branch attention convolutional neural network for micro-expression recognition
Wang, G., Huang, S., & Tao, Z. (2023) · Multimedia Systems · doi:10.1007/s00530-023-01080-3 · Cited by 22
“Inspired by Liong et al. [34], we adopt the TV-L1 method [49] to extract MEs’ OF features, i.e., horizontal optical flow, vertical optical flow, and optical strain, to enrich the motion variations of MEs further.”
MethodNickel, F., Studier‐Fischer, A., Özdemir, B., Odenthal, J., Müller, L.-R., Knoedler, S. A., Kowalewski, K., Camplisson, I., Allers, M. M., Dietrich, M., et al. (2023) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2023.04.007 · Cited by 21
Decomposed Cross-Modal Distillation for RGB-based Temporal Action Detection
Lee, P., Kim, T., Shim, M., Wee, D., & Byun, H. (2023) · 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/cvpr52729.2023.00235 · Cited by 26
Estimation of sea surface currents based on ocean colour remote-sensing image analysis
Sun, H., Song, Q., Shao, R., & Schlicke, T. (2016) · International Journal of Remote Sensing · doi:10.1080/01431161.2016.1226526 · Cited by 21
“…flow approaches have been developed (Brox et al. 2004; Bruhn, Weickert, and Schnörr 2005; Horn and Schunck 1981; Sánchez, Monzón, and Salgado 2013; Zach, Pock, and Bischof 2007), such as the approaches from HS (Horn & Schunck), LK (Lucas & Kanade), and CLG (Combined Local and Global),…”
MethodBi-Directional Vectors from Apex in CNN for Micro-Expression Recognition
Gan, Y. S., & Liong, S. (2018) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2018.8492829 · Cited by 20
“Alternatively, the motion changes can be approximated by employing optical flow estimation technique [29].”
MethodMoving Foreground-Aware Visual Attention and Key Volume Mining for Human Action Recognition
Zhang, J., Hu, H., & Lu, X. (2019) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3321511 · Cited by 21
“The input of Temporal Net is the stacked optical flow images (the length is set as 10), which are extracted based on the TVL1 method [38].”
MethodA Novel Tracking Method Based on Improved FAST Corner Detection and Pyramid LK Optical Flow
Zhang, H., Li, X., & Xu, G. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164332 · Cited by 21
“Typical values for x w and y w usually take integer pixels between [2,7] .”
BackgroundMulti-View Stereo: Redundancy Benefits for 3D Reconstruction
Rumpler, M., Irschara, A., & Bischof, H. (2011) · Cited by 21
Self-citationHealth & Gait: a dataset for gait-based analysis
Zafra-Palma, J., Marín‐Jiménez, N., Castro‐Piñero, J., Cuenca‐García, M., Muñoz‐Salinas, R., & Marín-Jiménez, M. J. (2025) · Scientific Data · doi:10.1038/s41597-024-04327-4 · Cited by 21
Motion propagation detection association for multi-target tracking in wide area aerial surveillance
Chen, B.-J., & Medioni, G. G. (2015) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2015.7301766 · Cited by 20
“3(b) shows the inconsistency in dense flow result [17]”
BackgroundA Comparison Study on Implementing Optical Flow and Digital Communications on FPGAs and GPUs
Bodily, J., Nelson, B., Wei, Z., Lee, D.-J., & Chase, J. (2010) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/1754386.1754387 · Cited by 20
Sequential Segment Networks for Action Recognition
Chen, Q.-Q., & Zhang, Y. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2689921 · Cited by 20
Improving Human Action Recognition by Non-action Classification
Wang, Y., & Hoai, M. (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.2016.295 · Cited by 21
Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos
Ghoddoosian, R., Dwivedi, I., Agarwal, N., & Dariush, B. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00929 · Cited by 20
“We employ the pre-trained I3D network [6] to extract features from optical flow [41] and RGB frames for both datasets.”
MethodHorn–Schunck optical flow applied to deformation measurement of a birdlike airfoil
Gong, X., & Bansmer, S. E. (2015) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2015.07.005 · Cited by 20
Passive Tomography of Turbulence Strength
Alterman, M., Schechner, Y. Y., Vo, M., & Narasimhan, S. G. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10593-2_4 · Cited by 20
“To compute the pixel displacement variance m, we use dense optical flow [53] implemented in OpenCV.”
MethodMultiframe Scene Flow with Piecewise Rigid Motion
Golyanik, V., Kim, K., Maier, R. L., NieBner, M., Stricker, D., & Kautz, J. (2017) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00039 · Cited by 20
A comprehensive solution for detecting events in complex surveillance videos
Zhu, Y., Zhou, K., Wang, M., Zhao, Y., & Zhao, Z. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6163-6 · Cited by 20
“For the extraction of optical flow fields, we choose the TVL1 [38] optical flow algorithm.”
MethodAttacking Automatic Video Analysis Algorithms
Hosseini, H., Xiao, B., Clark, A., & Poovendran, R. (2017) · doi:10.1145/3137616.3137618 · Cited by 28
“Optical flow encodes the pattern of apparent motion of objects and is computed from two adjacent frames sampled at higher rates than the video frames [59].”
BackgroundHallucinating Optical Flow Features for Video Classification
Tang, Y., Ma, L., & Zhou, L. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/130 · Cited by 22
Uncovering Human Multimodal Activity Recognition with a Deep Learning Approach
Ranieri, C. M., Vargas, P. A., & Romero, R. A. F. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207255 · Cited by 19
“Optical flow was calculated with the TVL1 algorithm [32].”
MethodModeling heading and path perception from optic flow in the case of independently moving objects
Raudies, F., & Heiko Neumann, B. (2013) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2013.00023 · Cited by 20
“In the first part, we derive a motion model for linear motion toward a plane and curvilinear motion above a ground plane or toward an initially fronto-parallel plane.”
MethodContextual Action Cues from Camera Sensor for Multi-Stream Action Recognition
Hong, J. K., Cho, B., Hong, Y. W., & Byun, H. (2019) · Sensors · doi:10.3390/s19061382 · Cited by 20
“Furthermore, the information in the time domain is extracted via the optical flow [17].”
MethodBetter Dense Trajectories by Motion in Videos
Liu, Y., Shen, J., Wang, W., Sun, H., & Shao, L. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2769097 · Cited by 19
“According to the evaluation criteria in the last section, we will give more comparison results with LDOF [29], TV-L1 [8], deepflow [17], Classic+NL [19], and ours.”
ResultKuang, L., Wang, Y., Hang, T., Chen, B., & Zhao, G. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11539-y · Cited by 22
“The detailed solution of (2) can be found in [37].”
BackgroundInteractive image/video retexturing using GPU parallelism
Li, P., Sun, H., Huang, C., Shen, J., & Nie, Y. (2012) · Computers & Graphics · doi:10.1016/j.cag.2012.07.004 · Cited by 19
Stereo Ground Truth with Error Bars
Kondermann, D., Nair, R. S., Meister, S., Mischler, W., Güssefeld, B., Honauer, K., Hofmann, S., Claus Brenner, A., & Jähne, B. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16814-2_39 · Cited by 19
Optical flow estimation from multichannel spherical image decomposition
Radgui, A., Demonceaux, C., Mouaddib, E. M., Rziza, M., & Aboutajdine, D. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.05.002 · Cited by 19
Robust Optical Flow Integration
Crivelli, T., Fradet, M., Conze, P.-H., Robert, P., & Pérez, P. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2336547 · Cited by 19
“…Identifier 10.1109/TIP.2014.2336547 consecutive video frames appear as the natural tool to build dense point trajectories: any optical flow technique, from the classic Horn and Schunk estimator [5] and alternatives [6] to its most recent descendants [7]–[9], can be readily used to construct any…”
BackgroundInfluentialTV-L 1 Optical Flow for Vector Valued Images
Rakêt, L. L., Roholm, L., Nielsen, M., & Lauze, F. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23094-3_24 · Cited by 19
“In this paper we have proposed a generalization of the TV-L 1 optical flow algorithm by Zach et al. [ 1 ].”
BackgroundMethodInfluentialAction recognition using edge trajectories and motion acceleration descriptor
Wang, X., & Qi, C. (2016) · Machine Vision and Applications · doi:10.1007/s00138-016-0746-x · Cited by 19
“The algorithm in [37] is employed to compute optical flow, which is reused later to compute motion-related descriptors (i.”
MethodEfficient motion estimation methods for fast recognition of activities of daily living
Poularakis, S., Avgerinakis, K., Briassouli, A., & Kompatsiaris, I. Y. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.01.005 · Cited by 19
Using Background-Oriented Schlieren to Visualize Convection in a Propagating Wildland Fire
Aminfar, A., Cobian‐Iñiguez, J., Ghasemian, M., Espitia, N. R., Weise, D. R., & Princevac, M. (2019) · Combustion Science and Technology · doi:10.1080/00102202.2019.1635122 · Cited by 19
One-shot learning hand gesture recognition based on modified 3d convolutional neural networks
Lu, Z., Qin, S., Li, X., Li, L., & Zhang, D. (2019) · Machine Vision and Applications · doi:10.1007/s00138-019-01043-7 · Cited by 19
“computed optical flow [60] and saliency images [61] from RGB videos, respectively, as illustrated in Fig.”
MethodTemporal Spiking Recurrent Neural Network for Action Recognition
Wang, W., Hao, S., Wei, Y., Xiao, S., Feng, J., & Sebe, N. (2019) · IEEE Access · doi:10.1109/access.2019.2936604 · Cited by 21
“The optical flows are extracted using the algorithm [33] implemented in OpenCV.”
MethodGenerating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models
de Souza, C. R., Gaidon, A., Cabon, Y., Murray, N., & López, A. M. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01222-z · Cited by 19
“Cool mixed-source mini-batches. for the PHAV samples in the motion stream, we use the same fast optical flow estimation algorithm as Wang et al. (2016b), i.e. TV-(cid:96) 1 (Zach et al., 2007), for all samples in order to fairly estimate the usefulness of our generated videos.”
A Multi-Stream Convolutional Neural Network Framework for Group Activity RecognitionPreprint
Azar, S. M., Atigh, M. G., & Nickabadi, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.10328 · Cited by 19
Gaze-Assisted Multi-Stream Deep Neural Network for Action Recognition
Liu, Y., Wu, Q., Tang, L., & Shi, H. (2017) · IEEE Access · doi:10.1109/access.2017.2753830 · Cited by 18
“The optical flow is extracted by TVL1 [36], which is widely used in different variations of two-stream deep networks.”
MethodMotion Guided LiDAR-Camera Self-calibration and Accelerated Depth Upsampling for Autonomous Vehicles
Castorena, J., Puskorius, G. V., & Pandey, G. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01233-w · Cited by 18
“However, given that current learnable optical flow methods are not invariant to camera model and type which is highly inconvenient to our camera-LiDAR registration problem we resort to the total variation (TV) optical flow method of [15].”
BackgroundGhoddoosian, R., Sayed, S., & Athitsos, V. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00020 · Cited by 18
Weakly Supervised Moment Localization with Decoupled Consistent Concept Prediction
Ma, F., Zhu, L., & Yang, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01600-0 · Cited by 18
“Video Encoding To encode both visual object and motion information in videos, we adopt TVL1 (Zach et al. 2007) to extract optical flow and use RGB and flow images for extracting video features.”
MethodYang, W., Zhang, T., Zhang, Y., & Wu, F. H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200399 · Cited by 18
Ouyed, A., Smith, N., Zeng, X., Galarneau, T. J., Su, H., & Dixon, R. D. (2023) · Geophysical Research Letters · doi:10.1029/2022gl101830 · Cited by 18
“We used Dense Optical Flow (DOF), specifically the OpenCV (Bradski, 2000) implementation of the TV-L 1 algorithm (Zach et al., 2007), to compute AMVs from the quality controlled (rectangular) patches FNOAA20 and FSNPP.”
MethodLocal-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding
Bao, P., Xia, Y., Yang, W., Ng, B. P., Er, M. H., & Kot, A. C. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i2.27831 · Cited by 18
“TV-L1 algorithm (Zach, Pock, and Bischof 2007) and the I3D network are applied to compute the optical flow features.”
MethodEfficient human action recognition by cascaded linear classifcation
Roth, P. M., Mauthner, T., Khan, I., & Bischof, H. (2009) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2009.5457655 · Cited by 18
“Thus, for frame t the appearance features are computed from frame t, and the flow features are extracted from framest andt 1. In particular, to estimate the optical dense flow field, we apply the method proposed in [ 32 ], which is publicly available: OFLib1.”
MethodSelf-citationBag of Optical Flow Volumes for Image Sequence Recognition
Riemenschneider, H., Donoser, M., & Bischof, H. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.28 · Cited by 18
“Highly accurate dense optical flow can now be calculated in real-time [26].”
BackgroundMethodSelf-citationLi, J., Zhou, Y., Ivanov, K., & Zheng, Y. (2013) · Ultrasonics · doi:10.1016/j.ultras.2013.09.024 · Cited by 18
“[52]):”
Ali, S., Daul, C., Weibel, T., & Blondel, W. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738266 · Cited by 18
“In that case, we use a fast and robust optical flow method [8] to determine the dense point correspondence between the image pairs.”
MethodHigh dynamic range imaging of non-static scenes
Hossain, I., & Gunturk, B. K. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.872513 · Cited by 18
A Variational Framework for Structure from Motion in Omnidirectional Image Sequences
Bagnato, L., Pascal Frossard, B., & Vandergheynst, P. (2011) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-011-0267-1 · Cited by 18
Anisotropic motion estimation on edge preserving Riesz wavelets for robust video mosaicing
Ali, S., Daul, C., Galbrun, E., Guillemin, F. H., & Blondel, W. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.09.021 · Cited by 18
Efficient Segmentation-Based PatchMatch for Large Displacement Optical Flow Estimation
Chen, J., Cai, Z., Lai, J., & Xie, X. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2885246 · Cited by 18
Applying Deep Learning Models to Mouse Behavior Recognition
Nguyen, N. G., Phan, D., Lumbanraja, F. R., Faisal, M. R., Abapihi, B., Purnama, B., Delimayanti, M. K., Mahmudah, K. R., Kubo, M., & Satou, K. (2019) · Journal of Biomedical Science and Engineering · doi:10.4236/jbise.2019.122012 · Cited by 18
“To generate optical-flow data from RGB data, we used the implementation of the TV-L1 algorithm from the research of [11] in OpenCV library.”
MethodA behaviorally inspired fusion approach for computational audiovisual saliency modeling
Tsiami, A., Koutras, P., Katsamanis, A., Vatakis, A., & Maragos, P. A. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.05.001 · Cited by 18
“For temporal visual saliency, we extracted warped optical flow maps according to [117], which is based on the TVL1 optical flow algorithm [118].”
MethodImproved Optical Flow for Gesture-based Human-robot Interaction
Chang, J.-Y., Tejero-de-Pablos, A., & Harada, T. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793825 · Cited by 19
“, non-deep learning-based) optical flow estimation [15].”
MethodDeep learning for software-based turbulence mitigation in long-range imaging
Nieuwenhuizen, R. P. J., & Klamer Schutte, B. (2019) · Artificial Intelligence and Machine Learning in Defense Applications · doi:10.1117/12.2532603 · Cited by 18
Learning Spatio-Temporal Representations With Temporal Squeeze Pooling
Huang, G., & Borş, A. G. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054200 · Cited by 19
“For the OF stream we use the TV-L1 optical flow algorithm [14] and its output is stored as JPEG images, where the colour encodes the optical flow vectors.”
MethodHu, H., Zhou, W., Li, X., Yan, N., & Li, H. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3422360 · Cited by 19
“The optical flow calculates pixel-wise displacements of two consecutive frames [56], which provides fine-grained motion representation directly.”
BackgroundMethodInfluentialFactorNet: Holistic Actor, Object, and Scene Factorization for Action Recognition in Videos
Nigam, N., Dutta, T., & Gupta, H. P. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3070688 · Cited by 18
Motion-Augmented Self-Training for Video Recognition at Smaller Scale
Gavrilyuk, K., Jain, M., Karmanov, I., & Snoek, C. G. M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01026 · Cited by 18
“For our motion representation we utilize TV-L1 [62], which is widely used for video action recognition.”
Egocentric Action Recognition by Automatic Relation Modeling
Li, H., Zheng, W., Zhang, J., Hu, H., Lu, J., & Lai, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3148790 · Cited by 18
“For each frame, five stacked maps of optical flows are pre-computed using TVL1 method [107].”
MethodA polar representation of motion and implications for optical flow
Adato, Y., Zickler, T. E., & Ben‐Shahar, O. (2011) · doi:10.1109/cvpr.2011.5995419 · Cited by 18
“[7,24,26]).”
An overview of intelligent surveillance systems development
Adrian, A. I., Ismet, P., & Papazian, P. (2018) · International Symposium on Electronics and Telecommunications (ISETC) · doi:10.1109/isetc.2018.8584003 · Cited by 18
Deep Keyframe Detection in Human Action VideosPreprint
Yan, X., Gilani, S. Z., Qin, H., Feng, M., Zhang, L., & Mian, A. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.10021 · Cited by 24
“For the extraction of the optical flow images, we use the TVL1 optical flow algorithm [39] from the OpenCV toolbox.”
MethodRGB Stream Is Enough for Temporal Action DetectionPreprint
Wang, C., Cai, H., Zou, Y., & Xiong, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04362 · Cited by 18
“For example, using Dual TV-L(1) [56] to extract optical flow from a pair of 96× 96 frames will cost 650 ms on Intel(R) Xeon(R) CPU E5-2630 v4@2.”
MethodChierchia, G., Pustelnik, N., Pesquet, J.-C., & Pesquet‐Popescu, B. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637873 · Cited by 17
“A first approach consists of computing TV channel-by-channel and then summing up the resulting smoothness measures [12, 13, 14, 15, 16].”
MethodTwo-Stream Gated Fusion ConvNets for Action Recognition
Zhu, J., Zou, W., & Zhu, Z. D. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545639 · Cited by 17
“Optical flows are extracted by the TVL1 optical flow algorithm [24].”
MethodExploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance
Chen, B.-J., & Medioni, G. G. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.93 · Cited by 17
Optical Flow Estimation Based on the Frequency-Domain Regularization
Chen, J., Lai, J., Cai, Z., Xie, X., & Pan, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2974490 · Cited by 17
“Zach et al. [11] first proposed an isotropic TV-L 1 regularizer to preserve motion discontinuities.”
BackgroundA circulant-matrix-based hybrid optical flow method for PIV measurement with large displacement
Ouyang, Z., Yang, H. S., Huang, Y., Zhang, Q., & Yin, Z. (2021) · Experiments in Fluids · doi:10.1007/s00348-021-03317-1 · Cited by 17
A Spatio-Temporal Motion Network for Action Recognition Based on Spatial Attention
Yang, Q. Z., Lu, T., & Zhou, H. (2022) · Entropy · doi:10.3390/e24030368 · Cited by 17
“[6,11] followed the architecture of two-stream network and investigated the fusion strategy of two-stream.”
BackgroundMethodChen, Z., Liu, H., Zhang, L., & Liao, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3174344 · Cited by 17
“TV-L1 algorithm [59] is applied to generate the optical flow frames from the RGB data.”
MethodTemporal Video Filtering and Exposure Control for Perceptual Motion Blur
Stengel, M., Bauszat, P., Eisemann, M., Eisemann, E., & Magnor, M. A. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2377753 · Cited by 17
“We then assume pðx; tÞ is defined by the optical flowFi!iþ1ðxÞ [32], [36] for any two frames i and iþ 1 in IUHFR, which proved successful in related work as well [34], [37].”
BackgroundTV-L1-Based 3D Medical Image Registration with the Census Cost Function
Hermann, S., & Werner, R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-642-53842-1_13 · Cited by 17
Activity Recognition Based on a Magnitude-Orientation Stream Network
Caetano, C., de Melo, V. H. C., dos Santos, J. A., & Schwartz, W. R. (2017) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2017.13 · Cited by 17
“w Extraction: As mentioned on Section III, the magnitude/orientation images are computed from the optical flow information. To that end, we extract the optical flow information using the TVL1 algorithm [39], implemented in OpenCV with CUDA. For the sake of comparison, our baseline [23] used the same optical flow algorith…”
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
