Scopus

Few-Shot Video Classification via Mutual Learning

Năm XB 2026 Tạp chí / Hội thảo Computational Intelligence in Engineering Science (ICCIES 2026) DOI / Link https://doi.org/10.1007/978-3-032-21625-0_39 ↗

Tác giả

Trung-Nghia Phung ^✉ ; Duc-Quang Vu ^✉

Tóm tắt

Video classification is a key task for organizing the massive volume of video data generated today. However, few-shot video classification, where only a small number of labeled examples are available, remains highly challenging. Most recent methods rely mainly on internal similarity or contrastive scores within a single network, which limits their ability to learn robust and generalizable representations. We propose a mutual-learning-based few-shot video classification approach, in which multiple networks are trained on the same task and encouraged to learn from each other's predictions. Concretely, the preceding network (i.e., the best-performing model from previous epochs) is used to extract spatio-temporal features from both query and support videos, and to compute an external similarity score with the current network. This stabilizes training, allows the present network to inherit the strengths of earlier models, and reduces overfitting. Experiments on benchmark datasets UCF-101, HMDB-51, and Kinetics show that our method significantly outperforms state-of-the-art few-shot video classification approaches. Ablation studies further confirm the contribution of the mutual learning mechanism. Our work advances the development of more efficient and accurate video classification systems for large-scale video data.

Tài liệu tham khảo

[1] Cao, C., Li, Y., Lv, Q., Wang, P., Zhang, Y.: Few-shot action recognition with implicit temporal alignment and pair similarity optimization. Comput. Vis. Image Underst. 210, 103250 (2021)

[2] Cao, K., Ji, J., Cao, Z., Chang, C.Y., Niebles, J.C.: Few-shot video classification via temporal alignment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10618–10627 (2020)

[3] Dang, V.H., Nguyen, M.T., Le, N.H., Nguyen, T.P., Tran, Q.V., Mai, T.H., Vy, V.P.T., Hung, T.N.K., Lee, C.Y., Tseng, C.L., Le, N.Q.K., Nguyen, P.A.: Exploration of 3d few-shot learning techniques for classification of knee joint injuries on mr images. Diagnostics 15(14) (2025)

[4] Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)

[5] Gao, Z., Tan, C., Wu, L., Li, S.Z.: Simvp: Simpler yet better video prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3170–3180 (2022)

[6] Hsieh, J.T., Liu, B., Huang, D.A., Fei-Fei, L.F., Niebles, J.C.: Learning to decompose and disentangle representations for video prediction. Adv. Neural Inform. Process. Syst. 31 (2018)

[7] Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et al.: The Kinetics Human Action Video Dataset. arXiv preprint arXiv:1705.06950 (2017)

[8] Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556–2563. IEEE (2011)

[9] Kumar Dwivedi, S., Gupta, V., Mitra, R., Ahmed, S., Jain, A.: Protogan: Towards few shot learning for action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 0–0 (2019)

[10] Li, Z., Chen, X., Liu, Y., Sun, M., Zhang, J., Yuan, J.: Few-shot video classification via temporal alignment and refinement. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1612–1621 (2020)

[11] Lichtenstein, M., Sattigeri, P., Feris, R., Giryes, R., Karlinsky, L.: Tafssl: Task-adaptive feature sub-space learning for few-shot classification. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VII, pp. 522–539. Springer (2020)

[12] Lu, S., Ye, H.J., Zhan, D.C.: Few-Shot Action Recognition with Compromised Metric via Optimal Transport. arXiv preprint arXiv:2104.03737 (2021)

[13] Ma, X., Sun, Y., Che, W., Liu, X.: Variational prototyping-encoder: One-shot learning with prototypical prototypes and variational inference. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5707–5716 (2019)

[14] Mai-Tan, H., Pham-Nguyen, H.N., Long, N.X., Minh, Q.T.: Mining urban traffic condition from crowd-sourced data. SN Comput. Sci. 1(4), 225 (2020)

[15] Minh, Q.T., Pham-Nguyen, H.N., Tan, H.M., Long, N.X.: Traffic congestion estimation based on crowd-sourced data. In: 2019 International Conference on Advanced Computing and Applications (ACOMP), pp. 119–126. IEEE (2019)

[16] Nguyen, D.A., Hoang, K.N., Nguyen, N.T., Tran, H.N.: Enhancing indoor robot pedestrian detection using improved pixor backbone and gaussian heatmap regression in 3d lidar point clouds. IEEE Access 12, 9162–9176 (2024)

[17] Nguyen, K.D., Tran, Q.H., Nguyen, K., Hua, B.S., Nguyen, R.: Inductive and transductive few-shot video classification via appearance and temporal alignments. In: Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XX, pp. 471–487. Springer (2022)

[18] Nguyen, T.H., Mai, T.H., Vu, D.Q.: A lightweight transformer-based model for fight recognition. In: Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications, pp. 339–346 (2024)

[19] Pang, Y., Wang, Z., Gao, J., Xie, J., Tian, Q.: Few-shot video classification with attentional similarity. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12438–12447 (2021)

[20] Park, S., Kim, H.: Few-shot video classification with spatio-temporal vae-gan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6466–6475 (2021)

[21] Phung, T., Vu, D.Q., Mai-Tan, H., Nhung, L.T.: Deep models for mispronounce prediction for vietnamese learners of english. In: Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications, pp. 682–689 (2022)

[22] Phung, T., Vu, V.D., Mai, T.H.: A pronunciation practice system based on pre-trained deep learning models. In: Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications, pp. 325–332 (2024)

[23] Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J.B., Larochelle, H., Zemel, R.S.: Meta-learning for semi-supervised few-shot classification. In: International Conference on Learning Representations (2018)

[24] Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: International conference on machine learning, pp. 4488–4497. PMLR (2018)

[25] Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)

[26] Song, Y., Wang, T., Mondal, S.K., Sahoo, J.P.: A Comprehensive Survey of Few-Shot Learning: Evolution, Applications, Challenges, and Opportunities (2022). https://arxiv.org/abs/2205.06743

[27] Soomro, K., Zamir, A.R., Shah, M.: A dataset of 101 human action classes from videos in the wild. Center Res. Comput. Vision 2 (2012)

[28] Sun, Q., Liu, X., Xu, Y., Tao, D.: Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 403–412 (2019)

[29] Tan, H.M., Pham-Nguyen, H.N., Minh, Q.T., Huu, P.N.: Traffic condition estimation based on historical data analysis. In: 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), pp. 256–261. IEEE (2021)

[30] Tan, H.M., Vu, D.Q., Lee, C.T., Li, Y.H., Wang, J.C.: Selective mutual learning: An efficient approach for single channel speech separation. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3678–3682. IEEE (2022)

[31] Tan, S., Yang, R.: Learning similarity: Feature-aligning network for few-shot action recognition. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2019)

[32] Tin, P.T., Nguyen, M.S.V., Bui, Q.A., Imoize, A.L., Kim, B.S.: System modeling and deep learning-based security analysis of uplink noma relay networks with irs and fountain codes. Comput. Model. Eng. Sci. 144, 2521–2543 (2025)

[33] Tran, H.N., Nguyen, N.V., Le, N.Q., Nguyen, N.N., Le, T.A., Nguyen, V.D.: Enhancing semantic scene segmentation for indoor autonomous systems using advanced attention-supported improved unet. SIViP 19(2), 190 (2025)

[34] Wang, X., Zhang, S., Qing, Z., Gao, C., Zhang, Y., Zhao, D., Sang, N.: Molo: Motion-augmented long-short contrastive learning for few-shot action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023)

[35] Wang, Y., Yao, Q., Kwok, J., Ni, L.M.: Generalizing from a Few Examples: A Survey on Few-shot Learning (2020). https://arxiv.org/abs/1904.05046

[36] Wu, R., Feng, M., Guan, W., Wang, D., Lu, H., Ding, E.: A mutual learning method for salient object detection with intertwined multi-supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8150–8159 (2019)

[37] Yang, L., Zhang, W., Lu, J., Zhou, J.: Prototypical networks for few-shot video classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10609–10618 (2021)

[38] Zhang, S., Zhou, J., He, X.: Learning Implicit Temporal Alignment for Few-shot Video Classification. arXiv preprint arXiv:2105.04823 (2021)

[39] Zhang, W., Li, Y., Lu, J., Zhou, J.: Few-shot learning by discriminative representation embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2242–2251 (2019)

[40] Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320–4328 (2018)

[41] Zhu, L., Yang, Y.: Compound memory networks for few-shot video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 751–766 (2018)

[42] Zhu, Z., Wang, L., Guo, S., Wu, G.: A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark. arXiv preprint arXiv:2110.12358 (2021)

← Quay lại danh sách bài báo