{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:13:49Z","timestamp":1757618029789,"version":"3.44.0"},"reference-count":140,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T00:00:00Z","timestamp":1746748800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T00:00:00Z","timestamp":1746748800000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11263-025-02439-x","type":"journal-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:57:35Z","timestamp":1746766655000},"page":"5505-5526","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Autoregressive Temporal Modeling for Advanced Tracking-by-Diffusion"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1517-1382","authenticated-orcid":false,"given":"Pha","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rishi","family":"Madhok","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khoa","family":"Luu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,9]]},"reference":[{"unstructured":"Aharon, N., Orfaig, R., & Bobrovsky, B. Z. (2022). BoT-SORT: Robust associations multi-pedestrian tracking. arXiv preprint arXiv:2206.14651","key":"2439_CR1"},{"doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., & Savarese, S. (2016). Social LSTM: Human trajectory prediction in crowded spaces. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 961\u2013971).","key":"2439_CR2","DOI":"10.1109\/CVPR.2016.110"},{"issue":"3","key":"2439_CR3","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0304-4149(82)90051-5","volume":"12","author":"BD Anderson","year":"1982","unstructured":"Anderson, B. D. (1982). Reverse-time diffusion equation models. Stochastic Processes and their Applications, 12(3), 313\u2013326.","journal-title":"Stochastic Processes and their Applications"},{"doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., & Schiele, B. (2018). Posetrack: A benchmark for human pose estimation and tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5167\u20135176).","key":"2439_CR4","DOI":"10.1109\/CVPR.2018.00542"},{"doi-asserted-by":"crossref","unstructured":"Andriyenko, A., & Schindler, K. (2011). Multi-target tracking by continuous energy minimization. In CVPR 2011 (pp. 1265\u20131272). IEEE.","key":"2439_CR5","DOI":"10.1109\/CVPR.2011.5995311"},{"issue":"9","key":"2439_CR6","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TPAMI.2011.21","volume":"33","author":"J Berclaz","year":"2011","unstructured":"Berclaz, J., Fleuret, F., Turetken, E., & Fua, P. (2011). Multiple object tracking using k-shortest paths optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(9), 1806\u20131819.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., & Leal-Taixe, L. (2019). Tracking without bells and whistles. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 941\u2013951).","key":"2439_CR7","DOI":"10.1109\/ICCV.2019.00103"},{"key":"2439_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: the clear mot metrics. EURASIP Journal on Image and Video Processing, 2008, 1\u201310.","journal-title":"EURASIP Journal on Image and Video Processing"},{"doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP) (IEEE) (pp. 3464\u20133468).","key":"2439_CR9","DOI":"10.1109\/ICIP.2016.7533003"},{"doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., & Leal-Taix\u00e9, L. (2020). Learning a neural solver for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6247\u20136257).","key":"2439_CR10","DOI":"10.1109\/CVPR42600.2020.00628"},{"doi-asserted-by":"crossref","unstructured":"Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., & Soatto, S. (2022). MeMOT: Multi-object tracking with memory. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8090\u20138100).","key":"2439_CR11","DOI":"10.1109\/CVPR52688.2022.00792"},{"doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, J., Weng, X., Khirodkar, R., & Kitani, K. (2023). Observation-centric sort: Rethinking sort for robust multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9686\u20139696).","key":"2439_CR12","DOI":"10.1109\/CVPR52729.2023.00934"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). 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\u20136308).","key":"2439_CR13","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Chen, L., Ai, H., Zhuang, Z., & Shang, C. (2018). Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In 2018 IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136). IEEE.","key":"2439_CR14","DOI":"10.1109\/ICME.2018.8486597"},{"doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., & Luo, P. (2023). Diffusiondet: Diffusion model for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 19830\u201319843).","key":"2439_CR15","DOI":"10.1109\/ICCV51070.2023.01816"},{"doi-asserted-by":"crossref","unstructured":"Chu, P., & Ling, H. (2019). FAMNet: Joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6172\u20136181).","key":"2439_CR16","DOI":"10.1109\/ICCV.2019.00627"},{"key":"2439_CR17","first-page":"58736","volume":"36","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Song, T., Wu, G., & Wang, L. (2024). Mixformerv2: Efficient fully transformer tracking. Advances in Neural Information Processing Systems, 36, 58736\u201358751.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR18","first-page":"15657","volume":"35","author":"P Dendorfer","year":"2022","unstructured":"Dendorfer, P., Yugay, V., O\u0161ep, A., & Leal-Taix\u00e9, L. (2022). Quo Vadis: Is trajectory forecasting the key towards long-term multi-object tracking? Advances in Neural Information Processing Systems, 35, 15657\u201315671.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR19","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. Neural Information Processing Systems, 34, 8780\u20138794.","journal-title":"Neural Information Processing Systems"},{"unstructured":"Dinh, L., Krueger, D., & Bengio, Y. (2014). Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516","key":"2439_CR20"},{"unstructured":"Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2017). Density estimation using real NVP. In International conference on learning representations.","key":"2439_CR21"},{"doi-asserted-by":"crossref","unstructured":"Doering, A., Chen, D., Zhang, S., Schiele, B., & Gall, J. (2022). Posetrack21: A dataset for person search, multi-object tracking and multi-person pose tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 20963\u201320972).","key":"2439_CR22","DOI":"10.1109\/CVPR52688.2022.02029"},{"doi-asserted-by":"crossref","unstructured":"Doersch, C., Yang, Y., Vecerik, M., Gokay, D., Gupta, A., Aytar, Y., Carreira, J., & Zisserman, A. (2023). TAPIR: Tracking any point with per-frame initialization and temporal refinement. In ICCV.","key":"2439_CR23","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"2439_CR24","first-page":"13610","volume":"35","author":"C Doersch","year":"2022","unstructured":"Doersch, C., Gupta, A., Markeeva, L., Recasens, A., Smaira, L., Aytar, Y., Carreira, J., Zisserman, A., & Yang, Y. (2022). Tap-vid: A benchmark for tracking any point in a video. Advances in Neural Information Processing Systems, 35, 13610\u201313626.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/9781108591034","volume-title":"Probability: theory and examples","author":"R Durrett","year":"2019","unstructured":"Durrett, R. (2019). Probability: theory and examples (Vol. 49). Cambridge University Press."},{"unstructured":"El-Nouby, A., Klein, M., Zhai, S., Bautista, M.\u00c1., Shankar, V., Toshev, A. T., Susskind, J. M., & Joulin, A. (2024). Scalable pre-training of large autoregressive image models. In Forty-first international conference on machine learning.","key":"2439_CR26"},{"doi-asserted-by":"crossref","unstructured":"Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Harshit, Huang, M., Liu, J., et al. (2021). LaSOT: A high-quality large-scale single object tracking benchmark. International Journal of Computer Vision, 129, 439\u2013461.","key":"2439_CR27","DOI":"10.1007\/s11263-020-01387-y"},{"doi-asserted-by":"crossref","unstructured":"Fang, H., Carbajal, G., Wermter, S., & Gerkmann, T. (2021). Variational autoencoder for speech enhancement with a noise-aware encoder. In ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 676\u2013680). IEEE.","key":"2439_CR28","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., & Zisserman, A. (2017). Detect to track and track to detect. In Proceedings of the IEEE international conference on computer vision (pp. 3038\u20133046).","key":"2439_CR29","DOI":"10.1109\/ICCV.2017.330"},{"doi-asserted-by":"crossref","unstructured":"Feng, R., Gao, Y., Tse, T. H. E., Ma, X., & Chang, H. J. (2023). DiffPose: SpatioTemporal diffusion model for video-based human pose estimation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 14861\u201314872).","key":"2439_CR30","DOI":"10.1109\/ICCV51070.2023.01365"},{"key":"2439_CR31","doi-asserted-by":"publisher","first-page":"15380","DOI":"10.1109\/TPAMI.2023.3301975","volume":"45","author":"T Fischer","year":"2023","unstructured":"Fischer, T., Huang, T. E., Pang, J., Qiu, L., Chen, H., Darrell, T., & Yu, F. (2023). QDTrack: Quasi-dense similarity learning for appearance-only multiple object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 15380\u201315393.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Gao, R., & Wang, L. (2023). MeMOTR: Long-term memory-augmented transformer for multi-object tracking. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9901\u20139910).","key":"2439_CR32","DOI":"10.1109\/ICCV51070.2023.00908"},{"doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R. (2012). Are we ready for autonomous driving? The kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition (pp. 3354\u20133361). IEEE.","key":"2439_CR33","DOI":"10.1109\/CVPR.2012.6248074"},{"doi-asserted-by":"crossref","unstructured":"Greff, K., Belletti, F., Beyer, L., Doersch, C., Du, Y., Duckworth, D., Fleet, D. J., Gnanapragasam, D., Golemo, F., Herrmann, C., & Kipf, T. (2022). Kubric: A scalable dataset generator. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3749\u20133761).","key":"2439_CR34","DOI":"10.1109\/CVPR52688.2022.00373"},{"doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., & Alahi, A. (2018). Social GAN: Socially acceptable trajectories with generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2255\u20132264).","key":"2439_CR35","DOI":"10.1109\/CVPR.2018.00240"},{"doi-asserted-by":"crossref","unstructured":"Harley, A. W., Fang, Z., & Fragkiadaki, K. (2022). Particle video revisited: Tracking through occlusions using point trajectories. In European conference on computer vision (pp. 59\u201375). Springer.","key":"2439_CR36","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"2439_CR37","first-page":"8266","volume":"36","author":"E Hedlin","year":"2023","unstructured":"Hedlin, E., Sharma, G., Mahajan, S., Isack, H., Kar, A., Tagliasacchi, A., & Yi, K. M. (2023). Unsupervised semantic correspondence using stable diffusion. Advances in Neural Information Processing Systems, 36, 8266\u20138279.","journal-title":"Advances in Neural Information Processing Systems"},{"unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., & Rosenhahn, B. (2017). Improvements to Frank-Wolfe optimization for multi-detector multi-object tracking, Vol. 8. arXiv preprint arXiv:1705.08314.","key":"2439_CR38"},{"key":"2439_CR39","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"unstructured":"Hornakova, A., Henschel, R., Rosenhahn, B., & Swoboda, P. (2020). Lifted disjoint paths with application in multiple object tracking. In International conference on machine learning (pp. 4364\u20134375). PMLR.","key":"2439_CR40"},{"key":"2439_CR41","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., & Fleet, D. J. (2022). Video diffusion models. Advances in Neural Information Processing Systems, 35, 8633\u20138646.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR42","doi-asserted-by":"publisher","first-page":"11037","DOI":"10.1609\/aaai.v34i07.6758","volume":"34","author":"L Huang","year":"2020","unstructured":"Huang, L., Zhao, X., & Huang, K. (2020). GlobalTrack: A simple and strong baseline for long-term tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 11037\u201311044.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Jiang, H., Fels, S., & Little, J. J. (2007). A linear programming approach for multiple object tracking. In 2007 IEEE conference on computer vision and pattern recognition (pp. 1\u20138). IEEE.","key":"2439_CR43","DOI":"10.1109\/CVPR.2007.383180"},{"doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., & Yi, K. M. (2021). COTR: Correspondence transformer for matching across images. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 6207\u20136217).","key":"2439_CR44","DOI":"10.1109\/ICCV48922.2021.00615"},{"doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., & Carion, N. (2021). MDETR-modulated detection for end-to-end multi-modal understanding. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 1780\u20131790).","key":"2439_CR45","DOI":"10.1109\/ICCV48922.2021.00180"},{"doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., & Rupprecht, C. (2023). CoTracker: It is better to track together. arXiv preprint arXiv:2307.07635","key":"2439_CR46","DOI":"10.1007\/978-3-031-73033-7_2"},{"issue":"1","key":"2439_CR47","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TPAMI.2018.2876253","volume":"42","author":"M Keuper","year":"2018","unstructured":"Keuper, M., Tang, S., Andres, B., Brox, T., & Schiele, B. (2018). Motion segmentation & multiple object tracking by correlation co-clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(1), 140\u2013153.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Kim, C., Li, F., Ciptadi, A., & Rehg, J. M. (2015). Multiple hypothesis tracking revisited. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 4696\u20134704).","key":"2439_CR48","DOI":"10.1109\/ICCV.2015.533"},{"unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational Bayes. In International conference on learning representations.","key":"2439_CR49"},{"unstructured":"Kong, Z., & Ping, W. (2021). On fast sampling of diffusion probabilistic models. In ICML workshop on invertible neural networks, normalizing flows, and explicit likelihood models.","key":"2439_CR50"},{"unstructured":"Kwon, M., Jeong, J., & Uh, Y. (2023). Diffusion models already have a semantic latent space. In The eleventh international conference on learning representations.","key":"2439_CR51"},{"unstructured":"Leal-Taixe, L. (2014). Multiple object tracking with context awareness. arxiv preprint arxiv:1411.7935","key":"2439_CR52"},{"doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Canton-Ferrer, C., & Schindler, K. (2016). Learning by tracking: Siamese CNN for robust target association. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 33\u201340).","key":"2439_CR53","DOI":"10.1109\/CVPRW.2016.59"},{"doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Fenzi, M., Kuznetsova, A., Rosenhahn, B., & Savarese, S. (2014). Learning an image-based motion context for multiple people tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3542\u20133549).","key":"2439_CR54","DOI":"10.1109\/CVPR.2014.453"},{"doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Pons-Moll, G., & Rosenhahn, B. (2011). Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker. In 2011 IEEE international conference on computer vision workshops (ICCV workshops) (pp. 120\u2013127). IEEE.","key":"2439_CR55","DOI":"10.1109\/ICCVW.2011.6130233"},{"unstructured":"Lee, A. X., Devin, C. M., Zhou, Y., Lampe, T., Bousmalis, K., Springenberg, J. T., Byravan, A., Abdolmaleki, A., Gileadi, N., Khosid, D., & Fantacci, C. (2022). Beyond pick-and-place: Tackling robotic stacking of diverse shapes. In Conference on robot learning (pp. 1089\u20131131). PMLR.","key":"2439_CR56"},{"doi-asserted-by":"crossref","unstructured":"Li, S., Fischer, T., Ke, L., Ding, H., Danelljan, M., & Yu, F. (2023). OVTrack: Open-vocabulary multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5567\u20135577).","key":"2439_CR57","DOI":"10.1109\/CVPR52729.2023.00539"},{"unstructured":"Li, P., Liu, Z., Chen, K., Hong, L., Zhuge, Y., Yeung,D. Y., Lu, H., & Jia, X. (2023). TrackDiffusion: Multi-object tracking data generation via diffusion models. arXiv preprint arXiv:2312.00651","key":"2439_CR58"},{"doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., & Hu, X. (2018). High performance visual tracking with Siamese region proposal network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8971\u20138980).","key":"2439_CR59","DOI":"10.1109\/CVPR.2018.00935"},{"doi-asserted-by":"crossref","unstructured":"Liu, Q., Chu, Q., Liu, B., & Yu, N. (2020) GSM: Graph similarity model for multi-object tracking. In IJCAI (pp. 530\u2013536).","key":"2439_CR60","DOI":"10.24963\/ijcai.2020\/74"},{"key":"2439_CR61","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J., Osep, A., Dendorfer, P., Torr, P., Geiger, A., Leal-Taix\u00e9, L., & Leibe, B. (2021). Hota: A higher order metric for evaluating multi-object tracking. International Journal of Computer Vision, 129, 548\u2013578.","journal-title":"International Journal of Computer Vision"},{"doi-asserted-by":"crossref","unstructured":"Luo, R., Song, Z., Ma, L., Wei, J., Yang, W., & Yang, M. (2024). Diffusiontrack: Diffusion model for multi-object tracking. In Proceedings of the AAAI conference on artificial intelligence.","key":"2439_CR62","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"2439_CR63","first-page":"47500","volume":"36","author":"G Luo","year":"2023","unstructured":"Luo, G., Dunlap, L., Park, D. H., Holynski, A., & Darrell, T. (2023). Diffusion hyperfeatures: Searching through time and space for semantic correspondence. Advances in Neural Information Processing Systems, 36, 47500\u201347510.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR64","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J. (2022). DPM-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Advances in Neural Information Processing Systems, 35, 5775\u20135787.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"crossref","unstructured":"Lv, W., Huang, Y., Zhang, N., Lin, R. S., Han, M., & Zeng, D. (2024). DiffMOT: A real-time diffusion-based multiple object tracker with non-linear prediction. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","key":"2439_CR65","DOI":"10.1109\/CVPR52733.2024.01828"},{"doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022). TrackFormer: Multi-object tracking with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8844\u20138854).","key":"2439_CR66","DOI":"10.1109\/CVPR52688.2022.00864"},{"unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., & Schindler, K. (2016). MOT16: A benchmark for multi-object tracking. arXiv:1603.00831 [cs] . ArXiv: 1603.00831","key":"2439_CR67"},{"unstructured":"Mittal, S., Abstreiter, K., Bauer, S., Sch\u00f6lkopf, B., & Mehrjou, A. (2023). Diffusion based representation learning. In International conference on machine learning (pp. 24963\u201324982). PMLR.","key":"2439_CR68"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, D. M., Henschel, R., Rosenhahn, B., Sonntag, D., & Swoboda, P. (2022). LMGP: Lifted multicut meets geometry projections for multi-camera multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8866\u20138875).","key":"2439_CR69","DOI":"10.1109\/CVPR52688.2022.00866"},{"unstructured":"Nguyen, P., Le, N. H., Cothren, J., Yilmaz, A., & Luu, K. (2024). DINTR: Tracking via diffusion-based interpolation. In The thirty-eighth annual conference on neural information processing systems. https:\/\/openreview.net\/forum?id=gAgwqHOBIg","key":"2439_CR70"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, P., Quach, K. G., Duong, C. N., Le, N., Nguyen, X. B., & Luu, K. (2022). Multi-camera multiple 3D object tracking on the move for autonomous vehicles. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) workshops (pp. 2569\u20132578).","key":"2439_CR71","DOI":"10.1109\/CVPRW56347.2022.00289"},{"unstructured":"Nguyen, P., Quach, K. G., Gauch, J., Khan, S. U., Raj, B., & Luu, K. (2023) UTOPIA: Unconstrained tracking objects without preliminary examination via cross-domain adaptation. arXiv preprint arXiv:2306.09613","key":"2439_CR72"},{"key":"2439_CR73","doi-asserted-by":"publisher","first-page":"110457","DOI":"10.1016\/j.patcog.2024.110457","volume":"152","author":"P Nguyen","year":"2024","unstructured":"Nguyen, P., Quach, K. G., Duong, C. N., Phung, S. L., Le, N., & Luu, K. (2024). Multi-camera multi-object tracking on the move via single-stage global association approach. Pattern Recognition, 152, 110457.","journal-title":"Pattern Recognition"},{"key":"2439_CR74","first-page":"3205","volume":"36","author":"P Nguyen","year":"2023","unstructured":"Nguyen, P., Quach, K. G., Kitani, K., & Luu, K. (2023). Type-to-track: Retrieve any object via prompt-based tracking. Advances in Neural Information Processing Systems, 36, 3205\u20133219.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR75","volume-title":"Stochastic differential equations: An introduction with applications","author":"B Oksendal","year":"2013","unstructured":"Oksendal, B. (2013). Stochastic differential equations: An introduction with applications. Springer Science & Business Media."},{"unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., & Assran, M. (2023). Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193","key":"2439_CR76"},{"doi-asserted-by":"crossref","unstructured":"O\u0161ep, A., Mehner, W., Voigtlaender, P., & Leibe, B. (2018). Track, then decide: Category-agnostic vision-based multi-object tracking. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 3494\u20133501). IEEE.","key":"2439_CR77","DOI":"10.1109\/ICRA.2018.8460975"},{"doi-asserted-by":"crossref","unstructured":"Pang, J., Qiu, L., Li, X., Chen, H., Li, Q., Darrell, T., & Yu, F. (2021). Quasi-dense similarity learning for multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 164\u2013173).","key":"2439_CR78","DOI":"10.1109\/CVPR46437.2021.00023"},{"doi-asserted-by":"crossref","unstructured":"Pellegrini, S., Ess, A., Schindler, K., & Van\u00a0Gool, L. (2009). You\u2019ll never walk alone: Modeling social behavior for multi-target tracking. In 2009 IEEE 12th international conference on computer vision. (pp. 261\u2013268). IEEE.","key":"2439_CR79","DOI":"10.1109\/ICCV.2009.5459260"},{"doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A. (2016). A benchmark dataset and evaluation methodology for video object segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 724\u2013732).","key":"2439_CR80","DOI":"10.1109\/CVPR.2016.85"},{"doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D., & Fowlkes, C. C. (2011). Globally-optimal greedy algorithms for tracking a variable number of objects. In CVPR 2011 (pp. 1201\u20131208). IEEE.","key":"2439_CR81","DOI":"10.1109\/CVPR.2011.5995604"},{"doi-asserted-by":"crossref","unstructured":"Porzi, L., Hofinger, M., Ruiz, I., Serrat, J., Bulo, S. R., Kontschieder, P. (2020). Learning multi-object tracking and segmentation from automatic annotations. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6846\u20136855).","key":"2439_CR82","DOI":"10.1109\/CVPR42600.2020.00688"},{"key":"2439_CR83","doi-asserted-by":"publisher","first-page":"9220","DOI":"10.1109\/TIP.2021.3124155","volume":"30","author":"CD Prakash","year":"2021","unstructured":"Prakash, C. D., & Karam, L. J. (2021). It GAN do better: GAN-based detection of objects on images with varying quality. IEEE Transactions on Image Processing, 30, 9220\u20139230.","journal-title":"IEEE Transactions on Image Processing"},{"doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., & Suwajanakorn, S. (2022). Diffusion autoencoders: Toward a meaningful and decodable representation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10619\u201310629).","key":"2439_CR84","DOI":"10.1109\/CVPR52688.2022.01036"},{"doi-asserted-by":"crossref","unstructured":"Qi, C., Cun, X., Zhang, Y., Lei, C., Wang, X., Shan, Y., & Chen, Q. (2023). FateZero: Fusing attentions for zero-shot text-based video editing. In Proceedings of the IEEE\/CVF international conference on computer vision.","key":"2439_CR85","DOI":"10.1109\/ICCV51070.2023.01460"},{"doi-asserted-by":"crossref","unstructured":"Quach, K. G., Nguyen, P., Le, H., Truong, T. D., Duong, C. N., Tran, M. T., & Luu, K. (2021). DyGLIP: a dynamic graph model with link prediction for accurate multi-camera multiple object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13784\u201313793).","key":"2439_CR86","DOI":"10.1109\/CVPR46437.2021.01357"},{"doi-asserted-by":"crossref","unstructured":"Rafi, U., Doering, A., Leibe, B., & Gall, J. (2020). Self-supervised keypoint correspondences for multi-person pose estimation and tracking in videos. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XX 16 (pp. 36\u201352). Springer.","key":"2439_CR87","DOI":"10.1007\/978-3-030-58565-5_3"},{"doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., & Malik, J. (2022). Tracking people by predicting 3D appearance, location and pose. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2740\u20132749).","key":"2439_CR88","DOI":"10.1109\/CVPR52688.2022.00276"},{"doi-asserted-by":"crossref","unstructured":"Ristani, E., & Tomasi, C. (2018). Features for multi-target multi-camera tracking and re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6036\u20136046).","key":"2439_CR89","DOI":"10.1109\/CVPR.2018.00632"},{"doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., & Tomasi, C. (2016). Performance measures and a data set for multi-target, multi-camera tracking. In European conference on computer vision (pp. 17\u201335). Springer.","key":"2439_CR90","DOI":"10.1007\/978-3-319-48881-3_2"},{"doi-asserted-by":"crossref","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., & Savarese, S. (2016). Learning social etiquette: Human trajectory prediction in crowded scenes. In European conference on computer vision (ECCV) (vol. 2 , p. 5).","key":"2439_CR91","DOI":"10.1007\/978-3-319-46484-8_33"},{"doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10684\u201310695).","key":"2439_CR92","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139, 2015, proceedings, part III 18 (pp. 234\u2013241). Springer.","key":"2439_CR93","DOI":"10.1007\/978-3-319-24574-4_28"},{"doi-asserted-by":"crossref","unstructured":"Scovanner, P., & Tappen, M. F. (2009). Learning pedestrian dynamics from the real world. In 2009 IEEE 12th international conference on computer vision (pp. 381\u2013388). IEEE.","key":"2439_CR94","DOI":"10.1109\/ICCV.2009.5459224"},{"unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., & Sun, J. (2018). CrowdHuman: A benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123","key":"2439_CR95"},{"issue":"11","key":"2439_CR96","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.1109\/TCSVT.2018.2882192","volume":"29","author":"H Sheng","year":"2018","unstructured":"Sheng, H., Zhang, Y., Chen, J., Xiong, Z., & Zhang, J. (2018). Heterogeneous association graph fusion for target association in multiple object tracking. IEEE Transactions on Circuits and Systems for Video Technology, 29(11), 3269\u20133280.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"unstructured":"Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., Parikh, D., Gupta, S., & Taigman, Y. (2023). Make-a-video: Text-to-video generation without text-video data. In The eleventh international conference on learning representations.","key":"2439_CR97"},{"unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning (pp. 2256\u20132265). PMLR.","key":"2439_CR98"},{"unstructured":"Song, J., Meng, C., & Ermon, S. (2021). Denoising diffusion implicit models. In International conference on learning representations.","key":"2439_CR99"},{"unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations. In International conference on learning representations.","key":"2439_CR100"},{"doi-asserted-by":"crossref","unstructured":"Stadler, D., & Beyerer, J. (2021). Improving multiple pedestrian tracking by track management and occlusion handling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 10958\u201310967).","key":"2439_CR101","DOI":"10.1109\/CVPR46437.2021.01081"},{"doi-asserted-by":"crossref","unstructured":"Sun, S., Akhtar, N., Song, X., Song, H., Mian, A., & Shah, M. (2020). Simultaneous detection and tracking with motion modelling for multiple object tracking. In Proceedings of the European conference on computer vision (ECCV) (pp. 626\u2013643).","key":"2439_CR102","DOI":"10.1007\/978-3-030-58586-0_37"},{"doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., & Schiele, B. (2017). Multiple people tracking by lifted multicut and person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3539\u20133548).","key":"2439_CR103","DOI":"10.1109\/CVPR.2017.394"},{"unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C. P., & Hariharan, B. (2023). Emergent correspondence from image diffusion. In Thirty-seventh conference on neural information processing systems","key":"2439_CR104"},{"doi-asserted-by":"crossref","unstructured":"Teed, Z., & Deng, J. (2020). Raft: Recurrent all-pairs field transforms for optical flow. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part II 16 (pp. 402\u2013419). Springer.","key":"2439_CR105","DOI":"10.1007\/978-3-030-58536-5_24"},{"unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., & Wang, L. (2024). Visual autoregressive modeling: Scalable image generation via next-scale prediction. arXiv preprint arXiv:2404.02905","key":"2439_CR106"},{"doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., & Gaidon, A. (2021). Learning to track with object permanence. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10860\u201310869).","key":"2439_CR107","DOI":"10.1109\/ICCV48922.2021.01068"},{"unstructured":"Truong, T. D., Duong, C. N., Dowling, A., Phung, S. L., Cothren, J., & Luu, K. (2023). CROVIA: Seeing drone scenes from car perspective via cross-view adaptation. arXiv preprint arXiv:2304.07199","key":"2439_CR108"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30","key":"2439_CR109"},{"doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G, Geiger, A., & Leibe, B. (2019). MOTS: Multi-object tracking and segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7942\u20137951)","key":"2439_CR110","DOI":"10.1109\/CVPR.2019.00813"},{"doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Luiten, J., Torr, P. H., & Leibe, B. (2020). Siam R-CNN: Visual tracking by re-detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6578\u20136588).","key":"2439_CR111","DOI":"10.1109\/CVPR42600.2020.00661"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Kitani, K., & Weng, X. (2021). Joint object detection and multi-object tracking with graph neural networks. In 2021 IEEE international conference on robotics and automation (ICRA) (pp. 13708\u201313715). IEEE.","key":"2439_CR112","DOI":"10.1109\/ICRA48506.2021.9561110"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Shu, X., Zhang, Z., Jiang, B., Wang, Y., Tian, Y., & Wu, F. (2021). Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13763\u201313773).","key":"2439_CR113","DOI":"10.1109\/CVPR46437.2021.01355"},{"doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., & Torr, P. H. (2019). Fast online object tracking and segmentation: A unifying approach. In Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (pp. 1328\u20131338).","key":"2439_CR114","DOI":"10.1109\/CVPR.2019.00142"},{"doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., & Wang, S. (2020). Towards real-time multi-object tracking. In Proceedings of the European conference on computer vision (ECCV) (pp. 107\u2013122). Springer.","key":"2439_CR115","DOI":"10.1007\/978-3-030-58621-8_7"},{"key":"2439_CR116","doi-asserted-by":"publisher","first-page":"5257","DOI":"10.1109\/TIP.2022.3192706","volume":"31","author":"S Wang","year":"2022","unstructured":"Wang, S., Sheng, H., Yang, D., Zhang, Y., Wu, Y., & Wang, S. (2022). Extendable multiple nodes recurrent tracking framework with RTU++. IEEE Transactions on Image Processing, 31, 5257\u20135271.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2439_CR117","first-page":"726","volume":"34","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Zhao, H., Li, Y. L., Wang, S., Torr, P., & Bertinetto, L. (2021). Do different tracking tasks require different appearance models? Advances in Neural Information Processing Systems, 34, 726\u2013738.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"crossref","unstructured":"Wojke, N., & Bewley, A. (2018). Deep cosine metric learning for person re-identification. In 2018 IEEE winter conference on applications of computer vision (WACV) (pp. 748\u2013756). IEEE.","key":"2439_CR118","DOI":"10.1109\/WACV.2018.00087"},{"doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP) (pp. 3645\u20133649). IEEE.","key":"2439_CR119","DOI":"10.1109\/ICIP.2017.8296962"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Cao, J., Song, L., Wang, Y., Yang, M., & Yuan, J. (2021). Track to detect and segment: An online multi-object tracker. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12352\u201312361).","key":"2439_CR120","DOI":"10.1109\/CVPR46437.2021.01217"},{"doi-asserted-by":"crossref","unstructured":"Wu, J. Z., Ge, Y., Wang, X., Lei, S. W., Gu, Y., Shi, Y., Hsu, W., Shan, Y., Qie, X., & Shou, M. Z. (2023). Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7623\u20137633).","key":"2439_CR121","DOI":"10.1109\/ICCV51070.2023.00701"},{"doi-asserted-by":"crossref","unstructured":"Wu, D., Han, W., Wang, T., Dong, X., Zhang, X., & Shen, J. (2023). Referring multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14633\u201314642).","key":"2439_CR122","DOI":"10.1109\/CVPR52729.2023.01406"},{"doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, W., Tan, X., Yang, W., Huang, H., Wen, S., Ding, E., & Huang, L. (2020). Segment as points for efficient online multi-object tracking and segmentation. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part I 16 (pp. 264\u2013281). Springer.","key":"2439_CR123","DOI":"10.1007\/978-3-030-58452-8_16"},{"issue":"10","key":"2439_CR124","doi-asserted-by":"publisher","first-page":"6424","DOI":"10.1109\/TPAMI.2021.3087898","volume":"44","author":"Z Xu","year":"2021","unstructured":"Xu, Z., Yang, W., Zhang, W., Tan, X., Huang, H., & Huang, L. (2021). Segment as points for efficient and effective online multi-object tracking and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), 6424\u20136437.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., Berg, A. C., Ortiz, L. E., & Berg, T. L. (2011). Who are you with and where are you going? In CVPR 2011 (pp. 1345\u20131352). IEEE.","key":"2439_CR125","DOI":"10.1109\/CVPR.2011.5995468"},{"doi-asserted-by":"crossref","unstructured":"Yan, B., Jiang, Y., Sun, P., Wang, D., Yuan, Z., Luo, P., & Lu, H. (2022). Towards grand unification of object tracking. In European conference on computer vision (pp. 733\u2013751). Springer.","key":"2439_CR126","DOI":"10.1007\/978-3-031-19803-8_43"},{"doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., & Xu, N. (2019). Video instance segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 5188\u20135197).","key":"2439_CR127","DOI":"10.1109\/ICCV.2019.00529"},{"issue":"9","key":"2439_CR128","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1109\/TCSVT.2020.3038720","volume":"31","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Kumar, T., Chen, T., Su, J., & Luo, J. (2020). Grounding-tracking-integration. IEEE Transactions on Circuits and Systems for Video Technology, 31(9), 3433\u20133443.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"doi-asserted-by":"crossref","unstructured":"Yang, F., Wang, Z., Wu, Y., Sakti, S., & Nakamura, S. (2022). Tackling multiple object tracking with complicated motions-re-designing the integration of motion and appearance. Image and Vision Computing, 124, 104514.","key":"2439_CR129","DOI":"10.1016\/j.imavis.2022.104514"},{"doi-asserted-by":"crossref","unstructured":"Ye, Y., Xu, K., Huang, Y., Yi, R., & Cai, Z. (2024). DiffusionEdge: Diffusion probabilistic model for crisp edge detection. In Proceedings of the AAAI conference on artificial intelligence.","key":"2439_CR130","DOI":"10.1609\/aaai.v38i7.28490"},{"doi-asserted-by":"crossref","unstructured":"Yu, Q., Medioni, G., & Cohen, I. (2007). Multiple target tracking using spatio-temporal Markov Chain Monte Carlo data association. In 2007 IEEE conference on computer vision and pattern recognition (pp. 1\u20138). IEEE.","key":"2439_CR131","DOI":"10.1109\/CVPR.2007.382991"},{"doi-asserted-by":"crossref","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., & Wei, Y. (2022). Motr: End-to-end multiple-object tracking with transformer. In European conference on computer vision (pp. 659\u2013675). Springer.","key":"2439_CR132","DOI":"10.1007\/978-3-031-19812-0_38"},{"doi-asserted-by":"crossref","unstructured":"Zhang, L., Li, Y., & Nevatia, R. (2008). Global data association for multi-object tracking using network flows. In 2008 IEEE conference on computer vision and pattern recognition (pp. 1\u20138). IEEE.","key":"2439_CR133","DOI":"10.1109\/CVPR.2008.4587584"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., & Hu, W. (2020). Ocean: Object-aware anchor-free tracking. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XXI 16 (pp. 771\u2013787). Springer.","key":"2439_CR134","DOI":"10.1007\/978-3-030-58589-1_46"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022). ByteTrack: Multi-object tracking by associating every detection box. In Proceedings of the European conference on computer vision (ECCV)","key":"2439_CR135","DOI":"10.1007\/978-3-031-20047-2_1"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, T., & Zhang, X. (2023). Motrv2: Bootstrapping end-to-end multi-object tracking by pretrained object detectors. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 22056\u201322065).","key":"2439_CR136","DOI":"10.1109\/CVPR52729.2023.02112"},{"key":"2439_CR137","first-page":"45533","volume":"36","author":"J Zhang","year":"2023","unstructured":"Zhang, J., Herrmann, C., Hur, J., Cabrera, L. P., Jampani, V., Sun, D., & Yang, M. H. (2023). A tale of two features: Stable diffusion complements DINO for zero-shot semantic correspondence. Advances in Neural Information Processing Systems, 36, 45533\u201345547.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2439_CR138","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). FairMOT: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129, 3069\u20133087.","journal-title":"International Journal of Computer Vision"},{"key":"2439_CR139","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.patrec.2023.02.023","volume":"168","author":"H Zhao","year":"2023","unstructured":"Zhao, H., Wang, X., Wang, D., Lu, H., & Ruan, X. (2023). Transformer vision-language tracking via proxy token guided cross-modal fusion. Pattern Recognition Letters, 168, 10\u201316.","journal-title":"Pattern Recognition Letters"},{"doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., & Kr\u00e4henb\u00fchl, P. (2020). Tracking objects as points. In Proceedings of the European conference on computer vision (ECCV) (pp. 474\u2013490).","key":"2439_CR140","DOI":"10.1007\/978-3-030-58548-8_28"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02439-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02439-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02439-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T14:26:58Z","timestamp":1757168818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02439-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,9]]},"references-count":140,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2439"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02439-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2025,5,9]]},"assertion":[{"value":"17 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}