{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:01:53Z","timestamp":1764403313576},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11554-023-01374-9","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T07:02:10Z","timestamp":1699254130000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A novel algorithm for human action recognition in compressed domain using attention-guided approach"],"prefix":"10.1007","volume":"20","author":[{"given":"S. M.","family":"Praveenkumar","sequence":"first","affiliation":[]},{"given":"Prakashgoud","family":"Patil","sequence":"additional","affiliation":[]},{"given":"P. S.","family":"Hiremath","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"1374_CR1","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Compressed video action recognition. In: CVPR, (2018)","DOI":"10.1109\/CVPR.2018.00631"},{"key":"1374_CR2","doi-asserted-by":"publisher","unstructured":"Bommes, L., Lin, X., Zhou, J.: MVmed: fast multi-object tracking in the compressed domain. In: 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 1419-1424 (2020), https:\/\/doi.org\/10.1109\/ICIEA48937.2020.9248145","DOI":"10.1109\/ICIEA48937.2020.9248145"},{"key":"1374_CR3","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 Int. Conf. Comput. Vis., pp. 2556\u20132563, IEEE, (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1374_CR4","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. tech. rep., University of Central Florida, (2012)"},{"key":"1374_CR5","unstructured":"Jiang, Y.-G., Liu, J., Roshan Zamir, A., Toderici, G., Laptev, I., Shah, M., Sukthankar, R.: THUMOS challenge: action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/, (2014). Accessed July 2022"},{"key":"1374_CR6","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Neurips, pp. 568\u2013576, (2014)"},{"key":"1374_CR7","doi-asserted-by":"publisher","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4724\u20134733 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"issue":"4","key":"1374_CR8","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2599174","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1374_CR9","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TIP.2020.3038372","volume":"30","author":"Z Gao","year":"2021","unstructured":"Gao, Z., Guo, L., Guan, W., Liu, A.-A., Ren, T., Chen, S.: A pairwise attentive adversarial spatiotemporal network for cross-domain few-shot action recognition-R2. IEEE Trans. Image Process. 30, 767\u2013782 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"1374_CR10","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TNNLS.2020.3041018","volume":"33","author":"Z Gao","year":"2022","unstructured":"Gao, Z., Guo, L., Ren, T., Liu, A.-A., Cheng, Z.-Y., Chen, S.: Pairwise two-stream ConvNets for cross-domain action recognition with small data. IEEE Trans. Neural Netw. Learn. Syst. 33(3), 1147\u20131161 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2020.3041018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"1374_CR11","doi-asserted-by":"publisher","first-page":"3587","DOI":"10.1109\/TCSVT.2021.3104651","volume":"32","author":"T Liu","year":"2022","unstructured":"Liu, T., Lam, K.-M., Zhao, R., Kong, J.: Enhanced attention tracking with multi-branch network for egocentric activity recognition. IEEE Trans. Circ. Syst. Vid. Technol. 32(6), 3587\u20133602 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3104651","journal-title":"IEEE Trans. Circ. Syst. Vid. Technol."},{"key":"1374_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202835","author":"T Liu","year":"2022","unstructured":"Liu, T., Zhao, R., Jia, W., Lam, K.-M., Kong, J.: Holistic-guided disentangled learning with cross-video semantics mining for concurrent first-person and third-person activity recognition. IEEE Trans. Neural Netw. Learn. Syst. (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3202835","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1374_CR13","doi-asserted-by":"publisher","first-page":"4746","DOI":"10.1109\/TIP.2022.3182866","volume":"31","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., et al.: A temporal-aware relation and attention network for temporal action localization. IEEE Trans. Image Process. 31, 4746\u20134760 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3182866","journal-title":"IEEE Trans. Image Process."},{"key":"1374_CR14","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s11042-014-2345","volume":"75","author":"RV Babu","year":"2016","unstructured":"Babu, R.V., Tom, M., Wadekar, P.: A survey on compressed domain video analysis techniques. Multimed. Tools Appl. 75, 1043\u20131078 (2016). https:\/\/doi.org\/10.1007\/s11042-014-2345","journal-title":"Multimed. Tools Appl."},{"key":"1374_CR15","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with deeply transferred motion vector CNNs. IEEE Trans. Image Process. 27, 2326\u20132339 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"1374_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: CVPR, (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"1374_CR17","doi-asserted-by":"crossref","unstructured":"Shou, Z., Yan, Z., Kalantidis, Y., Sevilla-Lara, L., Rohrbach, M., Lin, X., Chang, S.-F.: DMC-Net: generating discriminative motion cues for fast compressed video action recognition. tech. rep., Columbia Univ. & Facebook, (2019)","DOI":"10.1109\/CVPR.2019.00136"},{"key":"1374_CR18","unstructured":"Huo, Y., Xu, X., Lu, Y., Niu, Y., Lu, Z., Wen, J.-R.: Mobile video action recognition. tech. rep., (2019)"},{"key":"1374_CR19","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 4510\u20134520, IEEE Computer Society, (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1374_CR20","doi-asserted-by":"publisher","unstructured":"Wang, J., Torresani, L.: Deformable video transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14033\u201314042 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01366","DOI":"10.1109\/CVPR52688.2022.01366"},{"key":"1374_CR21","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1109\/ACCESS.2017.2778011","volume":"6","author":"A Ullah","year":"2018","unstructured":"Ullah, A., Ahmad, J., Muhammad, K., Sajjad, M., Baik, S.W.: Action recognition in video sequences using deep Bi-Directional LSTM with CNN features. IEEE Access 6, 1155\u20131166 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2017.2778011","journal-title":"IEEE Access"},{"key":"1374_CR22","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Log. Q. 2, 83\u201397 (1955)","journal-title":"Naval Res. Log. Q."},{"key":"1374_CR23","doi-asserted-by":"crossref","unstructured":"Wu, W., Wang, X., Luo, H., Wang, J., Yang, Y., Ouyang, W.: Bidirectional cross-modal knowledge exploration for video recognition with pre-trained vision-language models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"1374_CR24","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: SMART frame selection for action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence 35(2), 1451\u20131459 (2021)","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"1374_CR25","doi-asserted-by":"publisher","unstructured":"Li, Y., Lu, Z., Xiong, X., Huang, J.: PERF-Net: pose empowered RGB-Flow Net. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2022, pp. 798\u2013807 (2022), https:\/\/doi.org\/10.1109\/WACV51458.2022.00087","DOI":"10.1109\/WACV51458.2022.00087"},{"key":"1374_CR26","doi-asserted-by":"crossref","unstructured":"Wu, W., Sun, Z., Ouyang, W.: Revisiting classifier: transferring vision-language models for video recognition. In: AAAI Conference on Artificial Intelligence (AAAI), (2023)","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"1374_CR27","doi-asserted-by":"publisher","unstructured":"Qiu, Z., Yao, T., Ngo, C.-W., Tian, X., Mei, T.: Learning spatio-temporal representation with local and global diffusion. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 12048-12057, (2019), https:\/\/doi.org\/10.1109\/CVPR.2019.01233.","DOI":"10.1109\/CVPR.2019.01233."},{"key":"1374_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Ma, L., Zhang, Y., Liu, W., Chang, S.-F.: Multi-granularity generator for temporal action proposal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3604\u20133613, (2019)","DOI":"10.1109\/CVPR.2019.00372"},{"issue":"10","key":"1374_CR29","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1109\/TPAMI.2019.2921539","volume":"41","author":"H Xu","year":"2019","unstructured":"Xu, H., Das, A., Saenko, K.: Two-stream region convolutional 3D network for temporal activity detection. IEEE Trans. Pattern Anal. Mach. Intell. 41(10), 2319\u20132332 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2921539","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1374_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Ti., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3889\u20133898, (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"1374_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., Qiao, Y.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: Submitted on 29 Mar 2023 to Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"1374_CR32","doi-asserted-by":"publisher","unstructured":"Battash, B., Barad, H., Tang, H., Bleiweiss, A.: Mimic the raw domain: accelerating action recognition in the compressed domain. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2926\u20132934 (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00350","DOI":"10.1109\/CVPRW50498.2020.00350"},{"key":"1374_CR33","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., Snoek, C.G.: What do 15,000 object categories tell us about classifying and localizing actions? In: CVPR\u201915, pp. 46\u201355, (2015)","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"1374_CR34","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. In: THUMOS Action Recognition challenge, (2014)"},{"key":"1374_CR35","volume-title":"Introduction to Probability and Statistics","author":"J Susan Milton","year":"2007","unstructured":"Susan Milton, J., Arnold, J.C.: Introduction to Probability and Statistics, 4th edn. McGraw Hill (2007)","edition":"4"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01374-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-023-01374-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01374-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T16:27:29Z","timestamp":1700756849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-023-01374-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1374"],"URL":"https:\/\/doi.org\/10.1007\/s11554-023-01374-9","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"7 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"122"}}