pith. sign in

arxiv: 2604.15707 · v1 · submitted 2026-04-17 · 💻 cs.CV

LP²DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition

Ruxin Ding , Jianfeng Ren , Heng Yu , Jiawei Li , Xudong Jiang This is my paper

Pith reviewed 2026-05-10 08:59 UTC · model grok-4.3

classification 💻 cs.CV
keywords hashingbinarydynamiclocality-preservingpixel-differencetexturecodesframework
0
0 comments X

The pith

LP²DH jointly hashes spatiotemporal pixel-difference vectors with locality preservation and Stiefel-manifold optimization to produce compact binary features that achieve state-of-the-art accuracy on UCLA, DynTex++, and YUPENN dynamic texture benchmarks.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Dynamic textures are moving patterns in video, such as flames or waves. Older methods like STLBP create huge feature sets by looking at local patterns on separate planes, losing some connections between space and time. LP²DH instead computes differences between nearby pixels in both space and time, turns those difference vectors into short binary codes, and uses a special optimization on a curved mathematical surface to keep similar patterns close together after coding. It then groups the codes into a dictionary and makes a histogram as the final summary for classification.

Core claim

The proposed LP²DH achieves state-of-the-art performance on three major dynamic texture recognition benchmarks: 99.80% against DT-GoogleNet's 98.93% on UCLA, 98.52% against HoGF³D's 97.63% on DynTex++, and 96.19% compared to STS's 95.00% on YUPENN.

Load-bearing premise

That the locality-preserving embedding combined with curvilinear search on the Stiefel manifold produces binary codes whose discriminative power generalizes beyond the three specific benchmarks without overfitting or requiring extensive hyperparameter tuning.

Figures

Figures reproduced from arXiv: 2604.15707 by Heng Yu, Jianfeng Ren, Jiawei Li, Ruxin Ding, Xudong Jiang.

Figure 1
Figure 1. Figure 1: Overview of proposed LP2DH. It derives compact and discriminative features in two stages: 1) Locality-Preserving Pixel Difference Hashing, which maps PDVs to binary codes using an optimized projection matrix W. The matrix is learned through a multi-objective formulation that minimizes quantization loss (L1), maximizes information (L2) and variance (L3) and preserves local topology (L4), solved via Stiefel … view at source ↗
Figure 3
Figure 3. Figure 3: The per-class recognition rates of HOGF3D [1] and LP2DH on the DynTex++ dataset [66]. dictionary-based semantic aggregation, LP2DH captures subtle inter-class variations that are often lost in conventional hand￾crafted pipelines [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Ablation of LP2DH with different (a) dictionary size, (b) binary code length for P = 3, (c) binary code length for P = 5, (d) the number of nearest neighbours, (e) λ1, (f) λ2, and (g) λ3. TABLE IV RUNTIME COMPARISON ON THE DYNTEX++ DATASET. Category Method Train (s) Test (s) Optical-flow-based FD-MAP [13] 2,567 2,636 Model-based MixSHMM [17] 3,234 2,467 Geometry-based STLS [19] 13,206 13,109 Filter-based H… view at source ↗
read the original abstract

Spatiotemporal Local Binary Pattern (STLBP) is a widely used dynamic texture descriptor, but it suffers from extremely high dimensionality. To tackle this, STLBP features are often extracted on three orthogonal planes, which sacrifice inter-plane correlation. In this work, we propose a Locality-Preserving Pixel-Difference Hashing (LP$^{2}$DH) framework that jointly encodes pixel differences in the full spatiotemporal neighbourhood. LP$^{2}$DH transforms Pixel-Difference Vectors (PDVs) into compact binary codes with maximal discriminative power. Furthermore, we incorporate a locality-preserving embedding to maintain the PDVs' local structure before and after hashing. Then, a curvilinear search strategy is utilized to jointly optimize the hashing matrix and binary codes via gradient descent on the Stiefel manifold. After hashing, dictionary learning is applied to encode the binary vectors into codewords, and the resulting histogram is utilized as the final feature representation. The proposed LP$^{2}$DH achieves state-of-the-art performance on three major dynamic texture recognition benchmarks: 99.80% against DT-GoogleNet's 98.93% on UCLA, 98.52% against HoGF$^{3D}$'s 97.63% on DynTex++, and 96.19% compared to STS's 95.00% on YUPENN. The source code is available at: https://github.com/drx770/LP2DH.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Axiom & Free-Parameter Ledger

2 free parameters · 1 axioms · 0 invented entities

Abstract-only view limits visibility into exact hyperparameters; the framework implicitly relies on standard assumptions of manifold optimization and dictionary learning without introducing new physical entities.

free parameters (2)
  • hash code length
    Binary code dimensionality is a tunable parameter that controls compactness versus discriminability and must be chosen for each dataset.
  • dictionary size
    Number of codewords in the dictionary learning stage is a free parameter affecting the final histogram representation.
axioms (1)
  • domain assumption The Stiefel manifold optimization via curvilinear search converges to a useful local minimum for the joint hashing objective.
    Invoked when the paper states that the hashing matrix and binary codes are jointly optimized on the manifold.

pith-pipeline@v0.9.0 · 5579 in / 1322 out tokens · 44181 ms · 2026-05-10T08:59:30.143353+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

68 extracted references · 68 canonical work pages

  1. [1]

    Prominent local repre- sentation for dynamic textures based on high-order Gaussian-gradients,

    T. T. Nguyen, T. P. Nguyen, and F. Bouchara, “Prominent local repre- sentation for dynamic textures based on high-order Gaussian-gradients,” IEEE Trans. Multimedia, vol. 23, pp. 1367–1382, 2021

    work page 2021

  2. [2]

    Squirrel-cage local binary pattern and its application in video anomaly detection,

    X. Hu, Y . Huang, X. Gao, L. Luo, and Q. Duan, “Squirrel-cage local binary pattern and its application in video anomaly detection,”IEEE Trans. Inf. F orensics Security, vol. 14, no. 4, pp. 1007–1022, 2019

    work page 2019

  3. [3]

    Discriminant pixel- difference vector hashing of spatial-temporal local binary patterns for dynamic texture recognition,

    R. Ding, J. Ren, H. Yu, J. Li, and X. Jiang, “Discriminant pixel- difference vector hashing of spatial-temporal local binary patterns for dynamic texture recognition,” inIEEE Int. Conf. Acoust. Speech Signal Process., 2024, pp. 6245–6249

    work page 2024

  4. [4]

    Dynamic facial expression recognition under partial occlusion with optical flow reconstruction,

    D. Poux, B. Allaert, N. Ihaddadene, I. M. Bilasco, C. Djeraba, and M. Bennamoun, “Dynamic facial expression recognition under partial occlusion with optical flow reconstruction,”IEEE Trans. Image Process., vol. 31, pp. 446–457, 2022

    work page 2022

  5. [5]

    Dynamic texture recognition using volume local binary count patterns with an application to 2D face spoofing detection,

    X. Zhao, Y . Lin, and J. Heikkil ¨a, “Dynamic texture recognition using volume local binary count patterns with an application to 2D face spoofing detection,”IEEE Trans. Multimedia, vol. 20, no. 3, pp. 552– 566, 2018

    work page 2018

  6. [6]

    Dynamic scene understanding: The role of orientation features in space and time in scene classification,

    K. G. Derpanis, M. Lecce, K. Daniilidis, and R. P. Wildes, “Dynamic scene understanding: The role of orientation features in space and time in scene classification,” inIEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 1306–1313

    work page 2012

  7. [7]

    l0 gradient-regularization and scale space representation model for cartoon and texture decomposition,

    H. Pan, Y .-W. Wen, and Y . Huang, “l0 gradient-regularization and scale space representation model for cartoon and texture decomposition,” IEEE Trans. Image Process., vol. 33, pp. 4016–4028, 2024

    work page 2024

  8. [8]

    SARLBP: Scale adaptive robust local binary patterns for texture representation,

    P. C. Upadhyay, J. A. Lory, and G. N. DeSouza, “SARLBP: Scale adaptive robust local binary patterns for texture representation,”IEEE Trans. Image Process., vol. 34, pp. 969–981, 2025. IEEE TRANSACTIONS ON IMAGE PROCESSING 11

    work page 2025

  9. [9]

    Dynamic texture classification using unsupervised 3D filter learning and local binary encoding,

    X. Zhao, Y . Lin, L. Liu, J. Heikkil ¨a, and W. Zheng, “Dynamic texture classification using unsupervised 3D filter learning and local binary encoding,”IEEE Trans. Multimedia, vol. 21, no. 7, pp. 1694–1708, 2019

    work page 2019

  10. [10]

    A comprehensive taxonomy of dynamic texture representation,

    T. T. Nguyen and T. P. Nguyen, “A comprehensive taxonomy of dynamic texture representation,”ACM Comput. Surv., vol. 55, no. 1, pp. 1–39, 2021

    work page 2021

  11. [11]

    Optical flow computation for video under the dynamic illumination,

    J. Chen, H. Duan, Y . Song, Z. Cai, and G. Yang, “Optical flow computation for video under the dynamic illumination,”IEEE Trans. Multimedia, vol. 25, pp. 6285–6300, 2023

    work page 2023

  12. [12]

    Event-based optical flow via transforming into motion-dependent view,

    Z. Wan, G. Tan, Y . Wang, W. Zhai, Y . Cao, and Z.-J. Zha, “Event-based optical flow via transforming into motion-dependent view,”IEEE Trans. Image Process., vol. 33, pp. 5327–5339, 2024

    work page 2024

  13. [13]

    Directional beams of dense trajectories for dynamic texture recognition,

    T. T. Nguyen, T. P. Nguyen, F. Bouchara, and X. S. Nguyen, “Directional beams of dense trajectories for dynamic texture recognition,” inProc. Int. Conf. Adv. Concepts Intell. Vision Syst., 2018, pp. 74–86

    work page 2018

  14. [14]

    Dynamic texture video classification using extreme learning machine,

    L. Wang, H. Liu, and F. Sun, “Dynamic texture video classification using extreme learning machine,”Neurocomputing, vol. 174, pp. 278– 285, 2016

    work page 2016

  15. [15]

    Dynamical textures modeling via joint video dictionary learning,

    X. Wei, Y . Li, H. Shen, F. Chen, M. Kleinsteuber, and Z. Wang, “Dynamical textures modeling via joint video dictionary learning,”IEEE Trans. Image Process., vol. 26, no. 6, pp. 2929–2943, 2017

    work page 2017

  16. [16]

    Clustering dynamic textures with the hierarchical EM algorithm for modeling video,

    A. Mumtaz, E. Coviello, G. R. Lanckriet, and A. B. Chan, “Clustering dynamic textures with the hierarchical EM algorithm for modeling video,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 7, pp. 1606–1621, 2012

    work page 2012

  17. [17]

    Dynamic texture classification based on bag-of-models with mixture of student’s t-hidden Markov models,

    Z. Xing, Y . Qiao, Y . Zhao, and W. Liu, “Dynamic texture classification based on bag-of-models with mixture of student’s t-hidden Markov models,”Comput. Vis. Image Understanding, p. 103653, 2023

    work page 2023

  18. [18]

    Classifying dynamic textures via spatiotemporal fractal analysis,

    Y . Xu, Y . Quan, Z. Zhang, H. Ling, and H. Ji, “Classifying dynamic textures via spatiotemporal fractal analysis,”Pattern Recognit., vol. 48, no. 10, pp. 3239–3248, 2015

    work page 2015

  19. [19]

    Spatiotemporal lacunarity spectrum for dynamic texture classification,

    Y . Quan, Y . Sun, and Y . Xu, “Spatiotemporal lacunarity spectrum for dynamic texture classification,”Comput. Vis. Image Understanding, vol. 165, pp. 85–96, 2017

    work page 2017

  20. [20]

    Dynamic texture recognition using multiscale binarized statistical image features,

    S. Arashloo and J. Kittler, “Dynamic texture recognition using multiscale binarized statistical image features,”IEEE Trans. Multimedia, vol. 16, no. 8, pp. 2099–2109, 2014

    work page 2099

  21. [21]

    Rubik gaussian-based patterns for dynamic texture classification,

    T. T. Nguyen, T. P. Nguyen, and F. Bouchara, “Rubik gaussian-based patterns for dynamic texture classification,”Pattern Recognition Letters, vol. 135, pp. 180–187, 2020

    work page 2020

  22. [22]

    Momental directional patterns for dynamic texture recognition,

    T. T. Nguyen, T. P. Nguyen, F. Bouchara, and X. S. Nguyen, “Momental directional patterns for dynamic texture recognition,”Comput. Vis. Image Understanding, vol. 194, p. 102882, 2020

    work page 2020

  23. [23]

    Dynamic texture classification using directional binarized random fea- tures,

    X. Zhao, F. Xu, Y . Ma, Z. Liu, M. Deng, U. S. Khan, and Z. Xiong, “Dynamic texture classification using directional binarized random fea- tures,”IEEE Access, vol. 11, pp. 55 895–55 910, 2023

    work page 2023

  24. [24]

    Convolutional neural network on three orthogonal planes for dynamic texture classification,

    V . Andrearczyk and P. F. Whelan, “Convolutional neural network on three orthogonal planes for dynamic texture classification,”Pattern Recognit., vol. 76, pp. 36–49, 2018

    work page 2018

  25. [25]

    Geometry guided convolutional neural networks for self-supervised video representation learning,

    C. Gan, B. Gong, K. Liu, H. Su, and L. J. Guibas, “Geometry guided convolutional neural networks for self-supervised video representation learning,” inIEEE Conf. Comput. Vis. Pattern Recog., 2018, pp. 5589– 5597

    work page 2018

  26. [26]

    A spatiotemporal oriented energy network for dynamic texture recognition,

    I. Hadji and R. P. Wildes, “A spatiotemporal oriented energy network for dynamic texture recognition,” inInt. Conf. Comput. Vis., 2017, pp. 3066–3074

    work page 2017

  27. [27]

    Self-supervised video representation learning by uncovering spatio-temporal statistics,

    J. Wang, J. Jiao, L. Bao, S. He, W. Liu, and Y .-H. Liu, “Self-supervised video representation learning by uncovering spatio-temporal statistics,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 7, pp. 3791–3806, 2022

    work page 2022

  28. [28]

    Dynamic texture recognition via orthogonal tensor dictionary learning,

    Y . Quan, Y . Huang, and H. Ji, “Dynamic texture recognition via orthogonal tensor dictionary learning,” inInt. Conf. Comput. Vis., 2015, pp. 73–81

    work page 2015

  29. [29]

    Equiangular kernel dictionary learning with applications to dynamic texture analysis,

    Y . Quan, C. Bao, and H. Ji, “Equiangular kernel dictionary learning with applications to dynamic texture analysis,” inIEEE Conf. Comput. Vis. Pattern Recog., 2016, pp. 308–316

    work page 2016

  30. [30]

    Randomized neural network based signature for dynamic texture classification,

    J. J. d. M. S. Junior, L. C. Ribas, and O. M. Bruno, “Randomized neural network based signature for dynamic texture classification,”Expert Syst. Appl., vol. 135, pp. 194–200, 2019

    work page 2019

  31. [31]

    Dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern,

    R. Ding, J. Ren, H. Yu, and J. Li, “Dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern,” inIEEE Int. Conf. Acoust. Speech Signal Process., 2022, pp. 1840–1844

    work page 2022

  32. [32]

    Dynamic texture recognition using local binary patterns with an application to facial expressions,

    G. Zhao and M. Pietikainen, “Dynamic texture recognition using local binary patterns with an application to facial expressions,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 6, pp. 915–928, 2007

    work page 2007

  33. [33]

    Noise-resistant local binary pattern with an embedded error-correction mechanism,

    J. Ren, X. Jiang, and J. Yuan, “Noise-resistant local binary pattern with an embedded error-correction mechanism,”IEEE Trans. Image Process., vol. 22, no. 10, pp. 4049–4060, 2013

    work page 2013

  34. [34]

    Learning compact binary face descriptor for face recognition,

    J. Lu, V . E. Liong, X. Zhou, and J. Zhou, “Learning compact binary face descriptor for face recognition,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 10, pp. 2041–2056, 2015

    work page 2041

  35. [35]

    LBP encoding schemes jointly utilizing the information of current bit and other LBP bits,

    J. Ren, X. Jiang, and J. Yuan, “LBP encoding schemes jointly utilizing the information of current bit and other LBP bits,”IEEE Signal Process. Lett., vol. 22, no. 12, pp. 2373–2377, 2015

    work page 2015

  36. [36]

    Context-aware local binary feature learning for face recognition,

    Y . Duan, J. Lu, J. Feng, and J. Zhou, “Context-aware local binary feature learning for face recognition,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 5, pp. 1139–1153, 2018

    work page 2018

  37. [37]

    Learning LBP structure by maximizing the conditional mutual information,

    J. Ren, X. Jiang, and J. Yuan, “Learning LBP structure by maximizing the conditional mutual information,”Pattern Recognit., vol. 48, no. 10, pp. 3180–3190, 2015

    work page 2015

  38. [38]

    Dynamic texture recognition based on com- pleted volume local binary pattern,

    D. Tiwari and V . Tyagi, “Dynamic texture recognition based on com- pleted volume local binary pattern,”Multidimensional Syst. Signal Process., vol. 27, no. 2, pp. 563–575, 2016

    work page 2016

  39. [39]

    Sound-event classification using robust texture features for robot hearing,

    J. Ren, X. Jiang, J. Yuan, and N. Magnenat-Thalmann, “Sound-event classification using robust texture features for robot hearing,”IEEE Trans. Multimedia, vol. 19, no. 3, pp. 447–458, 2017

    work page 2017

  40. [40]

    Toward optimal manifold hashing via discrete locally linear embedding,

    R. Ji, H. Liu, L. Cao, D. Liu, Y . Wu, and F. Huang, “Toward optimal manifold hashing via discrete locally linear embedding,”IEEE Trans. Image Process., vol. 26, no. 11, pp. 5411–5420, 2017

    work page 2017

  41. [41]

    Spatiotemporal directional number transi- tional graph for dynamic texture recognition,

    A. R. Rivera and O. Chae, “Spatiotemporal directional number transi- tional graph for dynamic texture recognition,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 10, pp. 2146–2152, 2015

    work page 2015

  42. [42]

    Dynamic scene classification: Learning motion descriptors with slow features analysis,

    C. Th ´eriault, N. Thome, and M. Cord, “Dynamic scene classification: Learning motion descriptors with slow features analysis,” inIEEE Conf. Comput. Vis. Pattern Recog., 2013, pp. 2603–2610

    work page 2013

  43. [43]

    Dynamic texture recognition using enhanced LBP features,

    J. Ren, X. Jiang, and J. Yuan, “Dynamic texture recognition using enhanced LBP features,” inIEEE Int. Conf. Acoust. Speech Signal Process., 2013, pp. 2400–2404

    work page 2013

  44. [44]

    Unsupervised learning of visual representations using videos,

    X. Wang and A. Gupta, “Unsupervised learning of visual representations using videos,” inInt. Conf. Comput. Vis., 2015, pp. 2794–2802

    work page 2015

  45. [45]

    Shuffle and learn: unsupervised learning using temporal order verification,

    I. Misra, C. L. Zitnick, and M. Hebert, “Shuffle and learn: unsupervised learning using temporal order verification,” inEur . Conf. Comput. Vis., 2016, pp. 527–544

    work page 2016

  46. [46]

    Sponta- neous facial micro-expression analysis using spatiotemporal completed local quantized patterns,

    X. Huang, G. Zhao, X. Hong, W. Zheng, and M. Pietik ¨ainen, “Sponta- neous facial micro-expression analysis using spatiotemporal completed local quantized patterns,”Neurocomputing, vol. 175, pp. 564–578, 2016

    work page 2016

  47. [47]

    Blind quality evaluator of light field images by group-based representations and multiple plane-oriented perceptual characteristics,

    X. Chai, F. Shao, Q. Jiang, X. Wang, L. Xu, and Y .-S. Ho, “Blind quality evaluator of light field images by group-based representations and multiple plane-oriented perceptual characteristics,”IEEE Trans. Multimedia, vol. 26, pp. 607–622, 2024

    work page 2024

  48. [48]

    Color texture description with novel local binary patterns for effective image retrieval,

    C. Singh, E. Walia, and K. P. Kaur, “Color texture description with novel local binary patterns for effective image retrieval,”Pattern Recognit., vol. 76, pp. 50–68, 2018

    work page 2018

  49. [49]

    Multi-level fusion in ultrasound for cancer detection based on uniform LBP features,

    D. Q. Zeebaree, A. M. Abdulazeez, D. A. Zebari, H. Haron, and H. N. A. Hamed, “Multi-level fusion in ultrasound for cancer detection based on uniform LBP features,”Comput. Mater . Contin., vol. 66, no. 3, pp. 3363– 3382, 2021

    work page 2021

  50. [50]

    Local binary pattern- based hyperspectral image classification with superpixel guidance,

    S. Jia, B. Deng, J. Zhu, X. Jia, and Q. Li, “Local binary pattern- based hyperspectral image classification with superpixel guidance,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 2, pp. 749–759, 2017

    work page 2017

  51. [51]

    LBP-structure optimization with symme- try and uniformity regularizations for scene classification,

    J. Ren, X. Jiang, and J. Yuan, “LBP-structure optimization with symme- try and uniformity regularizations for scene classification,”IEEE Signal Process. Lett., vol. 24, no. 1, pp. 37–41, 2017

    work page 2017

  52. [52]

    Optimizing LBP structure for visual recognition using binary quadratic programming,

    J. Ren, X. Jiang, J. Yuan, and G. Wang, “Optimizing LBP structure for visual recognition using binary quadratic programming,”IEEE Signal Process. Lett., vol. 21, no. 11, pp. 1346–1350, 2014

    work page 2014

  53. [53]

    A chi-squared-transformed subspace of LBP histogram for visual recognition,

    J. Ren, X. Jiang, and J. Yuan, “A chi-squared-transformed subspace of LBP histogram for visual recognition,”IEEE Trans. Image Process., vol. 24, no. 6, pp. 1893–1904, 2015

    work page 1904

  54. [54]

    Facial expression recognition based on improved local binary pattern and class-regularized locality preserving projection,

    W.-L. Chao, J.-J. Ding, and J.-Z. Liu, “Facial expression recognition based on improved local binary pattern and class-regularized locality preserving projection,”Signal Process., vol. 117, pp. 1–10, 2015

    work page 2015

  55. [55]

    Group- constrained manifold learning: Application to AD risk assessment,

    R. Guerrero, C. Ledig, A. Schmidt-Richberg, and D. Rueckert, “Group- constrained manifold learning: Application to AD risk assessment,” Pattern Recognit., vol. 63, pp. 570–582, 2017

    work page 2017

  56. [56]

    Joint feature learning for face recognition,

    J. Lu, V . E. Liong, G. Wang, and P. Moulin, “Joint feature learning for face recognition,”IEEE Trans. Inf. F orensics Security, vol. 10, no. 7, pp. 1371–1383, 2015

    work page 2015

  57. [57]

    Learning deep binary descriptors via bitwise interaction mining,

    Z. Wang, H. Xiao, Y . Duan, J. Zhou, and J. Lu, “Learning deep binary descriptors via bitwise interaction mining,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 2, pp. 1919–1933, 2023. IEEE TRANSACTIONS ON IMAGE PROCESSING 12

    work page 1919

  58. [58]

    A prob- abilistic code balance constraint with compactness and informativeness enhancement for deep supervised hashing,

    Q. Zhang, L. Hu, L. Cao, C. Shi, S. Wang, and D. D. Liu, “A prob- abilistic code balance constraint with compactness and informativeness enhancement for deep supervised hashing,” inProc. 31st Int. Joint Conf. Artif. Intell. (IJCAI), 2022

    work page 2022

  59. [59]

    A survey on learning to hash,

    J. Wang, T. Zhang, N. Sebe, H. T. Shenet al., “A survey on learning to hash,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 769–790, 2017

    work page 2017

  60. [60]

    Learning canonical embeddings for unsupervised shape correspondence with locally linear transformations,

    P. He, P. Emami, S. Ranka, and A. Rangarajan, “Learning canonical embeddings for unsupervised shape correspondence with locally linear transformations,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 12, pp. 14 872–14 887, 2023

    work page 2023

  61. [61]

    Self-weighted unsupervised LDA,

    X. Li, Y . Zhang, and R. Zhang, “Self-weighted unsupervised LDA,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 3, pp. 1627–1632, 2023

    work page 2023

  62. [62]

    New vector transport operators extending a Riemannian CG algorithm to generalized Stiefel manifold with low-rank applications,

    X. Wang, K. Deng, Z. Peng, and C. Yan, “New vector transport operators extending a Riemannian CG algorithm to generalized Stiefel manifold with low-rank applications,”J. Comput. Appl. Math., vol. 451, p. 116024, 2024

    work page 2024

  63. [63]

    Riemannian hamiltonian methods for min-max optimization on manifolds,

    A. Han, B. Mishra, P. Jawanpuria, P. Kumar, and J. Gao, “Riemannian hamiltonian methods for min-max optimization on manifolds,”SIAM Journal on Optimization, vol. 33, no. 3, pp. 1797–1827, 2023

    work page 2023

  64. [64]

    Efficient and robust approxi- mate nearest neighbor search using hierarchical navigable small world graphs,

    Y . A. Malkov and D. A. Yashunin, “Efficient and robust approxi- mate nearest neighbor search using hierarchical navigable small world graphs,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 4, pp. 824–836, 2020

    work page 2020

  65. [65]

    2D-LCoLBP: A learning two-dimensional co-occurrence local binary pattern for image recognition,

    X. Bi, Y . Yuan, B. Xiao, W. Li, and X. Gao, “2D-LCoLBP: A learning two-dimensional co-occurrence local binary pattern for image recognition,”IEEE Trans. Image Process., vol. 30, pp. 7228–7240, 2021

    work page 2021

  66. [66]

    Maximum margin distance learning for dynamic texture recognition,

    B. Ghanem and N. Ahuja, “Maximum margin distance learning for dynamic texture recognition,” inEur . Conf. Comput. Vis., 2010, pp. 223– 236

    work page 2010

  67. [67]

    Dynamic textures,

    G. Doretto, A. Chiuso, Y . Wu, and S. Soatto, “Dynamic textures,”Int. J. Comput. Vis., vol. 51, pp. 91–109, 02 2003

    work page 2003

  68. [68]

    Identifying pareto fronts reliably using a multistage reference-vector- based framework,

    K. Deb, C. L. d. V . Lopes, F. V . C. Martins, and E. F. Wanner, “Identifying pareto fronts reliably using a multistage reference-vector- based framework,”IEEE Trans. Evol. Comput., vol. 28, no. 1, pp. 252– 266, 2024. Ruxin Dingreceived her B.Sc. degree in computer science from the University of Nottingham Ningbo China in 2021. She is currently pursuing a...

    work page 2024