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 601–700 of 1,002
Deep Optical Flow Supervised Learning With Prior Assumptions
Xiang, X., Zhai, M., Zhang, R., Qiao, Y., & Saddik, A. E. (2018) · IEEE Access · doi:10.1109/access.2018.2863233 · Cited by 17
“Based on the basic energy function, many improvements have been introduced in [2]–[4].”
BackgroundHierarchical Surface Prediction
Häne, C., Tulsiani, S., & Malik, J. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2896296 · Cited by 17
“By computing optical flow hierarchically on a spatial pyramid, e.g., [2], real-time computation of optical flow is feasible [51].”
BackgroundAn Efficient Spatial-Temporal Polyp Detection Framework for Colonoscopy Video
Zhang, P., Sun, X., Wang, D., Wang, X., Cao, Y., & Liu, B. (2019) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00-93 · Cited by 17
“’s method [30].”
Li, T., Wei, B., Cong, J., Hong, Y., & Li, S. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103659 · Cited by 17
LSM: Learning Subspace Minimization for Low-Level Vision
Tang, C., Yuan, L., & Tan, P. (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/cvpr42600.2020.00627 · Cited by 17
Creating Autonomous Vehicle Systems, Second Edition
Liu, S., Li, L., Tang, J., Wu, S., & Gaudiot, J. (2020) · Synthesis lectures on computer science · doi:10.2200/s01036ed1v01y202007csl012 · Cited by 19
Spatiotemporal Optimization for Short-Term Solar Forecasting Based on Satellite Imagery
Oh, M., Kim, C. K., Kim, B., Yun, C.-Y., Kang, Y.-H., & Kim, H. (2021) · Energies · doi:10.3390/en14082216 · Cited by 17
“The optimized parameters for the Dual TVL1 were taken from similar previous studies [44].”
MethodMulti-scale joint feature network for micro-expression recognition
Li, X., Wei, G., Wang, J., & Zhou, Y. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0217-9 · Cited by 16
Pikoulis, I., Filntisis, P. P., & Maragos, P. A. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9666957 · Cited by 16
“Optical flow extraction is carried out via the TVL1 algorithm [42].”
Evaluation of a New Coarse-to-Fine Strategy for Fast Semi-Global Stereo Matching
Hermann, S., & Klette, R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25367-6_35 · Cited by 17
“[18].”
A Superresolution Framework for High-Accuracy Multiview Reconstruction
Goldlüecke, B., & Cremers, D. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03798-6_35 · Cited by 17
Bagnato, L., Pascal Frossard, B., & Vandergheynst, P. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5414552 · Cited by 17
“In [1], Zach et al. provide a real time optical flow algorithm with striking performance.”
InfluentialEnergy and Execution Time Comparison of Optical Flow Algorithms on SIMD and GPU Architectures
Petreto, A., Hennequin, A. M., Kœhler, T., Romera, T., Fargeix, Y., Gaillard, B., Bouyer, M., Meunier, Q. L., & Lacassagne, L. (2018) · Conference on Design and Architectures for Signal and Image Processing · doi:10.1109/dasip.2018.8597004 · Cited by 19
“TV-L1, which is well described in [17] and [4], relies on the total variation method using the L(1) norm for the regularization terms (TV-L1).”
MethodCFA Video Denoising and Demosaicking Chain via Spatio-Temporal Patch-Based Filtering
Buades, A., & Duran, J. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2956691 · Cited by 17
“2: for each frame I Y k ∈ {I Y n }N n=1 do 3: Nk = temporal neighborhood (M adjacent frames) 4: Compute optical flow between I Y k to all I Y j ∈ Nk using TV-L1 algorithm [58].”
MethodInfluentialZhou, L., Mao, Q., & Dong, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13148 · Cited by 17
“2) Implementation details: In the pre-processing step, we utilized the algorithm of libfacedetection [46] to crop out the facial area in each sample and then extracted TV-L1 optical flow [47] images from the onset and apex frames.”
Automatic surveillance in transportation hubs: No longer just about catching the bad guy
Denman, S., Kleinschmidt, T., Ryan, D., Barnes, P., Sridharan, S., & Fookes, C. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.08.001 · Cited by 16
Martin, P.-E., Benois‐Pineau, J., Péteri, R., & Morlier, J. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803780 · Cited by 16
“In this work we consider the following OF methods : Farneback [20], Beyond Pixel (BP) [21] used in [16], DIS [22], TVL1 [23] and DeepFlow [24].”
MethodWeakly Supervised Regional and Temporal Learning for Facial Action Unit Recognition
Yan, J.-W., Wang, J., Li, Q., Wang, C., & Pu, S.-L. (2022) · IEEE transactions on multimedia · doi:10.1109/tmm.2022.3160061 · Cited by 19
“For a video sequence, we first extract the TV-L1 optical flow [37] between two facial frames.”
MethodA Review of Micro-expression Recognition based on Deep Learning
Zhang, H., & Zhang, H. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892307 · Cited by 16
“Lucas-Kanade OF [24] and TV-L1 [25] are two widely used methods for optical flow extraction.”
MethodDetecting Deepfake Videos using Spatiotemporal Trident Network
Lin, K., Han, W., Li, S., Gu, Z., Zhao, H., & Mei, Y. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3623639 · Cited by 19
“In this paper, TV-L1 algorithm [48] is used to calculate optical flow.”
Fast dense stereo correspondences by binary locality sensitive hashing
Heise, P., Jensen, B., Klose, S., & Knoll, A. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7138987 · Cited by 16
“[5] and belief propagation [8] are well known methods belonging to this category as well as variational formulations mainly used for the related problem of optical flow [24].”
MethodA real-time multi-cue framework for determining optical flow confidence
Gehrig, S. K., & Scharwächter, T. (2011) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2011.6130491 · Cited by 16
Video matting via opacity propagation
Tang, Z., Miao, Z., Wan, Y., & Zhang, D. (2011) · The Visual Computer · doi:10.1007/s00371-011-0598-3 · Cited by 16
“where (v̄x, v̄y) is the mean motion vector of a 2D window that is estimated by the backward optical flow [31].”
InfluentialSide information creation for efficient Wyner–Ziv video coding: Classifying and reviewing
Brites, C., Ascenso, J., & Pereira, F. M. B. (2013) · Signal Processing Image Communication · doi:10.1016/j.image.2013.05.002 · Cited by 16
Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees
Aodha, O. M., & Brostow, G. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.31 · Cited by 16
“The optical flow algorithms chosen as specialists were TV [29], FL [27], CN [21] and LD [7].”
BackgroundMethodSpatio-temporal clustering of probabilistic region trajectories
Galasso, F., Iwasaki, M., Nobori, K., & Cipolla, R. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126438 · Cited by 16
“In particular, we use the optical flow algorithm of [23] and smooth its output by bilateral filtering to preserve the boundary sharpness [15].”
MethodIs a Memoryless Motion Detection Truly Relevant for Background Generation with LaBGen?
Laugraud, B., & Droogenbroeck, M. V. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70353-4_38 · Cited by 16
“The parameter values being considered for LaBGen-OF are the same for P, N and S; τ = 0.02, 0.03, . . . , 0.1; and A with 6 optical flow algorithms: a fast sparseto-dense pyramidal Lucas-Kanade [2], Farnebäck [5], Dual TV-L1 [21], SimpleFlow [18], DeepFlow [20], and DISFlow [8].”
MethodInfluentialAppearance-and-Dynamic Learning With Bifurcated Convolution Neural Network for Action Recognition
Zhang, J., Hu, H., & Liu, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3006223 · Cited by 16
“The optical flow data is extracted by the TVL1 algorithm [37] implemented with OpenCV.”
MethodNie, K., Shi, X., Cheng, S., Gao, Z., & Xu, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3034148 · Cited by 16
Human activity prediction using saliency-aware motion enhancement and weighted LSTM network
Weng, Z., Li, W., & Jin, Z. (2021) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-020-00544-0 · Cited by 16
“In the data preprocessing stage, the TVL1 optical flow algorithm [29] was adopted.”
MethodSparse Deep LSTMs with Convolutional Attention for Human Action Recognition
Aghaei, A., Nazari, A., & Moghaddam, M. E. (2021) · SN Computer Science · doi:10.1007/s42979-021-00576-x · Cited by 15
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
Toering, M., Gatopoulos, I., Stol, M., & Hu, V. T. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00092 · Cited by 16
Enhanced Attention Tracking With Multi-Branch Network for Egocentric Activity Recognition
Liu, T., Lam, K., Zhao, R., & Kong, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3104651 · Cited by 16
Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching
Hermann, S., & Klette, R. (2012) · ACCV Workshops · doi:10.1007/978-3-642-37484-5_45 · Cited by 20
“[22], and Werlberger et al.”
Random coded sampling for high-speed HDR video
Portz, T., Zhang, L., & Jiang, H. (2013) · IEEE International Conference on Computational Photography (ICCP) · doi:10.1109/iccphot.2013.6528308 · Cited by 16
“Optical flow is computed over the entire video using a GPU implementation of the TV-L1 optical flow algorithm [19].”
MethodNovelty-based Spatiotemporal Saliency Detection for Prediction of Gaze in Egocentric Video
Polatsek, P., Benešová, W., Paletta, L., & Perko, R. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2523339 · Cited by 16
A multi-aperture optical flow estimation method for an artificial compound eye
Wu, S., Zhang, G., Neri, F., Zhu, M. Q., Jiang, T., & Kuhnert, K.-D. (2018) · Integrated Computer-Aided Engineering · doi:10.3233/ica-180593 · Cited by 15
Feature flow: In-network feature flow estimation for video object detection
Jin, R., Lin, G., Wen, C., Wang, J., & Liu, F. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108323 · Cited by 15
Spatio-Temporal Collaborative Module for Efficient Action Recognition
Hao, Y., Wang, S., Tan, Y., He, X., Liu, Z., & Wang, M. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3221292 · Cited by 15
“Apart from the RGB features, TVNet [32] proposes to learn optical-flow-like features from videos by unfolding the iterations of the TV-L1 [33] method to customized neural layers.”
MethodHear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization
Fedorishin, D., Mohan, D. D., Jawade, B., Setlur, S., & Govindaraju, V. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00231 · Cited by 16
Identity-invariant representation and transformer-style relation for micro-expression recognition
Shao, Z., Li, F., Zhou, Y. Z., Chen, H., Zhu, H., & Yao, R. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04533-4 · Cited by 16
Li, Z., Tian, L., Mok, T. C. W., Bai, X., Wang, P., Ge, J. S., Zhou, J., Lü, L., Ye, X., Yan, K., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43999-5_53 · Cited by 15
Rethinking RAFT for Efficient Optical Flow
Eslami, N., Arefi, F., Mansourian, A. M., & Shohreh Kasaei, B. (2024) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/mvip62238.2024.10491183 · Cited by 15
“In summary, the main contributions of this work are as follows: • Proposing the Amorphous Lookup Operator (ALO) as a novel method for tackling large displacement problem of the optical flow estimation methods.”
MethodBilayer Sparse Topic Model for Scene Analysis in Imbalanced Surveillance Videos
Wang, J., Fu, W., Lu, H., & Ma, S. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2363408 · Cited by 15
Depth From Light Fields Analyzing 4D Local Structure
Luke, J. P., Rosa, F. L., Marichal-Hernández, J. G., Sanluis, J. C., Conde, C. D., & Rodríguez-Ramos, J. M. (2014) · Journal of Display Technology · doi:10.1109/jdt.2014.2360992 · Cited by 15
Multi-image super-resolution using a dual weighting scheme based on Voronoi tessellation
Bätz, M., Eichenseer, A., & Kaup, A. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532874 · Cited by 15
“Here, motion estimation is conducted by applying the TV-L1based optical flow described in [18, 19] on all auxiliary frames around the frame to be super-resolved, i.”
MethodFALDOI: A New Minimization Strategy for Large Displacement Variational Optical Flow
Palomares, R. P., Meinhardt-Llopis, E., Ballester, C., & Haro, G. (2016) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-016-0688-y · Cited by 14
“Then, a simple thresholding step gives an explicit solution [62].”
BackgroundMethodDense Batch Non-Rigid Structure from Motion in a Second
Golyanik, V., & Stricker, D. (2017) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2017.35 · Cited by 15
Deep Adaptive Temporal Pooling for Activity Recognition
Song, S., Cheung, N. M., Chandrasekhar, V., & Mandal, B. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240713 · Cited by 16
“ed average of them by setting the spatial weight as 1 and temporal weight as 1.5. We use dense optical flow approach for extracting motions from videos as the input of temporal stream. TVL1 algorithm [46] is chosen as the implementation of optical flow algorithm. For MoG parameter initialization, we initialize the mea…”
InfluentialNon-Local Kalman: A Recursive Video Denoising Algorithm
Ehret, T., Morel, J., & Arias, P. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451421 · Cited by 15
“In particular, we used the implementation of [14] of the TV-L1 optical flow [15].”
MethodDu, L., Wang, Z., Wang, L., Zhao, Z., Su, F., Zhuang, B., & Boulgouris, N. V. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2905598 · Cited by 15
“In TVNet [12], a relaxed formulation of TV-L1 [13] optical-flow optimization was implemented in the form of a neural network that can be trained in an end-to-end fashion.”
MethodInfluentialAn End to End Framework With Adaptive Spatio-Temporal Attention Module for Human Action Recognition
Liu, S., Ma, X., Wu, H., & Li, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2979549 · Cited by 16
“At testing, we use TV-L1 algorithm [37] to extract stacks of flow fields from the center and four corners of a video, which is implemented in OpenCV with CUDA.”
MethodFast Optical Flow Extraction From Compressed Video
Young, S. I., Girod, B., & Taubman, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2985866 · Cited by 15
“Despite its simplicity, the variational optimization framework of Horn and Schunck is still the basis of recent motion estimation algorithms; see, e.g., [15]–[22].”
BackgroundCompound Micro-Expression Recognition System
Zhao, Y., & Xu, J. (2020) · International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) · doi:10.1109/icitbs49701.2020.00161 · Cited by 14
Busy-Quiet Video Disentangling for Video Classification
Huang, G., & Borş, A. G. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00083 · Cited by 18
“We draw an apple-to-apple comparison between the proposed MBPM and other motion representation methods [2, 10, 23, 47, 52, 54].”
MethodModeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
Li, J., Qiang, W., Zheng, C., Su, B., Razzak, F., Wen, J.-R., & Xiong, H. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3198746 · Cited by 16
Zhang, B., Ma, K., Wu, S., & Yuan, Z. (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/cvpr52729.2023.00548 · Cited by 15
“Many previous works have utilized optical flow methods [27] or event cameras [31] to represent motion versus capturing the motion of moving objects.”
BackgroundResidual Images Remove Illumination Artifacts!
Vaudrey, T., & Klette, R. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03798-6_48 · Cited by 15
Evaluation of clustering methods for finding dominant optical flow fields in crowded scenes
Eibl, G., & Brändle, N. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761911 · Cited by 15
“The N feature vectors are randomly sampled from dense optical flow fields obtained by a real-time variational approach published in [7].”
MethodMoving object detection in dynamic scenes based on optical flow and superpixels
Li, X., & Xu, C. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7414628 · Cited by 15
“To overcome these limitations, this paper selects TV-L(1) [12] optical flow as a scheme to compute optical flow field.”
BackgroundMethodBoosting VLAD with double assignment using deep features for action recognition in videos
Duţă, I. C., Nguyen, T. A., Aizawa, K., Ionescu, B. E., & Sebe, N. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899964 · Cited by 15
“To extract optical flow fields we use the OpenCV implementation of TVL1 algorithm [27].”
MethodVillela, K., Nass, C., Novais, R. L., Simões, P., Traina, A. J. M., Rodrigues, J. A., Menéndez, J. M., Kurano, J. A., Franke, T., & Poxrucker, A. (2018) · Studies in computational intelligence · doi:10.1007/978-3-319-74002-7_9 · Cited by 15
Joint Feature Optimization and Fusion for Compressed Action Recognition
Li, H., Jiang, X., Guan, B., Tan, R. R. M., Wang, R., & Magnenat‐Thalmann, N. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3112008 · Cited by 15
Automatic calibration of RGBD and thermal cameras
Lussier, J. T., & Thrun, S. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942598 · Cited by 15
“T }, we first run TV-L1 optical flow estimation [22].”
MethodSim2real transfer learning for 3D pose estimation: motion to the rescuePreprint
Doersch, C., & Zisserman, A. (2019) · arXiv (Cornell University) · Cited by 15
Xin, H., Zheng, S., Xu, K., & Yan, L. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.3023129 · Cited by 18
“We use the TV-L1 algorithm [39] to calculate the optical flow of adjacent frames.”
MethodUsing Visual Anomaly Detection for Task Execution Monitoring
Thoduka, S., Gall, J., & Plöger, P. G. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636133 · Cited by 14
“The expected optical flow caused by the robot body, O , is calculated from consecutive rendered frames, using the TV-L1 algorithm [26].”
A Two-Stage Modality Fusion Approach for Recognizing Human Actions
Zheng, H. M., Zhang, B., Lin, J., Zhao, D., & Shang, G. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3316137 · Cited by 14
“The method used to compute optical flow is TVL1 [51].”
MethodContrastive Transformer Hashing for Compact Video Representation
Shen, X., Zhou, Y., Yuan, Y., Yang, X., Lan, L., & Zheng, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3326994 · Cited by 14
“For OPF modality, each frame is represented by TV-L 1 feature [41] due to its excellent performance.”
MethodMumtaz, A., Sargano, A. B., & Habib, Z. (2024) · The Visual Computer · doi:10.1007/s00371-023-03210-4 · Cited by 14
“There are many common motion-flow estimators, such as TVL1 [88] and FlowFields [89] are classical approaches, whereas FlowNet2 [90] and PWC-Net [91] aredeeprepresentation-basedapproaches.”
Alvén, J., Hagberg, E., Hagerman, D., Petersen, R., & Hjelmgren, O. (2024) · Scientific Reports · doi:10.1038/s41598-024-52480-y · Cited by 13
“We used the Dual TV L1 optical flow algorithm in Zach et al. 22 . implemented in OpenCV 4.4.0, for flow computations (stopping criterion threshold 0.05, number of warpings per scale 1, number of pyramid scales 1).”
MethodInfluentialMultimodal Attention-Enhanced Feature Fusion-Based Weakly Supervised Anomaly Violence Detection
Shin, J., Miah, A. S. M., Kaneko, Y., Hassan, N., Lee, H.-S., & Jang, S.-W. (2025) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2024.3517154 · Cited by 14
Mauthner, T., Roth, P. M., & Bischof, H. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02230-2_1 · Cited by 14
“To estimate the motion information, a dense optical flow field is computed between consecutive frames using an efficient GPU-based implementation [16].”
MethodSelf-citationExploring Fisher vector and deep networks for action spotting
Wang, Z., Wang, L., Du, W., & Qiao, Y. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301330 · Cited by 13
“Thus, we follow the work of [20], and extract optical flow [22] from videos and store them as gray images, which can be used as the input for temporal convolutional neural network.”
MethodOttaviano, G., & Kohli, P. (2013) · 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.2013.292 · Cited by 14
“For this reason, we use a decomposition based approach used in [21].”
MethodAirborne Based High Performance Crowd Monitoring for Security Applications
Perko, R., Schnabel, T., Fritz, G., Almér, A., & Paletta, L. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38886-6_62 · Cited by 14
Virtual reality for animal navigation with camera-based optical flow tracking
Vishniakou, I., Plöger, P. G., & Seelig, J. D. (2019) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2019.108403 · Cited by 14
Multi-level Temporal Pyramid Network for Action Detection
Wang, X., Gao, C., Zhang, S., & Sang, N. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60639-8_4 · Cited by 14
Joint projection filling method for occlusion handling in Depth-Image-Based Rendering
Jantet, V., Guillemot, C. M., & Morin, L. (2011) · 3D Research · doi:10.1007/3dres.04(2011)4 · Cited by 15
“Depth-Image-Based Rendering (DIBR) techniques [Shum and Kang(2000), Zhang and Chen(2004)] include hybrid rendering methods between IBR and GBR techniques.”
MethodVariational method for super-resolution optical flow
Mochizuki, Y., Kameda, Y., Imiya, A., Sakai, T., & Imaizumi, T. (2010) · Signal Processing · doi:10.1016/j.sigpro.2010.11.010 · Cited by 14
Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations
Lasinger, K., Vogel, C., & Schindler, K. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.280 · Cited by 14
“The ancestral smoothness term is quadratic regularization (QR) [17], later it emerged that the more robust Total Variation (TV) [32, 39] was often preferable.”
BackgroundChasing Feet in the Wild: A Proposed Egocentric Motion-Aware Gait Assessment Tool
Nouredanesh, M., Li, A. W., Godfrey, A., Hoey, J., & Tung, J. Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11024-6_12 · Cited by 14
COIN: A Large-scale Dataset for Comprehensive Instructional Video AnalysisPreprint
Tang, Y., Ding, D., Rao, Y., Zheng, Y., Zhang, D., Zhao, L., Lu, J., & Zhou, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02874 · Cited by 14
“Here SSN−Flow adopted the optical flows calculated by [48], and SSN−Fusion combined the predicted scores of SSN−RGB and SSN−Flow.”
MethodZhao, S., Li, S., Zhang, Y., & Liu, S. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3568633 · Cited by 15
“After that, themotionflow features between the key frames are extracted by the TV_L1 method in [33].”
Robust modified L2 local optical flow estimation and feature tracking
Senst, T., Eiselein, V., Evangelio, R. H., & Sikora, T. (2011) · Proceedings · doi:10.1109/wacv.2011.5711571 · Cited by 13
“More robust norms are the modified L(1) [12, 22] norm and Huber’s minmax norm [3, 20], because their influence functions are limited.”
BackgroundResultLightweight Video Denoising using Aggregated Shifted Window Attention
Lindner, L., Effland, A., Ilic, F., Pock, T., & Kobler, E. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00043 · Cited by 13
“This method incorporates TV-l1 optical flow [40], thereby creating a significant dependence on the accuracy of a motion estimate.”
MethodSelf-citationVideo-based neonatal pain expression recognition with cross-stream attention
Lu, G., Chen, H., Wei, J.-S., Li, X.-N., Zheng, X.-L., Leng, H.-Y., Lou, Y., & Yan, J.-J. (2023) · Multimedia tools and applications · doi:10.1007/s11042-023-15403-z · Cited by 12
“For temporal stream ConvNet, TV-L1 algorithm [38] is used to estimate the optical-flow maps of consecutive frames from a given video clip with the length of ( L + 1) frames, and thus 2 L optical-flow maps (including horizontal and vertical components) are obtained.”
Context-aware Video Anomaly Detection in Long-Term Datasets
Yang, Z., & Radke, R. J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00404 · Cited by 13
“We use the TV-L1 method [38] to extract a pixel-wise flow field and divide the input into non-overlapping patches for calculating the histogram of flow.”
Activity detection and recognition of daily living events
Avgerinakis, K., Briassouli, A., & Kompatsiaris, I. Y. (2013) · doi:10.1145/2505323.2505327 · Cited by 13
Stixels Motion Estimation without Optical Flow Computation
Günyel, B., Benenson, R., Timofte, R., & Gool, L. V. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33783-3_38 · Cited by 13
Occlusion-aware video registration for highly non-rigid objects
Taetz, B., Bleser, G., Golyanik, V., & Stricker, D. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477720 · Cited by 13
“Due to the high parallelizability of these methods, real-time capability was achieved [28].”
MethodQiu, W., Chen, Y., Kishimoto, J., de Ribaupierre, S., Chiu, B. C. Y., Fenster, A., Menon, B. K., & Yuan, J. Y. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2643635 · Cited by 13
“methods, were successfully developed to efficiently solve a wide spectrum of problems in medical image segmentation [32], [33], [34], [35], [36] and registration [37], [38], [39], [40], [34], [35], [36].”
MethodVariational 3D-PIV with sparse descriptors
Lasinger, K., Vogel, C., Pock, T., & Schindler, K. (2018) · Measurement Science and Technology · doi:10.1088/1361-6501/aab5a0 · Cited by 13
Self-citationReal-Time Sign Language Recognition Based on Video Stream
Zhao, K., Zhang, K., Zhai, Y. J., Wang, D., & Su, J. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9188508 · Cited by 13
Multi-View Hand-Hygiene Recognition for Food Safety
Zhong, C., Reibman, A. R., Mina, H. A., & Deering, A. J. (2020) · Journal of Imaging · doi:10.3390/jimaging6110120 · Cited by 13
“For this, we create optical flow images using the TV-L1 optical flow [48] implementation [49].”
MethodMartínez-Cebrián, J., Fernández‐Torres, M., & Díaz-de-María, F. (2020) · IEEE Access · doi:10.1109/access.2020.3041606 · Cited by 14
“Second, the optical flow algorithm used for motion estimation is an efficient implementation 1 of TVL1 [58].”
MethodExploiting inter-frame regional correlation for efficient action recognition
Xu, Y., Yang, J., Mao, K., Yin, J., & See, S. C. W. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114829 · Cited by 13
An Efficient Algorithm for Ocean-Front Evolution Trend Recognition
Yang, Y., Lam, K., Sun, X., Dong, J., & Lguensat, R. (2022) · Remote Sensing · doi:10.3390/rs14020259 · Cited by 13
“Furthermore, we apply the TVL1 method [55] to extract optical-flow images.”
MethodWeakly-supervised temporal action localization: a survey
Baraka, A. M., & Noor, M. H. M. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07102-x · Cited by 13
“TV-L1 [38] is one of the most important algorithms that is used in WTAL to compute the optical-flow between frames, as well as pre-training the networks on large-scale action recognition datasets such as UCF-101 [39] or HMDB-51 [40].”
MethodKhowaja, S. A., & Lee, S. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-03848-3 · Cited by 13
“The RGB modality is mostly used for action recognition mainly for two reasons: the first is the flexibility of transformation to derive different representations such as optical flows (Zach et al. 2007), dynamic images (Bilen et al.”
BackgroundMethod
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
