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
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
“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
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 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 4,232
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
(2020) · doi:10.1007/978-3-030-58536-5_24 · Cited by 2,824
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 2,209
“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 2,152
“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
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
“…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 1,553
“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
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
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
“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 911
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
“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
“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 699
Sun, D., Roth, S., & Black, M. J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0644-x · Cited by 698
“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 600
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
“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
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
“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
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 492
New features and insights for pedestrian detection
Walk, S., Majer, N., Konrad Schindler, B., & 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 475
“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
“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
“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
“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
“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 445
“[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
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 414
“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
“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
“[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
“[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
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
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
“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
“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 374
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 352
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 402
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
“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 329
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 330
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
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
“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
“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 303
“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
“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
“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 300
“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
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 287
“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
“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
“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
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 274
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 300
“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
“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 269
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 292
“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
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 246
“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
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
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 240
“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 248
“[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
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 238
“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
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 244
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
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 241
“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 267
“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 232
“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 225
“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
“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
“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
“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 219
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 217
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 209
“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
“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 208
“[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
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
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 208
“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
“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 197
“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 201
Furnari, A., & Farinella, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00635 · Cited by 182
“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
“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
“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 181
“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
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 181
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
“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
“, [32] which reduces the optical flow runtime to 36 seconds.”
Background
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
