Research

A bit about my research

My research interest mainly lies in computer vision and image analysis using machine learning techniques. Specifically, I develop algorithms for learning representations, understanding people, and segmenting images. Below is a selection of my publications, the details of which can be found on Google Scholar.

L. Zhao*, N.B. Gundavarapu*, L. Yuan*, H. Zhou*, S. Yan**, J.J. Sun**, L. Friedman**, R. Qian**, T. Weyand, Y. Zhao, R. Hornung, F. Schroff, M.-H. Yang, D.A. Ross, H. Wang, H. Adam , M. Sirotenko***, T. Liu***, B. Gong***. VideoPrism: A foundational visual encoder for video understanding. ICML 2024. [arXiv][Google AI Blog] (* Equal primary contribution; ** Equal core technical contribution; *** Equal senior contribution, project leads)
Y. Zhao, L. Zhao, X. Zhou, J. Wu, C.-T. Chu, H. Miao, F. Schroff, H. Adam, T. Liu, B. Gong, P. Krähenbühl, L. Yuan. Distilling vision-language models on millions of videos. CVPR 2024. [arXiv]

Y. Xiong, L. Zhao, B. Gong, M.-H. Yang, F. Schroff, T. Liu, C.-J. Hsieh, L. Yuan. Structured video-language modeling with temporal grouping and spatial grounding. ICLR 2024. [arXiv]

Z. Li, L. Zhao, Z. Zhang, H. Zhang, D. Liu, T. Liu, D.N. Metaxas. Steering prototype with prompt-tuning for rehearsal-free continual learning. WACV 2024. [arXiv]

L. Yuan*, N.B. Gundavarapu*, L. Zhao*, H. Zhou*, Y. Cui, L. Jiang, X. Yang, M. Jia, T. Weyand, L. Friedman, M. Sirotenko, H. Wang, F. Schroff, M.-H. Yang, T. Liu, B. Gong. VideoGLUE: Video general understanding evaluation of foundation models. arXiv:2307.03166, 2023. [arXiv] (* Equal contribution)

L. Zhao, L. Yuan, B. Gong, Y. Cui, F. Schroff, M.-H. Yang, H. Adam, T. Liu. Unified visual relationship detection with vision and language models. ICCV 2023. [arXiv]

Q. Wang, L. Zhao, L. Yuan, T. Liu, X. Peng. Learning from semantic alignment between unpaired multiviews for egocentric video recognition. ICCV 2023. [arXiv]

Z. Xu*, M.D. Collins*, Y. Wang, L. Panait, S. Oh, S. Augenstein, T. Liu, F. Schroff, H.B. McMahan. Learning to generate image embeddings with user-level differential privacy. arXiv:2211.10844, 2022. [arXiv] (* Equal contribution)

T.R. Scott, T. Liu, M.C. Mozer, A.C. Gallagher. An Empirical Study on Clustering Pretrained Embeddings: Is deep strictly better? arXiv:2211.05183, 2022. [arXiv]

R. Qian, Y. Li, L. Yuan, B. Gong, T. Liu, M. Brown, S. Belongie, M.-H. Yang, H. Adam, Y. Cui. On temporal granularity in self-supervised video representation learning. BMVC 2022. [arXiv]

H. Zhou, A. Kadav, A. Shamsian, S. Geng, F. Lai, L. Zhao, T. Liu, M. Kapadia, H.P. Graf. COMPOSER: Compositional reasoning of group activity in videos with keypoint-only modality. ECCV 2022. [arXiv][Code]

L. Yuan, R. Qian, Y. Cui, B. Gong, F. Schroff, M.-H. Yang, H. Adam, T. Liu. Contextualized spatio-temporal contrastive learning with self-supervision. CVPR 2022. [arXiv]

J. Zheng, X. Shi, A. Gorban, J. Mao, Y. Song, C.R. Qi, T. Liu, V. V. Chari, A. Cronman, Y. Zhou, C. Li, D. Anguelov. Multi-modal 3D human pose estimation with 2D weak supervision in autonomous driving. CVPR 2022 Workshop on Autonomous Driving. [arXiv]

J. Zhuang, B. Gong, L. Yuan, Y. Cui, H. Adam, N.C. Dvornek, S. Tatikonda, J.S. Duncan, T. Liu. Surrogate gap minimization improves sharpness-aware training. ICLR 2022. [OpenReview][arXiv][Website]

T. Liu*, J.J. Sun*, L. Zhao, J. Zhao, L. Yuan, Y. Wang, L.-C. Chen, F. Schroff, H. Adam. View-invariant, occlusion-robust probabilistic embedding for human pose. International Journal of Computer Vision (IJCV), 130, 111-135, 2022 (Published 11/16/21). [Publisher][arXiv][Google AI Blog][Code][Website] (* Equal contribution)

L. Zhao, Y. Wang, J. Zhao, L. Yuan, F. Schroff, H. Adam, X. Peng, D.N. Metaxas, T. Liu. Learning view-disentangled human pose representation by contrastive cross-view mutual information maximization. CVPR 2021 (Oral). [arXiv]

L. Zhao, T. Liu, X. Peng, D.N. Metaxas. Maximum-entropy adversarial data augmentation for improved generalization and robustness. NeurIPS 2020. [arXiv][Code]

J.J. Sun, J. Zhao, L.-C. Chen, F. Schroff, H. Adam, T. Liu. View-Invariant probabilistic embedding for human pose. ECCV 2020 (Spotlight). [arXiv][Google AI Blog][Presentation][Short Presentation][Code][Website]

B. Cheng, M.D. Collins, Y. Zhu, T. Liu, T.S. Huang, H. Adam, L.-C. Chen. Panoptic-DeepLab: A simple, strong, and fast baseline for bottom-up panoptic segmentation. CVPR 2020. [arXiv][Code]

J.J. Sun, T. Liu, A.S. Cowen, F. Schroff, H. Adam, G. Prasad. EEV Dataset: Predicting expressions evoked by diverse videos. arXiv:2001.05488, 2020. [arXiv][CVPR'21 Workshop]

B. Cheng, M.D. Collins, Y. Zhu, T. Liu, T.S. Huang, H. Adam, L.-C. Chen. Panoptic-DeepLab. ICCV 2019 Joint COCO and Mapillary Recognition Workshop (Winner of the Mapillary Vista Panoptic Segmentation Task, Best Paper and Most Innovative Award). [arXiv][Code]

T.-J. Yang, M.D. Collins, Y. Zhu, J.-J. Hwang, T. Liu, X. Zhang, V. Sze, G. Papandreou, L.-C. Chen. DeeperLab: Single-shot image parser. arXiv:1902.05093, 2019. [arXiv]

J.J. Sun, T. Liu, G. Prasad. GLA in MediaEval 2018 Emotional Impact of Movies Task. MediaEval 2018 Multimedia Benchmark Workshop (Winner of the Emotional Impact of Movies Task). [arXiv][Presentation]

P. Nguyen*, T. Liu*, G. Prasad, B. Han. Weakly supervised action localization by sparse temporal pooling network. CVPR 2018. [arXiv][Code] (* Equal contribution)

T. Liu, M. Zhang, M. Javanmardi, N. Ramesh, T. Tasdizen. SSHMT: Semi-supervised hierarchical merge tree for electron microscopy image segmentation. ECCV 2016 (Spotlight). [arXiv][Presentation][Code]

T. Liu, M. Seyedhosseini, T. Tasdizen. Image segmentation using hierarchical merge tree. IEEE Transactions on Image Processing, 25, pp. 4596--4607, 2016. [Publisher][arXiv][Code]

M. Javanmardi, M. Sajjadi, T. Liu, T. Tasdizen. Unsupervised total variational loss for semi-supervised learning of semantic segmentation. arXiv: 1605.01368, 2016. [arXiv]

I. Arganda-Carreras, S.C. Turaga, D.R. Berger, D. Ciresan, A. Giusti, L.M. Gambardella, J. Schmidhuber, D. Laptev, S. Dwivedi, J.M. Buhmann, T. Liu, M. Seyedhosseini, T. Tasdizen, L. Kamentsky, R. Burget, V. Uher, X. Tan, C. Sun, T.D. Pham, E. Bas, M.G. Uzunbas, A. Cardona, J. Schindelin, H.S. Seung. Crowdsourcing the creation of image segmentation algorithms for connectomics. Frontiers in Neuroanatomy, 9:142, 2015. [Publisher][PDF]

C. Jones, T. Liu, N.W. Cohan, M.H. Ellisman, T. Tasdizen. Efficient semi-automatic 3D segmentation for neuron tracing in electron microscopy images. Journal of Neuroscience Methods, 246, pp. 13--21, 2015. [Publisher]

T. Liu, C. Jones, M. Seyedhosseini, T. Tasdizen. A modular approach to 3D electron microscopy image segmentation. Journal of Neuroscience Methods, 226, 88--102, 2014. [PDF][Code]

T. Tasdizen, M. Seyedhosseini, T. Liu, C. Jones, E. Jurrus. Image segmentation for connectomics using machine learning. Computational Intelligence in Biomedical Imaging, pp. 237--278, Springer New York, 2014. [Publisher]

T. Liu, M. Seyedhosseini, M.H. Ellisman, T. Tasdizen. Watershed merge forest classification for electron microscopy image stack segmentation. ICIP 2013. [PDF]

C. Jones, T. Liu, M.H. Ellisman, T. Tasdizen. Semi-automatic neuron segmentation in electron microscopy images via sparse labeling. ISBI 2013. [PDF]

T. Liu, E. Jurrus, M. Seyedhosseini, M.H. Ellisman, T. Tasdizen. Watershed merge tree classification for electron microscopy image segmentation. ICPR 2012. [PDF][Code]