pith. sign in

arxiv: 2606.13030 · v1 · pith:4EHLMJXPnew · submitted 2026-06-11 · 💻 cs.CV

A Multi-Modal Framework with Cross-Subject Pseudo-Labeling and Semantic Alignment for Micro-Gesture Recognition

Haoran Zhang , Haokun Zhang , Pengyu Liu , Yujia Zhang , Weibao Xue , Yanbin Hao This is my paper

Pith reviewed 2026-06-27 07:41 UTC · model grok-4.3

classification 💻 cs.CV
keywords micro-gesture recognitionmulti-modal frameworkunsupervised domain adaptationpseudo-labelingcross-subject evaluationlong-tailed distributionvideo gesture analysis
0
0 comments X

The pith

Cross-modal pseudo-labeling improves single-modal robustness for micro-gesture recognition across subjects.

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

The paper builds a multi-modal pipeline that extracts skeleton joints, 3D heatmaps, and RGB features from untrimmed videos to detect subtle spontaneous gestures. It adds a square-root weighting scheme and an orthogonal semantic embedding loss to keep rare gesture classes from being ignored. The central step is a cross-modal pseudo-labeling method that transfers information between modalities to adapt the model when the same gestures appear on new people. This produces a 68.13 percent F1-score on the challenge test set. A reader would care because reliable detection of these low-signal movements could support emotion-aware interfaces without needing new labels for every user.

Core claim

The authors combine saliency-guided multi-modal feature extraction with square-root smoothed class weighting and an orthogonal semantic embedding loss, then apply a cross-modal pseudo-labeling strategy for unsupervised domain adaptation that generates pseudo-labels across modalities to strengthen single-modal models under cross-subject shifts, followed by temperature-scaled soft-voting fusion, reaching 68.13 percent F1-score.

What carries the argument

Cross-Modal Pseudo-Labeling (CMPL) strategy, which generates and refines pseudo-labels by exchanging information across skeleton, heatmap, and RGB streams to close the domain gap in unsupervised adaptation.

If this is right

  • Single-modal branches gain robustness when trained with labels transferred from other modalities.
  • The square-root weighting and orthogonal loss together maintain tail-class accuracy without lowering head-class scores.
  • Temperature scaling during late fusion reduces overconfident errors in the final prediction.
  • The saliency-guided extraction supplies complementary fine-grained cues that survive domain shifts.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same cross-modal labeling pattern could transfer to other video tasks that face subject-specific domain gaps and scarce labels.
  • If the pseudo-labels prove reliable, the method reduces dependence on subject-specific annotations for deployment.
  • Applying the approach to datasets with even lower motion contrast would test whether the accuracy assumption holds outside the challenge setting.

Load-bearing premise

Pseudo-labels produced by combining signals from different modalities stay accurate enough to raise rather than lower performance when class distributions are long-tailed and signal-to-noise ratios are low.

What would settle it

Run the framework with CMPL disabled and record the drop in F1-score on the same cross-subject test set; if the drop is small or negative while pseudo-label accuracy on a validation split falls below 60 percent, the adaptation benefit disappears.

Figures

Figures reproduced from arXiv: 2606.13030 by Haokun Zhang, Haoran Zhang, Pengyu Liu, Weibao Xue, Yanbin Hao, Yujia Zhang.

Figure 1
Figure 1. Figure 1: The overall architecture of our proposed framework. First, raw RGB vol￾umes and 68-keypoint skeletons are fed into four parallel branches (Swin3D, R(2+1)D, PoseC3D, and Decoupled ST-CNN) for multi-modal spatio-temporal modeling. Second, the generated logits are calibrated and aggregated via a Temperature-Scaled Fusion (σ(z/T)) to mitigate individual model overconfidence. Finally, an iterative pseudo￾labeli… view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of the extreme long-tailed class distribution in the iMiGUE dataset. The severe imbalance ratio (> 2000 : 1) often leads to catastrophic mode collapse if traditional aggressive re-sampling techniques are applied. By performing a single round of retraining from scratch on this super-dataset, the models implicitly learn the idiosyncratic behavioral nuances and fine-grained micro-action patterns … view at source ↗
Figure 3
Figure 3. Figure 3: A conceptual diagram illustrating the Orthogonal Semantic Embedding Loss. This mechanism explicitly pulls ambiguous visual features toward their respective fixed orthogonal anchors, effectively preventing minority tail classes from being swallowed by dominant majority head classes within the latent feature space. 4 Experiments 4.1 Dataset and Evaluation Metric The iMiGUE dataset [41] is collected to evalua… view at source ↗
read the original abstract

Micro-gestures (MGs) are spontaneous and subtle body movements that frequently convey hidden human emotions. Recognizing MGs in untrimmed videos remains highly challenging due to their extremely low signal-to-noise ratio, severe long-tailed class distribution, and the inherent domain shift encountered in cross-subject evaluation scenarios. In this paper, we propose a comprehensive multi-modal framework for Track 1 of the 4th MiGA-IJCAI Challenge. To capture fine-grained representations, we design a saliency-guided multi-modal extraction pipeline integrating 68-keypoint skeleton joint coordinates, 3D heatmap volumes, and high-resolution RGB visual features. We introduce a gentle square-root smoothed weighting mechanism paired with an Orthogonal Semantic Embedding Loss to protect tail classes without compromising overall recognition capabilities. More importantly, to bridge the cross-subject generalization gap, we propose a Cross-Modal Pseudo-Labeling (CMPL) strategy for unsupervised domain adaptation, which significantly boosts single-modal robustness. A temperature-scaled soft-voting mechanism is finally utilized to alleviate overconfidence during late fusion. Extensive experiments demonstrate that our framework achieves a competitive F1-score of 68.13\%, securing the 4th place.

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.

Referee Report

2 major / 0 minor

Summary. The paper proposes a multi-modal framework for micro-gesture recognition on Track 1 of the 4th MiGA-IJCAI Challenge. It combines a saliency-guided extraction pipeline across skeleton joints, 3D heatmaps, and RGB features; a square-root smoothed weighting scheme with an Orthogonal Semantic Embedding Loss for tail-class protection; a Cross-Modal Pseudo-Labeling (CMPL) strategy for unsupervised cross-subject domain adaptation; and temperature-scaled soft-voting for late fusion. The framework reports a test-set F1-score of 68.13%, placing 4th.

Significance. If the reported ranking holds and the individual components can be shown to contribute measurably, the work supplies a practical engineering solution for low-SNR, long-tailed, cross-subject micro-gesture recognition. The competition result itself constitutes reproducible empirical evidence on an external test set; the CMPL component, if validated, would address a recognized difficulty in multi-modal domain adaptation for subtle actions.

major comments (2)
  1. [Abstract / CMPL strategy description] The central claim that CMPL 'significantly boosts single-modal robustness' (abstract) is load-bearing yet unsupported: the manuscript provides neither an ablation isolating CMPL from saliency-guided extraction and late-fusion voting, nor any quantitative measure of pseudo-label noise or error amplification under the stated long-tailed, low-SNR regime.
  2. [Experiments section] No baseline comparisons, ablation tables, or statistical significance tests are referenced for the 68.13% F1-score, so the contribution of the square-root weighting, Orthogonal Semantic Embedding Loss, or temperature scaling cannot be verified relative to simpler multi-modal fusion.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and will strengthen the empirical sections accordingly.

read point-by-point responses

  1. Referee: [Abstract / CMPL strategy description] The central claim that CMPL 'significantly boosts single-modal robustness' (abstract) is load-bearing yet unsupported: the manuscript provides neither an ablation isolating CMPL from saliency-guided extraction and late-fusion voting, nor any quantitative measure of pseudo-label noise or error amplification under the stated long-tailed, low-SNR regime.

    Authors: We agree the abstract claim requires direct support. The revised manuscript will add an ablation isolating CMPL (with and without it, on single-modal streams) and report pseudo-label accuracy plus error rates on a held-out validation split under the long-tailed regime. revision: yes

  2. Referee: [Experiments section] No baseline comparisons, ablation tables, or statistical significance tests are referenced for the 68.13% F1-score, so the contribution of the square-root weighting, Orthogonal Semantic Embedding Loss, or temperature scaling cannot be verified relative to simpler multi-modal fusion.

    Authors: We concur that component contributions need explicit verification. The revision will include ablation tables for square-root weighting, Orthogonal Semantic Embedding Loss, and temperature scaling, plus comparisons to standard multi-modal fusion baselines, with results from multiple runs and statistical significance tests. revision: yes

Circularity Check

0 steps flagged

No circularity: results measured on external challenge test set with no internal equations or self-citations reducing claims to fitted inputs

full rationale

The paper describes a multi-modal pipeline (saliency-guided extraction, square-root weighting, Orthogonal Semantic Embedding Loss, CMPL for UDA, temperature-scaled voting) and reports an F1-score of 68.13% on the MiGA-IJCAI Challenge test set. No equations are presented that define a quantity in terms of itself or rename a fitted parameter as a prediction. No self-citation chains or uniqueness theorems are invoked to justify core components. The evaluation is external and falsifiable, making the derivation self-contained against the provided benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only review; no explicit free parameters, invented entities, or non-standard axioms are stated. The CMPL strategy implicitly assumes that cross-modal agreement produces reliable pseudo-labels.

axioms (1)
  • domain assumption Cross-modal pseudo-labels generated from multiple modalities can be trusted to adapt models across subjects without introducing harmful label noise.
    Invoked when describing the CMPL strategy for unsupervised domain adaptation.

pith-pipeline@v0.9.1-grok · 5761 in / 1333 out tokens · 27957 ms · 2026-06-27T07:41:58.161460+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

52 extracted references · 7 canonical work pages

  1. [1]

    Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning. pp. 813–

  2. [2]

    In: Advances in neural information pro- cessing systems

    Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in neural information pro- cessing systems. vol. 32 (2019)

    2019

  3. [3]

    IEEE Transactions on Pattern Analysis and Machine Intelligence43(1), 172–186 (2019)

    Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi- person 2d pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence43(1), 172–186 (2019)

    2019

  4. [4]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

    Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the Kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6299–6308 (2017)

    2017

  5. [5]

    arXiv preprint arXiv:2408.03097 (2024)

    Chen, G., Wang, F., Li, K., Wu, Z., Fan, H., Yang, Y., Wang, M., Guo, D.: Pro- totype learning for micro-gesture classification. arXiv preprint arXiv:2408.03097 (2024)

    work page arXiv 2024

  6. [6]

    International Journal of Computer Vision131(5), 1346–1366 (2023)

    Chen, H., Shi, H., Liu, X., Li, X., Zhao, G.: SMG: A micro-gesture dataset to- wards spontaneous body gestures for emotional stress state analysis. International Journal of Computer Vision131(5), 1346–1366 (2023)

    2023

  7. [7]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13359–13368 (2021)

    2021

  8. [8]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Cheng, K., Zhang, Y., He, X., Chen, W., Cheng, J., Lu, H.: Skeleton-based ac- tion recognition with shift graph convolutional network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 183– 192 (2020)

    2020

  9. [9]

    In: Proceedings of the IEEE/CVF conference on com- puter vision and pattern recognition

    Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE/CVF conference on com- puter vision and pattern recognition. pp. 9268–9277 (2019)

    2019

  10. [10]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2969–2978 (2022)

    2022

  11. [11]

    Psychiatry 32(1), 88–106 (1969) 12 H

    Ekman, P., Friesen, W.V.: Nonverbal leakage and clues to deception. Psychiatry 32(1), 88–106 (1969) 12 H. Zhanget al

    1969

  12. [12]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recog- nition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 6202–6211 (2019)

    2019

  13. [13]

    In: Pro- ceedings of the European Conference on Computer Vision Workshops

    Filntisis, P.P., Efthymiou, N., Potamianos, G., Maragos, P.: Emotion understand- ing in videos through body, context, and visual-semantic embedding loss. In: Pro- ceedings of the European Conference on Computer Vision Workshops. pp. 747–755. Springer (2020)

    2020

  14. [14]

    The Journal of Machine Learning Research17(1), 2096–2030 (2016)

    Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. The Journal of Machine Learning Research17(1), 2096–2030 (2016)

    2096

  15. [15]

    In: Proceedings of the 33rd ACM International Conference on Multimedia

    Gu, J., Li, K., Wang, F., Wei, Y., Wu, Z., Fan, H., Wang, M.: Motion matters: Motion-guided modulation network for skeleton-based micro-action recognition. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 5461–5470 (2025)

    2025

  16. [16]

    arXiv preprint arXiv:2507.08344 (2025)

    Gu, J., Wang, F., Li, K., Wei, Y., Wu, Z., Guo, D.: MM-gesture: towards precise micro-gesture recognition through multimodal fusion. arXiv preprint arXiv:2507.08344 (2025)

    work page arXiv 2025

  17. [17]

    In: International Conference on Machine Learning

    Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neu- ral networks. In: International Conference on Machine Learning. pp. 1321–1330. PMLR (2017)

    2017

  18. [18]

    IEEE Transactions on Circuits and Systems for Video Technology34(7), 6238–6252 (2024)

    Guo, D., Li, K., Hu, B., Zhang, Y., Wang, M.: Benchmarking micro-action recog- nition: Dataset, methods, and applications. IEEE Transactions on Circuits and Systems for Video Technology34(7), 6238–6252 (2024)

    2024

  19. [19]

    In: Proceedings of the 32nd ACM International Conference on Multimedia

    Guo, D., Li, X., Li, K., Chen, H., Hu, J., Zhao, G., Yang, Y., Wang, M.: MAC 2024: Micro-action analysis grand challenge. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 11304–11305 (2024)

    2024

  20. [20]

    IEEE Transactions on Circuits and Systems for Video Technology32(10), 7120–7132 (2022)

    Hao, Y., Wang, S., Cao, P., Gao, X., Xu, T., Wu, J., He, X.: Attention in attention: Modeling context correlation for efficient video classification. IEEE Transactions on Circuits and Systems for Video Technology32(10), 7120–7132 (2022)

    2022

  21. [21]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Hao, Y., Zhang, H., Ngo, C.W., He, X.: Group contextualization for video recog- nition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 928–938 (2022)

    2022

  22. [22]

    In: Proceedings of the MiGA Workshop at IJCAI (2025)

    Hu, X., Pu, C., Li, Y., Xie, K., Qiguang, M.: Enhancing micro-gesture classification via global-aware importance estimation in vision transformer. In: Proceedings of the MiGA Workshop at IJCAI (2025)

    2025

  23. [23]

    In: Proceedings of the MiGA Workshop at IJCAI (2023)

    Huang, H., Guo, X., Peng, W., Xia, Z.: Micro-gesture classification based on ensem- ble hypergraph convolution transformer. In: Proceedings of the MiGA Workshop at IJCAI (2023)

    2023

  24. [24]

    In: Proceedings of the MiGA Workshop at IJCAI (2024)

    Huang, H., Wang, Y., Kerui, L., Xia, Z.: Multi-modal micro-gesture classifica- tion via multiscale heterogeneous ensemble network. In: Proceedings of the MiGA Workshop at IJCAI (2024)

    2024

  25. [25]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Joze, H.R.V., Shaban, A., Iuzzolino, M.L., Koishida, K.: MMTM: Multimodal transfer module for CNN fusion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13289–13299 (2020)

    2020

  26. [26]

    In: International Conference on Learning Representations (2020)

    Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., Kalantidis, Y.: De- coupling representation and classifier for long-tailed recognition. In: International Conference on Learning Representations (2020)

    2020

  27. [27]

    In: Workshop on Challenges in Representation Learning, ICML

    Lee, D.H.: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML. vol. 3, p. 896 (2013) Multi-Modal Framework for Micro-Gesture Recognition 13

    2013

  28. [28]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Lee, J., Lee, M., Lee, D., Lee, S.: Hierarchically decoupled graph convolutional network for skeleton-based action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 10444–10453 (2023)

    2023

  29. [29]

    In: International Conference on Machine Learning

    Li, J., Qiu, R., Chen, S., et al.: Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International Conference on Machine Learning. pp. 6028–6039. PMLR (2020)

    2020

  30. [30]

    arXiv preprint arXiv:2603.26586 (2026)

    Li, K., Gu, J., Wang, F., Wu, Z., Fan, H., Guo, D.: MA-Bench: Towards fine-grained micro-action understanding. arXiv preprint arXiv:2603.26586 (2026)

    work page arXiv 2026

  31. [31]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Li, K., Guo, D., Chen, G., Fan, C., Xu, J., Wu, Z., Fan, H., Wang, M.: Prototypical calibrating ambiguous samples for micro-action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 4815–4823 (2025)

    2025

  32. [32]

    In: Proceedings of the 31st ACM International Conference on Multimedia

    Li, K., Guo, D., Chen, G., Liu, F., Wang, M.: Data augmentation for human behavior analysis in multi-person conversations. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 9516–9520 (2023)

    2023

  33. [33]

    arXiv preprint arXiv:2307.10624 (2023)

    Li, K., Guo, D., Chen, G., Peng, X., Wang, M.: Joint skeletal and semantic embed- ding loss for micro-gesture classification. arXiv preprint arXiv:2307.10624 (2023)

    work page arXiv 2023

  34. [34]

    In: Proceedings of the 33rd ACM International Conference on Multimedia

    Li, K., Guo, D., Li, X., Chen, H., Liu, P., Wang, F., Hu, J., Zhao, G., Wang, M.: MAC 2025: The 2nd micro-action analysis grand challenge. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 14216–14221 (2025)

    2025

  35. [35]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Li, K., Liu, P., Guo, D., Wang, F., Wu, Z., Fan, H., Wang, M.: MMAD: Multi-label micro-action detection in videos. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13225–13236 (2025)

    2025

  36. [36]

    In: International Conference on Learning Representations (2022)

    Li, K., Wang, Y., Gao, P., Song, G., Liu, Y., Li, H., Qiao, Y.: UniFormer: Unifying convolution and self-attention for visual recognition. In: International Conference on Learning Representations (2022)

    2022

  37. [37]

    In: Proceedings of the IEEE International Conference on Computer Vision

    Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll´ ar, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980–2988 (2017)

    2017

  38. [38]

    arXiv preprint arXiv:2503.15978 (2025)

    Liu, P., Dong, G., Guo, D., Li, K., Li, F., Yang, X., Wang, M., Ying, X.: A survey on fMRI-based brain decoding for reconstructing multimodal stimuli. arXiv preprint arXiv:2503.15978 (2025)

    work page arXiv 2025

  39. [39]

    arXiv preprint arXiv:2507.09512 (2025)

    Liu, P., Li, K., Wang, F., Wei, Y., She, J., Guo, D.: Online micro-gesture recog- nition using data augmentation and spatial-temporal attention. arXiv preprint arXiv:2507.09512 (2025)

    work page arXiv 2025

  40. [40]

    arXiv preprint arXiv:2407.04490 (2024)

    Liu, P., Wang, F., Li, K., Chen, G., Wei, Y., Tang, S., Wu, Z., Guo, D.: Micro-gesture online recognition using learnable query points. arXiv preprint arXiv:2407.04490 (2024)

    work page arXiv 2024

  41. [41]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Liu, X., Shi, H., Chen, H., Yu, Z., Li, X., Zhao, G.: iMiGUE: An identity-free video dataset for micro-gesture understanding and emotion analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10631–10642 (2021)

    2021

  42. [42]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video Swin Trans- former. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3202–3211 (2022)

    2022

  43. [43]

    In: International Conference on Learning Representations (2017)

    Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017)

    2017

  44. [44]

    In: International Conference on Learning Representations (2019)

    Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)

    2019

  45. [45]

    In: Chinese 14 H

    Shang, T., Hao, Y., Pei, M., Li, K., Ben, H., Wang, S.: Cross-modal feature en- hancement and contrastive alignment for micro-gesture recognition. In: Chinese 14 H. Zhanget al. Conference on Pattern Recognition and Computer Vision (PRCV). pp. 203–217. Springer (2025)

    2025

  46. [46]

    In: Advances in Neural Information Processing Systems

    Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C., Cubuk, E.D., Kurakin, A., Xie, C.L.: FixMatch: Simplifying semi-supervised learning with con- sistency and confidence. In: Advances in Neural Information Processing Systems. vol. 33, pp. 596–608 (2020)

    2020

  47. [47]

    In: Advances in Neural Information Processing Systems

    Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems. vol. 35, pp. 10078–10093 (2022)

    2022

  48. [48]

    In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

    Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6450–6459 (2018)

    2018

  49. [49]

    In: Proceedings of the MiGA Workshop at IJCAI (2025)

    Xu, H., Cheng, L., Wang, Y., Tang, S., Zhong, Z.: Towards fine-grained emotion understanding via skeleton-based micro-gesture recognition. In: Proceedings of the MiGA Workshop at IJCAI (2025)

    2025

  50. [50]

    In: Proceedings of the AAAI Conference on Ar- tificial Intelligence

    Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Ar- tificial Intelligence. vol. 32 (2018)

    2018

  51. [51]

    PloS one9(1), e86041 (2014)

    Yan, W.J., Li, X., Wang, S.J., Zhao, G., Liu, Y.J., Chen, Y.H., Xia, X.: CASME II: A database for spontaneous macro-expression and micro-expression spotting and recognition. PloS one9(1), e86041 (2014)

    2014

  52. [52]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhou, B., Cui, Q., Wei, X.S., Chen, Z.M.: BBN: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9719– 9728 (2020)

    2020