Dense Trajectories and Motion Boundary Descriptors for Action Recognition
Open accessThe DOI matches its Crossref record; 71 of the 72 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · cited 2×
“Yeffet and Wolf (2009) pro-pose Local Trinary Patterns for videos as extension of Local Binary Patterns (LBP) (Ojala et al, 2002).”
BackgroundMethodSURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · cited 2×
“Willems et al (2008) generalizes the image SURF descriptor (Bay et al, 2006) to the video domain by computing weighted sums of uniformly sampled responses of spatio-temporal Haar wavelets.”
(1981) · Cited by 11,963
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · cited 1×
“2010), an extension of spatial pyramids for images (Lazebnik et al. 2006).”
Self-citationShi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 1×
“Here, we use the criterion of Shi and Tomasi (1994), that is points on the grid are removed, if the eigenvalues of the auto-correlation matrix are very small.”
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965 · cited 1×
“We follow the original protocol using three train-test splits (Kuehne et al, 2011).”
A Bayesian Hierarchical Model for Learning Natural Scene Categories
Li, F.-F., & Perona, P. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.16 · Cited by 3,613 · cited 4×
“Another possible explanation is that Farneb¨ack (2003) estimates optical flow locally and captures fine details in textured areas, whereas LDOF includes global smoothness constraints and preserves motion boundaries, see figure 10.”
BackgroundMethodInfluentialLearning realistic human actions from movies
Laptev, I., Marszalek, M., Schmid, C., & Rozenfeld, B. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587756 · Cited by 3,444 · cited 1×
“…descriptors range from higher order derivatives (lo-cal jets), gradient information, optical flow, and brightness information (Doll´ar et al, 2005; Laptev et al, 2008; Sch¨uldt et al, 2004) to spatio-temporal extensions of image descriptors, such as 3D-SIFT (Scovanner et al, 2007), HOG3D…”
BackgroundSelf-citationRecognizing human actions: a local SVM approach
Schuldt, C., Laptev, I., & Caputo, B. (2004) · Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. · doi:10.1109/icpr.2004.1334462 · Cited by 3,010
Two-Frame Motion Estimation Based on Polynomial Expansion
Farnebäck, G. (2003) · Lecture Notes in Computer Science · doi:10.1007/3-540-45103-x_50 · Cited by 2,971 · cited 4×
“Another possible explanation is that Farneb¨ack (2003) estimates optical flow locally and captures fine details in textured areas, whereas LDOF includes global smoothness constraints and preserves motion boundaries, see figure 10.”
BackgroundMethodInfluentialRecognizing human actions: A local SVM approach
Schüldt, C., Laptev, I., & Barbara Caputo, B. (2004) · Cited by 2,906
Laptev, I. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-1838-7 · Cited by 2,629
Behavior Recognition via Sparse Spatio-Temporal Features
Dollar, P., Rabaud, V., Cottrell, G., & Belongie, S. (2006) · 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance · doi:10.1109/vspets.2005.1570899 · Cited by 2,460 · cited 5×
“Other detection approaches are based on Gabor filters (Bre-gonzio et al, 2009; Doll´ar et al, 2005) and on the determinant of the spatio-temporal Hessian matrix (Willems et al, 2008).”
BackgroundMethodInfluentialAction recognition by dense trajectories
Wang, H., Klaser, A., Schmid, C., & Liu, C.-L. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995407 · Cited by 2,154 · cited 2×
“A preliminary version of this article has appeared in (Wang et al, 2011).”
Self-citationZhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-9794-4 · Cited by 1,923 · cited 2×
“Different descriptors are combined in a multi-channel approach (Zhang et al, 2007): where D ( x ci , x cj ) is the χ 2 distance between video x i and x j with respect to the c -th channel.”
Self-citationA Spatio-Temporal Descriptor Based on 3D-Gradients
Klaeser, A., Marszalek, M., & Schmid, C. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.99 · Cited by 1,846 · cited 4×
“Feature descriptors range from higher order derivatives (lo-cal jets), gradient information, optical flow, and brightness information (Doll´ar et al, 2005; Laptev et al, 2008; Sch¨uldt et al, 2004) to spatio-temporal extensions of image descriptors, such as 3D-SIFT (Scovanner et al, 2007), HOG3D (Kl¨aser et al, 2008),…”
BackgroundInfluentialSelf-citationHuman Detection Using Oriented Histograms of Flow and Appearance
Dalal, N., Triggs, B., & Schmid, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744047_33 · Cited by 1,652 · cited 4×
“Laptev (2005) have introduced spatio-temporal interest points, which are an extension of the Harris detector from image to video.”
BackgroundMethodInfluentialSelf-citationA 3-dimensional sift descriptor and its application to action recognition
Scovanner, P., Ali, S., & Shah, M. (2007) · Proceedings of the 15th ACM international conference on Multimedia · doi:10.1145/1291233.1291311 · Cited by 1,596 · cited 3×
“…brightness information (Doll´ar et al, 2005; Laptev et al, 2008; Sch¨uldt et al, 2004) to spatio-temporal extensions of image descriptors, such as 3D-SIFT (Scovanner et al, 2007), HOG3D (Kl¨aser et al, 2008), extended SURF (Willems et al, 2008), and Local Trinary Patterns (Yeffet and Wolf, 2009).”
Evaluation of local spatio-temporal features for action recognition
Wang, H., Ullah, M. M., Klaser, A., Laptev, I., & Schmid, C. (2009) · Procedings of the British Machine Vision Conference 2009 · doi:10.5244/c.23.124 · Cited by 1,296 · cited 6×
“More specifically, about 100 interest points are detected in each frame and are added to the tracker – this is somewhat denser than space-time interest points (Wang et al, 2009).”
InfluentialSelf-citationLarge 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 MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition
Rodriguez, M. D., Ahmed, J., & Shah, M. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587727 · Cited by 1,223 · cited 2×
“In this section, we evaluate the impact of the parameters on dense trajectories.”
BackgroundMarszalek, M., Laptev, I., & Schmid, C. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206557 · Cited by 1,168 · cited 2×
“The performance is evaluated by computing the average precision (AP) for each action class and reporting the mean AP over all classes (mAP) as in Marszałek et al (2009).”
Self-citationRecognizing realistic actions from videos “in the wild”
Liu, J., Luo, J., & Shah, M. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206744 · Cited by 1,075 · cited 5×
“Scovanner et al (2007) extend the popular SIFT descriptor (Lowe, 2004) to the spatiotemporal domain, and Kläser et al (2008) introduce the HOG3D descriptor. Willems et al (2008) generalizes the image SURF descriptor (Bay et al, 2006) to the video domain by computing weighted sums of uniformly sampled responses of spat…”
InfluentialLe, Q. V., Zou, W. Y., Yeung, S. Y., & Ng, A. Y. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995496 · Cited by 960 · cited 1×
“This is over 6% higher than the state of the art (Le et al, 2011) that employs features learning using deep networks.”
Sampling Strategies for Bag-of-Features Image Classification
Nowak, E., Jurie, F., & Triggs, B. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744085_38 · Cited by 927 · cited 2×
“We show that motion boundaries provide a robust descriptor for action recognition that significantly outperforms existing state-of-the-art descriptors.”
BackgroundFree viewpoint action recognition using motion history volumes
Weinland, D., Ronfard, R., & Boyer, E. (2006) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2006.07.013 · Cited by 896
An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector
Willems, G., Tuytelaars, T., & Van Gool, L. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88688-4_48 · Cited by 869 · cited 9×
“SIFT trajectories can also handle shot boundaries, but are not able to capture the complex motion patterns accurately. tectors.”
BackgroundMethodResultInfluentialObject Segmentation by Long Term Analysis of Point Trajectories
Brox, T., & Malik, J. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15555-0_21 · Cited by 744 · cited 8×
“The resulting trajectories are more robust, in particular in the presence of fast irregular motions (Sand and Teller, 2008; Brox and Malik, 2010; Wang et al, 2011), see Figure 1.”
InfluentialModeling Temporal Structure of Decomposable Motion Segments for Activity Classification
Niebles, J. C., Chen, C.-W., & Fei-Fei, L. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15552-9_29 · Cited by 700
Action bank: A high-level representation of activity in video
Sadanand, S., & Corso, J. J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247806 · Cited by 691 · cited 1×
“On the recent HMDB51 dataset, we outperform the state of the art (Sadanand and Corso, 2012) by 16% using only “MBH”.”
Recognizing 50 human action categories of web videos
Reddy, K. K., & Shah, M. (2013) · Machine Vision and Applications · doi:10.1007/s00138-012-0450-4 · Cited by 655
Convolutional Learning of Spatio-temporal Features
Taylor, G. W., Fergus, R., LeCun, Y., & Bregler, C. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15567-3_11 · Cited by 629 · cited 1×
“6 Tran and Sorokin (2008) 80.”
Learning the distribution of object trajectories for event recognition
Johnson, N., & Hogg, D. (1996) · Image and Vision Computing · doi:10.1016/0262-8856(96)01101-8 · Cited by 499
Learning a hierarchy of discriminative space-time neighborhood features for human action recognition
Kovashka, A., & Grauman, K. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539881 · Cited by 495 · cited 1×
“1% which is around 2% better than the state of the art (Kovashka and Grauman, 2010).”
Activity recognition using the velocity histories of tracked keypoints
Messing, R., Pal, C., & Kautz, H. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459154 · Cited by 455 · cited 7×
“To quantify the improvement obtained with our dense trajectories, we compare to three baseline trajectories in our experimental results: KLT trajectories (Matikainen et al, 2009; Messing et al, 2009; Sun et al, 2010), SIFT trajectories (Sun et al, 2009, 2010), as well as dense cuboids.”
InfluentialAction Recognition from Arbitrary Views using 3D Exemplars
Weinland, D., Boyer, E., & Ronfard, R. (2007) · 2007 IEEE 11th International Conference on Computer Vision · doi:10.1109/iccv.2007.4408849 · Cited by 448 · cited 2×
“IXMAS 10 (Weinland et al, 2007) is a dataset recorded by cameras from five different viewpoints, as shown in the fifth row of Figure 8.”
MethodDense 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 422 · cited 2×
“Dalal et al (2006) proposed the motion boundary histograms (MBH) descriptor for human detection by computing derivatives separately for the horizontal and vertical components of the optical flow.”
MethodView-Independent Action Recognition from Temporal Self-Similarities
Junejo, I. N., Dexter, E., Laptev, I., & Pérez, P. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.68 · Cited by 392
Particle Video: Long-Range Motion Estimation Using Point Trajectories
Sand, P., & Teller, S. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-008-0136-6 · Cited by 365
Hierarchical spatio-temporal context modeling for action recognition
Sun, J., Wu, X., Yan, S., Cheong, L.-F., Chua, T.-S., & Li, J. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206721 · Cited by 358 · cited 4×
“Some recent methods (Matikainen et al, 2009; Messing et al, 2009; Sun et al, 2009, 2010) show good results for action recognition by leveraging the motion information of trajectories.”
InfluentialLocal Trinary Patterns for human action recognition
Yeffet, L., & Wolf, L. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459201 · Cited by 339 · cited 4×
“Feature descriptors range from higher order derivatives (lo-cal jets), gradient information, optical flow, and brightness information (Doll´ar et al, 2005; Laptev et al, 2008; Sch¨uldt et al, 2004) to spatio-temporal extensions of image descriptors, such as 3D-SIFT (Scovanner et al, 2007), HOG3D (Kl¨aser et al, 2008),…”
InfluentialHuman Activity Recognition with Metric Learning
Tran, D., & Sorokin, A. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_42 · Cited by 332 · cited 2×
“The UIUC dataset(12) (Tran and Sorokin, 2008) is recorded in a controlled experimental setting with clean background and fixed cameras.”
Recognising action as clouds of space-time interest points
Bregonzio, M., Gong, S., & Xiang, T. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206779 · Cited by 332 · cited 1×
“Bregonzio et al (2009) have extended this approach with 2D Gabor filters of different orientations.”
Object, Scene and Actions: Combining Multiple Features for Human Action Recognition
Ikizler-Cinbis, N., & Sclaroff, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_36 · Cited by 285
Learning spatiotemporal graphs of human activities
Brendel, W., & Todorovic, S. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126316 · Cited by 231 · cited 2×
“Brendel and Todorovic [62] reported a similar result (77.”
Trajectons: Action recognition through the motion analysis of tracked features
Matikainen, P., Hebert, M., & Sukthankar, R. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457659 · Cited by 224
Extracting Spatiotemporal Interest Points using Global Information
Wong, S.-F., & Cipolla, R. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4408923 · Cited by 224 · cited 1×
“Wong and Cipolla (2007) have added global informa-1 tion to the interest point detection by applying non-negative matrix factorization (NNMF) on the entire video sequence.”
Action recognition using context and appearance distribution features
Wu, X., Xu, D., Duan, L., & Luo, J. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995624 · Cited by 222 · cited 2×
“6% and significantly outperforms the state of the art (Wu et al, 2011b) by 5% .”
Motion Interchange Patterns for Action Recognition in Unconstrained Videos
Kliper-Gross, O., Gurovich, Y., Hassner, T., & Wolf, L. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33783-3_19 · Cited by 184 · cited 1×
“Recently, Kliper-Gross et al (2012) reported 72 .”
Discriminative Video Pattern Search for Efficient Action Detection
Yuan, J., Liu, Z., & Wu, Y. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.38 · Cited by 172
Trajectory analysis and semantic region modeling using a nonparametric Bayesian model
Wang, X., Ma, K. T., Ng, G.-W., & Grimson, W. E. L. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587718 · Cited by 170
Action Recognition Using Mined Hierarchical Compound Features
Gilbert, A., Illingworth, J., & Bowden, R. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.144 · Cited by 167 · cited 1×
“8 Gilbert et al. (2011) 50.”
Wu, S., Oreifej, O., & Shah, M. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126397 · Cited by 165 · cited 2×
“6% and significantly outperforms the state of the art (Wu et al, 2011b) by 5% .”
BackgroundTracklet Descriptors for Action Modeling and Video Analysis
Raptis, M., & Soatto, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_42 · Cited by 147 · cited 1×
“Raptis and Soatto (2010) track feature points in regions of interest.”
Multifeature Object Trajectory Clustering for Video Analysis
Anjum, N., & Cavallaro, A. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2008.2005603 · Cited by 130 · cited 2×
“Mean shift is applied to cluster object trajectories based on multiple features in (Anjum and Cavallaro, 2008), and clusters with less trajectories are considered as rare events. Similarly, Jung et al (2008) design a framework for event detection in video”
Improving bag-of-features action recognition with non-local cues
Ullah, M. M., Parizi, S. N., & Laptev, I. (2010) · British Machine Vision Conference (BMVC) · doi:10.5244/c.24.95 · Cited by 117 · cited 1×
“We add structure information to the bag of features using spatio-temporal pyramids (Laptev et al, 2008; Ullah et al, 2010), an extension of spatial pyramids for images (Lazeb-nik et al, 2006).”
MethodProceedings of the ... Scandinavian Conference on Image Analysis
Bildanalys, S. S. F. A. (1980) · Medical Entomology and Zoology · Cited by 116
Feature Tracking and Motion Compensation for Action Recognition
Uemura, H., Ishikawa, S., & Mikolajczyk, K. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.30 · Cited by 77 · cited 2×
“Compared to video stabilization (Ikizler-Cinbis and Sclaroff, 2010) and motion compensation (Uemura et al, 2008), this is a simpler way to discount for camera motion.”
Activity recognition using dense long-duration trajectories
Sun, J., Mu, Y., Yan, S., & Cheong, L. (2010) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2010.5583046 · Cited by 68 · cited 6×
“Recently, Sun et al (2010) combined both approaches and added random trajectories in low density regions of both trackers in order to increase density.”
InfluentialRecognizing activities with cluster-trees of tracklets
Gaidon, A., Harchaoui, Z., & Schmid, C. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.30 · Cited by 67 · cited 1×
“Recently, Gaidon et al (2012) achieved 82 .”
Self-citationActivities as Time Series of Human Postures
Brendel, W., & Todorović, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15552-9_52 · Cited by 66 · cited 2×
“On YouTube, we significantly outperform the state of the art (Brendel and Todorovic, 2010) by over 8%.”
Recognition of Dynamic Video Contents With Global Probabilistic Models of Visual Motion
Piriou, G., Bouthémy, P., & Yao, J. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881963 · Cited by 47 · cited 2×
“Similarly, Jung et al (2008) design a framework for event detection in video To take into account camera motion, Piriou et al (2006) define global probabilistic motion models for both the dominant image motion (assumed to be due to camera motion) and the residual image motion (related to scene…”
Event Detection Using Trajectory Clustering and 4-D Histograms
Jung, C. R., Hennemann, L., & Musse, S. R. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2008.2005600 · Cited by 38 · cited 2×
“Similarly, Jung et al (2008) design a framework for event detection in video To take into account camera motion, Piriou et al (2006) define global probabilistic motion models for both the dominant image motion (assumed to be due to camera motion) and the residual image motion (related to scene…”
A Statistical Video Content Recognition Method Using Invariant Features on Object Trajectories
Hervieu, A., Bouthémy, P., & Cadre, J.-P. L. (2008) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2008.2005609 · Cited by 35 · cited 1×
“As we use trajectories with a fixed length of L = 15 frames, we obtain a 30 dimensional descriptor.”
MethodWill person detection help bag-of-features action recognition?
Kläser, A., Marszałek, M., Ivan Laptev, A., & Schmid, C. (2010) · Cited by 35
Self-citationA probabilistic representation for efficient large scale visual recognition tasks
Bhattacharya, S., Sukthankar, R., Jin, R., & Shah, M. A. (2011) · 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.2011.5995746 · Cited by 34 · cited 1×
“Willems et al (2008) generalizes the image SURF descriptor (Bay et al, 2006) to the video domain by computing weighted sums of uniformly sampled responses of spatio-temporal Haar wavelets.”
BackgroundMachine Learning for Vision-Based Motion Analysis
(2010) · Advances in computer vision and pattern recognition · doi:10.1007/978-0-85729-057-1 · Cited by 22 · cited 2×
“A preliminary version of this article has appeared in (Wang et al, 2011).”
Learning Dense Optical-Flow Trajectory Patterns for Video Object Extraction
Lu, W.-C., Wang, Y.-C. F., & Chen, C. (2010) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2010.79 · Cited by 13 · cited 1×
“A similar approach is proposed by Lu et al (2010).”
MethodIEEE Transactions on Multimedia
(2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2723119 · Cited by 1
Cited by
Long-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
“[29] uses dense trajectories [44] and SIFT features as well as temporal context reasoning modeled in a CRF.”
MethodAction Recognition with Improved Trajectories
Wang, H., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.441 · Cited by 3,407
Self-citationViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767
“Early video research used hand-crafted features to encode appearance and motion information [41, 69].”
MethodSelf-citationCan Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
Hara, K., Kataoka, H., & Satoh, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00685 · Cited by 2,205
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599174 · Cited by 1,547
Metadata
- Authors
- Wang, H., Kläser, A., Schmid, C., & Liu, C.-L.
- Affiliations
- Institut national de recherche en sciences et technologies du numérique (FR)
- Chinese Academy of Sciences (CN)
- Corresponding author
- Wang, Heng
- Venue
- International Journal of Computer Vision
- Published
- 2013-03-06
- Volume
- 103
- Issue
- 1
- Pages
- 60-79
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2068611653
- Cited by
- 1,669
- References
- 72
- Citations by year
- 2026: 26 · 2025: 53 · 2024: 66 · 2023: 76 · 2022: 91 · 2021: 137 · 2020: 113 · 2019: 148 · 2018: 204 · 2017: 200 · 2016: 199 · 2015: 193 · 2014: 126 · 2013: 37
- FWCI
- 208.13
- Type
- journal article
- Language
- en
- Open access
- green
- inria.hal.science
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- Locations
- International Journal of Computer Vision (publishedVersion)
- HAL (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Keywords
- dense trajectories, human action recognition, video representation, optical flow, histogram of oriented gradients, camera movement
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.