A Duality Based Approach for Realtime TV-L 1 Optical Flow
Integrity signals
Registry
Cites
Statistics
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?
The temporal network is designed to capture different visual aspects of videos compared to the spatial network, indicating that feature distributions are more diverse between optical flow and RGB.
“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]
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 17,089 · see citing works
Horn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312 · see citing works
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 · see citing works
chambolle (2004) · doi:10.1023/b:jmiv.0000011321.19549.88 · Cited by 3,227 · see citing works
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 · see citing works
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 · see citing works
Thormaehlen, T., Broszio, H., & Weißenfeld, A. (2004) · Lecture notes in computer science · doi:10.1007/b97865 · Cited by 901 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
Nagel, H.-H., & Enkelmann, W. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767833 · Cited by 786 · see citing works
Structure-Texture Image Decomposition—Modeling, Algorithms, and Parameter Selection
Aujol, J., Gilboa, G., Chan, T. F.-C., & Osher, S. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-4331-z · Cited by 630 · see citing works
A framework for the robust estimation of optical flow
Black, M. J., & Anandan, P. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1993.378214 · Cited by 456 · see citing works
Highly Accurate Optic Flow Computation with Theoretically Justified Warping
Papenberg, N., Bruhn, A., Brox, T., Didas, S., & Weickert, J. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-005-3960-y · Cited by 409 · see citing works
Journal of Mathematical Imaging and Vision
(2013) · Journal of Mathematical Imaging and Vision · doi:10.1007/10851.1573-7683 · Cited by 209 · see citing works
Computing Optical Flow via Variational Techniques
Aubert, G., Rachid Deriche, B., & Kornprobst, P. (1999) · SIAM Journal on Applied Mathematics · doi:10.1137/s0036139998340170 · Cited by 208 · see citing works
Bruhn, A., Weickert, J., Kohlberger, T., & Schnörr, C. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-6616-7 · Cited by 155 · see citing works
Variational optical flow computation in real time
Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., & Schnörr, C. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.846018 · Cited by 152 · see citing works
Hierarchical Estimation and Segmentation of Dense Motion Fields
Mémin, É., & Pérez, P. (2002) · International Journal of Computer Vision · doi:10.1023/a:1013539930159 · Cited by 144 · see citing works
Diffusion and regularization of vector- and matrix-valued imagesPreprint
Weickert, J., & Brox, T. (2002) · doi:10.22028/d291-26208 · Cited by 128 · see citing works
Diffusion and regularization of vector- and matrix-valued images
Weickert, J., & Brox, T. (2002) · Contemporary mathematics - American Mathematical Society · doi:10.1090/conm/313/05378 · Cited by 109 · see citing works
Inverse Problems, Image Analysis, and Medical Imaging
Nashed, M. Z., & Scherzer, O. (2002) · Contemporary mathematics - American Mathematical Society · doi:10.1090/conm/313 · Cited by 98 · see citing works
Real-Time Quantized Optical Flow
Camus, T. A. (1997) · Real-Time Imaging · doi:10.1006/rtim.1996.0048 · Cited by 73 · see citing works
A nonlinear primal-dual method for total variation-based image restoration
Chan, T. F.-C., Golub, G. H., & Mulet, P. (1996) · Lecture notes in control and information sciences · doi:10.1007/3-540-76076-8_137 · Cited by 71 · see citing works
Real-time motion estimation and visualization on graphics cards
Strzodka, R., & Garbe, C. S. (2005) · IEEE Visualization · doi:10.1109/visual.2004.88 · Cited by 68 · see citing works
A Scale-Space Approach to Nonlocal Optical Flow Calculations
Álvarez, L., Sánchez, J., & Weickert, J. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48236-9_21 · Cited by 64 · see citing works
A Nonlinear primal dual method for TV-based image restoration
Chan, T. F.-C., Golub, G. H., & Mulet, P. (1996) · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · Cited by 26 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · see citing works
“For optical flow we evaluate state-of-the-art variational [24, 6, 48, 44, 7, 9, 45] and local [5, 47] methods.”
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570 · see citing works
A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging
Chambolle, A., & Pock, T. (2011) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-010-0251-1 · Cited by 4,336 · see citing works
“See again [36] for more details.”
Self-citationTemporal Segment Networks: Towards Good Practices for Deep Action Recognition
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Gool, L. V. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_2 · Cited by 4,164 · see citing works
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2018) · 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.2018.00675 · Cited by 3,672 · see citing works
(2020) · doi:10.1007/978-3-030-58536-5_24 · Cited by 2,824 · see citing works
TSM: Temporal Shift Module for Efficient Video Understanding
Lin, J., Gan, C., & Han, S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00718 · Cited by 2,152 · see citing works
“To extract the optical flow information between frames, we followed [48] to use the TVL1 optical flow algorithm [55] implemented in OpenCV with CUDA.”
BackgroundMethodBeyond short snippets: Deep networks for video classification
Ng, J. Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., & Toderici, G. D. (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.2015.7299101 · Cited by 2,121 · see citing works
“Optical flow is computed from two adjacent frames sampled at 15fps using the approach of [26].”
MethodTian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997 · see citing works
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., B.G., V. K., Carneiro, G., & Reid, I. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_45 · Cited by 1,632 · see citing works
“…regularizer is known to over-smooth the estimated motion, however a vast literature of more sophisticated edge preserving regularizers with robust penalty functions like [2,22] for which gradients can be computed are at our disposal and can be easily used with our setup to get sharper depth maps.”
BackgroundRethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01267-0_19 · Cited by 1,494 · see citing works
“For these experiments, we follow the standard setup as described in [10] and extract optical flow features with the TV-L1 approach [40].”
MethodSecrets of optical flow estimation and their principles
Sun, D., Roth, S., & Black, M. J. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539939 · Cited by 1,656 · see citing works
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
Brox, T., & Malik, J. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.143 · Cited by 1,295 · see citing works
Action recognition with trajectory-pooled deep-convolutional descriptors
Wang, L., Qiao, Y., & Tang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299059 · Cited by 1,194 · see citing works
“We choose the TVL1 optical flow algorithm [40] and use the OpenCV implementation, due to its balance between accuracy and efficiency.”
MethodScaling Egocentric Vision: The "Equation missing" Dataset
Damen, D., Doughty, H., Farinella, G. M., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_44 · Cited by 875 · see citing works
Spatiotemporal Multiplier Networks for Video Action Recognition
Feichtenhofer, C., Pinz, A. J., & Wildes, R. P. (2017) · 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.2017.787 · Cited by 692 · see citing works
“Optical flow [42] is precomputed prior to training and stored as JPEG images (with displacement vectors > 20 pixels clipped).”
MethodQuicksilver: Fast predictive image registration – A deep learning approach
Yang, X., Kwitt, R., Styner, M., & Niethammer, M. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.008 · Cited by 630 · see citing works
“Optical flow approaches, such as the classical Horn and Schunck optical flow [41], the more recent total variation approaches [42], or methods based on linear elasticity theory [1] are examples for displacementbased registration formulations.”
MethodComputer Vision for Autonomous Vehicles
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000079 · Cited by 664 · see citing works
Sun, D., Roth, S., & Black, M. J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0644-x · Cited by 698 · see citing works
“Note in practice the weight λC on the coupling term is usually small or is steadily increased from small values (Wedel et al. 2008b; Zach et al. 2007).”
BackgroundMethodInfluentialTEA: Temporal Excitation and Aggregation for Action Recognition
Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., & Wang, L. (2020) · 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/cvpr42600.2020.00099 · Cited by 592 · see citing works
Moments in Time Dataset: One Million Videos for Event Understanding
Monfort, M., Vondrick, C., Oliva, A., Andonian, A., Zhou, B., Ramakrishnan, K., Bargal, S. A., Yan, T., Brown, L., Fan, Q., et al. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2901464 · Cited by 537 · see citing works
“In the interest of performance, we pre-compute optical flow on consecutive frames using an off-the-shelf implementation of TVL1 optical flow algorithm [46] from the OpenCV toolbox [22].”
MethodNot only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision
Wu, P., Liu, J., Shi, Y., Sun, Y., Shao, F., Wu, Z., & Yang, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58577-8_20 · Cited by 521 · see citing works
STM: SpatioTemporal and Motion Encoding for Action Recognition
Jiang, B., Wang, M., Gan, W., Wu, W., & Yan, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00209 · Cited by 496 · see citing works
“However, calculating optical flow with TV-L1 method [38] is expensive in both time and space.”
MethodMotion Detail Preserving Optical Flow Estimation
Li, X., Jia, J., & Matsushita, Y. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.236 · Cited by 499 · see citing works
VideoLSTM convolves, attends and flows for action recognition
Li, Z., Gavrilyuk, K., Gavves, E., Jain, M., & Snoek, C. G. M. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2017.10.011 · Cited by 485 · see citing works
New features and insights for pedestrian detection
Walk, S., Majer, N., Schindler, K., & Schiele, B. (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.2010.5540102 · Cited by 468 · see citing works
“2In our previous paper [27] we used the optic flow software of [29], which is a precursor of [26].”
MethodOptical flow modeling and computation: A survey
Fortun, D., Bouthemy, P., & Kervrann, C. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.02.008 · Cited by 457 · see citing works
“interesting and useful properties [46, 63, 279, 284].”
BackgroundMethodInfluentialDense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
Sundaram, N., Brox, T., & Keutzer, K. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_32 · Cited by 428 · see citing works
“Very efficient GPU implementations of other variational optical flow models have been proposed in [3,13,14].”
BackgroundMethodAn Improved Algorithm for TV-L 1 Optical Flow
Wedel, A., Pock, T., Zach, C., Bischof, H., & Cremers, D. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03061-1_2 · Cited by 423 · see citing works
“In the following we show how this approach was adopted in [ 31 ] to the optical flow case, yielding a different approach to solve Eq. 3.”
MethodInfluentialSelf-citationPérez, J. S., Meinhardt-Llopis, E., & Facciolo, G. (2013) · Image Processing On Line · doi:10.5201/ipol.2013.26 · Cited by 417 · see citing works
“1 Introduction The method described in Zach, Pock and Bischof’s article [6] is based on the brightness constancy assumption.”
MethodModern regularization methods for inverse problems
Benning, M., & Burger, M. (2018) · Acta Numerica · doi:10.1017/s0962492918000016 · Cited by 408 · see citing works
“[212, 370]) or joint reconstruction problems (cf.”
Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01531-2 · Cited by 400 · see citing works
Less is more: Micro-expression recognition from video using apex frame
Liong, S., See, J., Wong, K., & Phan, R. C. ‐. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.11.006 · Cited by 399 · see citing works
“We employed TV-L1 [34] for optical flow approximation due to its two major advantages: better noise robustness and the ability to preserve flow discontinuities.”
Kinect range sensing: Structured-light versus Time-of-Flight Kinect
Sarbolandi, H., Lefloch, D., & Kolb, A. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.05.006 · Cited by 389 · see citing works
“Lindner and Kolb [34] apply a fast optical flow algorithm [54] three times in order to align the four correlation images A0, A1, A2, A3 to the first correlation image A0.”
MethodLearning to Estimate Hidden Motions with Global Motion Aggregation
Jiang, S., Campbell, D., Lu, Y., Li, H., & Hartley, R. I. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00963 · Cited by 380 · see citing works
“[46] added total variation regularisation and proposed an efficient numerical scheme to optimise the energy functional.”
MethodPROST: Parallel robust online simple tracking
Santner, J., Leistner, C., Saffari, A., Pock, T., & Bischof, H. (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.2010.5540145 · Cited by 380 · see citing works
“[24] achieved realtime performance by minimizing this energy on the GPU.”
BackgroundSelf-citationFast Optical Flow Using Dense Inverse Search
Kroeger, T., Timofte, R., Dai, D., & Gool, L. V. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46493-0_29 · Cited by 375 · see citing works
FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding
Shao, D., Zhao, Y., Dai, B., & Lin, D. (2020) · 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/cvpr42600.2020.00269 · Cited by 369 · see citing works
Live dense reconstruction with a single moving camera
Newcombe, R. A., & 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.2010.5539794 · Cited by 367 · see citing works
“Details of solutions to minimising (11) are given in [9], [ 19 ].”
BackgroundMulti-cue onboard pedestrian detection
Wojek, C., Walk, S., & Schiele, B. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206638 · Cited by 350 · see citing works
“de Objectives Detect pedestrians from a moving platform • Exploit motion information • Leverage complementarity of features • Evaluate different classifiers • New datasets with image pairs Features • HOG [1] 8× 8 pixel cells, 2× 2 blocks 9-bin histograms, unsigned gradients • Haar wavelets [2] 32 and 16 pixel masks ho…”
BackgroundCompressed Video Action Recognition
Wu, C.-Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A. J., & Krähenbühl, P. (2018) · 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.2018.00631 · Cited by 358 · see citing works
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
Sun, S., Kuang, Z., Sheng, L., Ouyang, W., & Zhang, W. (2018) · 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.2018.00151 · Cited by 347 · see citing works
Towards Good Practices for Very Deep Two-Stream ConvNetsPreprint
Wang, L., Xiong, Y., Wang, Z., & Qiao, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.02159 · Cited by 381 · see citing works
PoTion: Pose MoTion Representation for Action Recognition
Choutas, V., Weinzaepfel, P., Revaud, J., & Schmid, C. (2018) · 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.2018.00734 · Cited by 342 · see citing works
“The second one is based on the motion, taking as input the optical flow that is computed with off-the-shelf methods [2, 46], converted into images and stacked over several frames.”
MethodLearning and Using the Arrow of Time
Wei, D., Lim, J. J., Zisserman, A., & Freeman, W. T. (2018) · 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.2018.00840 · Cited by 318 · see citing works
OFF-ApexNet on micro-expression recognition system
Gan, Y. S., Liong, S., Yau, W., Huang, Y., & Tan, L. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.02.005 · Cited by 321 · see citing works
Hierarchical Surface Prediction for 3D Object Reconstruction
Häne, C., Tulsiani, S., & Malik, J. (2017) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00054 · Cited by 308 · see citing works
Simultaneous Optical Flow and Intensity Estimation from an Event Camera
Bardow, P. A., Davison, A. J., & Leutenegger, S. (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.2016.102 · Cited by 306 · see citing works
“Our algorithm is formulated as sliding window variational optimisation, and has much in common with well known variational methods for estimating two-view optical flow from standard video [11, 24].”
BackgroundMethodSkeleton Aware Multi-modal Sign Language Recognition
Jiang, S., Sun, B., Wang, L., Bai, Y., Li, K., & Fu, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00380 · Cited by 309 · see citing works
“We follow the same process in [63] to obtain optical flow features using TVL1 algorithm [67] implemented with OpenCV and CUDA.”
MethodPhase-based frame interpolation for video
Schaub-Meyer, S., Wang, O., Zimmer, H., Grosse, M., & Sorkine‐Hornung, A. (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.2015.7298747 · Cited by 298 · see citing works
“There has been some parallel flow implementations on GPUs which allow to significantly reduce running times [28, 30].”
BackgroundConvolutional Two-Stream Network Fusion for Video Action RecognitionPreprint
Feichtenhofer, C., Pinz, A. J., & Zisserman, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.06573 · Cited by 384 · see citing works
“For the temporal net, we use optical flow [1, 37] stacking with L = 10 frames [22].”
MethodSelf-supervised Co-training for Video Representation Learning
Han, T., Xie, W., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.09709 · Cited by 292 · see citing works
“The optical flow is computed with the un-supervised TV-L1 algorithm [67], and the same pre-processing procedure is used as in [11].”
MARS: Motion-Augmented RGB Stream for Action Recognition
Crasto, N., Weinzaepfel, P., Alahari, K., & Schmid, C. (2019) · 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.2019.00807 · Cited by 293 · see citing works
“Irrespective of their differences, all the methods discussed above use hand-crafted optical flow features such as [1, 45] for the motion stream, creating a bottleneck for fast and online inference.”
BackgroundMethodInfluentialHidden Two-Stream Convolutional Networks for Action Recognition
Zhu, Y., Lan, Z., Newsam, S. D., & Hauptmann, A. G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_23 · Cited by 300 · see citing works
Going Deeper into First-Person Activity Recognition
Ma, M., Fan, H., & Kitani, K. (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.2016.209 · Cited by 281 · see citing works
“In our experiments, we crop and resize input images to 256 × 256 and calculate optical flow using OpenCV GPU implementation of [37].”
MethodLarge displacement optical flow
Brox, T., Bregler, C., & Malik, J. (2009) · 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.2009.5206697 · Cited by 281 · see citing works
“Most of the time is spent for the deformation of the patches and the variational flow, which is both potentially available in real-time using the GPU [19].”
MethodClustering Driven Deep Autoencoder for Video Anomaly Detection
Chang, Y., Tu, Z., Xie, W. C., & Yuan, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58555-6_20 · Cited by 280 · see citing works
“One traditional optical flow algorithm TV-L1 [41] and one deep learning based optical flow method FlowNet2-SD [12] are selected for comparison.”
MethodInfluentialTwo-Stream 3-D convNet Fusion for Action Recognition in Videos With Arbitrary Size and Length
Wang, X., Gao, L., Wang, P., Sun, X., & Liu, X. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2749159 · Cited by 263 · see citing works
ClothFlow: A Flow-Based Model for Clothed Person Generation
Han, X., Huang, W., Hu, X., & Scott, M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01057 · Cited by 270 · see citing works
COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis
Tang, Y., Ding, D., Rao, Y., Zheng, Y., Zhang, D., Zhao, L., Lu, J., & Zhou, J. (2019) · 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.2019.00130 · Cited by 270 · see citing works
“Here SSN−Flow adopted the optical flows calculated by [48], and SSN−Fusion combined the predicted scores of SSN−RGB and SSN−Flow.”
MethodCompleteness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
Liu, D., Jiang, T., & Wang, Y. (2019) · 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.2019.00139 · Cited by 248 · see citing works
“Concretely, for each video in the training set, we compute its optical flow using the TV-L1 algorithm [50] and average the intensity in every frame.”
MethodAction Recognition with Dynamic Image Networks
Bilen, H., Fernando, B., Gavves, E., & Vedaldi, A. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2769085 · Cited by 262 · see citing works
Beyond Short Snippets: Deep Networks for Video ClassificationPreprint
Ng, J. Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., & Toderici, G. D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.08909 · Cited by 276 · see citing works
“Optical flow is computed from two adjacent frames sampled at 15fps using the approach of [26].”
MethodDynamic 3D avatar creation from hand-held video input
Ichim, A.-E., Bouaziz, S., & Pauly, M. V. (2015) · ACM Transactions on Graphics · doi:10.1145/2766974 · Cited by 249 · see citing works
A Key Volume Mining Deep Framework for Action Recognition
Zhu, W., Hu, J., Sun, G., Cao, X., & Qiao, Y. (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.2016.219 · Cited by 245 · see citing works
“For the motion stream, We use off-the-shell tvl1 method [35] implemented in OpenCV to compute optical flows.”
MethodTS-LSTM and temporal-inception: Exploiting spatiotemporal dynamics for activity recognition
Ma, C., Chen, M.-H., Kira, Z., & AlRegib, G. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.09.003 · Cited by 247 · see citing works
Enriched Long-Term Recurrent Convolutional Network for Facial Micro-Expression Recognition
Khor, H.-Q., See, J., Phan, R. C. W., & Lin, W. (2018) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2018.00105 · Cited by 244 · see citing works
What's going on? Discovering spatio-temporal dependencies in dynamic scenes
Kuettel, D., Breitenstein, M. D., Gool, L. V., & Ferrari, V. (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.2010.5539869 · Cited by 241 · see citing works
“Given an input video, we extract optical flow in each pair of consecutive frames using [14] (Figure 2(a)).”
Zolfaghari, M., Oliveira, G. L., Sedaghat, N., & Brox, T. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.316 · Cited by 242 · see citing works
“[52], which is a reliable variational method that runs sufficiently fast.”
MethodVideo anomaly detection with spatio-temporal dissociation
Chang, Y., Tu, Z., Xie, W. C., Luo, B., Zhang, S., Sui, H., & Yuan, J. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108213 · Cited by 239 · see citing works
Deep Temporal Linear Encoding Networks
Diba, A., Sharma, V., & Gool, L. V. (2017) · 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.2017.168 · Cited by 236 · see citing works
“For the extraction of the optical flow frames, we use the TVL1 optical flow algorithm [42] from the OpenCV toolbox with CUDA implementation.”
MethodAttention Clusters: Purely Attention Based Local Feature Integration for Video Classification
Long, X., Gan, C., de Melo, G., Wu, J., Liu, X., & Wen, S. (2018) · 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.2018.00817 · Cited by 233 · see citing works
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · doi:10.1561/9781680836899 · Cited by 243 · see citing works
End-to-End Learning of Motion Representation for Video Understanding
Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., & Huang, J. (2018) · 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.2018.00630 · Cited by 230 · see citing works
Video-based surgical skill assessment using 3D convolutional neural networks
Funke, I., Mees, S. T., Weitz, J., & Speidel, S. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-01995-1 · Cited by 227 · see citing works
“3 The optical flow fields are calculated using the TV-L1 algorithm [32] implemented in OpenCV [4].”
MethodThe EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
Damen, D., Doughty, H., Farinella, G. M., Fidler, S., Furnari, A., Kazakos, E., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2991965 · Cited by 228 · see citing works
“Evaluation Metrics: We report two sets of metrics: aggregate and per-class, which are equivalent to the class-agnostic and classaware metrics in [12].”
BackgroundResultWang, X., Farhadi, A., & Gupta, A. (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.2016.291 · Cited by 228 · see citing works
“To compute the optical flow, we apply the TVL1 optical flow algorithm [59] and discretize the values to the range of [0, 255].”
MethodSequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN
Shi, Y., Tian, Y., Wang, Y., & Huang, T. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2666540 · Cited by 221 · see citing works
“Finally, we report the experimental results and compare sDTD with the state-of-theart methods.”
ResultMotion estimation with non-local total variation regularization
Werlberger, M., Pock, T., & Bischof, H. (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.2010.5539945 · Cited by 218 · see citing works
“After linearization, energy (2) yields a convex optimization problem which can be solved using for example the primal-dual quadratic splitting technique of [ 29 ].”
BackgroundMethodInfluentialSelf-citationDense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
Garg, R., Roussos, A., & Agapito, L. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.168 · Cited by 210 · see citing works
“Total Variation based regularization smooths while preserving discontinuities and has been successfully applied to various related optic flow estimation [15, 34], and 3D reconstruction methods [19].”
MethodRevisiting Anchor Mechanisms for Temporal Action Localization
Yang, L., Peng, H., Zhang, D., Fu, J., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3016486 · Cited by 216 · see citing works
“TV-L1 [38] algorithm is used to estimate the optical flow.”
MethodZimmer, H., Bruhn, A., & Weickert, J. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0422-6 · Cited by 215 · see citing works
Memory-Augmented Dense Predictive Coding for Video Representation Learning
Han, T., Xie, W., & Zisserman, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_19 · Cited by 211 · see citing works
Learning Spatio-Temporal Representation With Local and Global Diffusion
Qiu, Z., Yao, T., Ngo, C., Tian, X., & Mei, T. (2019) · 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.2019.01233 · Cited by 205 · see citing works
“The optical flow image in this paper consists of two-direction optical flow extracted by TV-L1 algorithm [50].”
MethodReal-Time Dense Geometry from a Handheld Camera
Stühmer, J., Gumhold, S., & Cremers, D. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15986-2_2 · Cited by 205 · see citing works
“The key idea is to adopt recently developed high-accuracy optic flow algorithms [7] to the problem of depth map estimation from multiple images.”
MethodLattice Long Short-Term Memory for Human Action Recognition
Sun, L., Jia, K., Chen, K., Yeung, D., Shi, B. E., & Savarese, S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.236 · Cited by 206 · see citing works
“[15] incorporate motion information by training another neural network on optical flow [37].”
BackgroundMethodRethinking Spatiotemporal Feature Learning For Video Understanding.
Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. P. (2017) · Cited by 205 · see citing works
Gate-Shift Networks for Video Action Recognition
Sudhakaran, S., Escalera, S., & Lanz, O. (2020) · 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/cvpr42600.2020.00118 · Cited by 197 · see citing works
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
Sun, D., Yang, X., Liu, M.-Y., & Kautz, J. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2894353 · Cited by 200 · see citing works
“Another paper, TVNet [73], subsumes a specific optical flow solver, the TV-L1 method [74], and is initialized by unfolding its optimization iterations as neural layers.”
MethodD3D: Distilled 3D Networks for Video Action Recognition
Stroud, J., Ross, D. A., Sun, C., Deng, J., & Sukthankar, R. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093274 · Cited by 194 · see citing works
“We use TV-L1 optical flow in place of ground truth optical flow during training [36].”
MethodA Deep One-Class Neural Network for Anomalous Event Detection in Complex Scenes
Wu, P., Liu, J., & Shen, F. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2933554 · Cited by 194 · see citing works
“Given the training video clips, we normalize the intensity of pixels in all frames in the range [0, 1], and then compute their optical flow field as motion information using the method in [25].”
MethodZhou, L., Mao, Q., Huang, X., Zhang, F., & Zhang, Z. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108275 · Cited by 190 · see citing works
Furnari, A., & Farinella, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00635 · Cited by 182 · see citing works
“Optical flows are extracted using the TVL1 algorithm [63].”
MethodRepresentation Flow for Action Recognition
Piergiovanni, A., & Ryoo, M. S. (2019) · 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.2019.01018 · Cited by 190 · see citing works
“The standard, variational methods for approximating optical flow (e.g., Brox [2] and TV-L1 [27] methods) take sequential images I1, I2 as input.”
MethodInfluentialEfficient sparse-to-dense optical flow estimation using a learned basis and layers
Wulff, J., & Black, M. 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.2015.7298607 · Cited by 186 · see citing works
“For each movie, we compute the optical flow using GPUFlow [52].”
BackgroundMethodInfluential3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Narayan, S., Cholakkal, H., Khan, F. S., & Shao, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00877 · Cited by 179 · see citing works
“In our framework, a TV-L1 optical flow [32] is used to generate the optical flow frames of the video.”
MethodStructure- and motion-adaptive regularization for high accuracy optic flow
Wedel, A., Cremers, D., Pock, T., & Bischof, H. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459375 · Cited by 178 · see citing works
Self-citationDual-stream Shallow Networks for Facial Micro-expression Recognition
Khor, H.-Q., See, J., Liong, S., Phan, R. C. ‐., & Lin, W. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8802965 · Cited by 177 · see citing works
Efficient Dense Scene Flow from Sparse or Dense Stereo Data
Wedel, A., Rabe, C., Vaudrey, T., Brox, T., Franke, U., & Cremers, D. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88682-2_56 · Cited by 176 · see citing works
“Real-time methods have been proposed in [2,18].”
Depth from focus with your mobile phone
Suwajanakorn, S., Hernández, C., & Seitz, S. M. (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.2015.7298972 · Cited by 170 · see citing works
“, [32] which reduces the optical flow runtime to 36 seconds.”
Background
- 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
