IIS Computer Vision & Machine Learning Lab

Selected Publications

• Li-Heng Wang, YuJu Cheng and Tyng-Luh Liu, Tracking Everything Everywhere across Multiple Cameras, The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA, February 2025. (AAAI-2025)

• Cheng-Yao Hong and Tyng-Luh Liu, Multimodal Promptable Token Merging for Diffusion Models, The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA, February 2025. (AAAI-2025)

• Pei-Kai Huang, Jun-Xiong Chong, Cheng-Hsuan Chiang, Tzu-Hsien Chen, Tyng-Luh Liu and Chiou-Ting Hsu, SLIP: Spoof-aware One-class Face Anti-Spoofing with Language Image Pretraining, The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA, February 2025. (AAAI-2025)

• Chieh Liu, Yu-Min Chu, Ting-I Hsieh, Hwann-Tzong Chen and Tyng-Luh Liu, Learning Diffusion Models for Multi-View Anomaly Detection, 18th European Conference on Computer Vision, Milan, Italy, September 2024. (ECCV-2024)

• Chih-Jung Tsai, Hwann-Tzong Chen and Tyng-Luh Liu, Pseudo-Embedding for Generalized Few-Shot 3D Segmentation, 18th European Conference on Computer Vision, Milan, Italy, September 2024. (ECCV-2024)

• Cheng-Yao Hong, Yen-Chi Hsu and Tyng-Luh Liu, Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking, IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, June 2024. (CVPR-2024)

• Pei-Kai Huang, Cheng-Hsuan Chiang, Tzu-Hsien Chen, Jun-Xiong Chong, Tyng-Luh Liu and Chiou-ting Hsu, One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning, IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, June 2024. (CVPR-2024)

• Cheng-Yao Hong, Yu-Ying Chou and Tyng-Luh Liu, Attention Discriminant Sampling for Point Clouds, International Conference on Computer Vision, Paris, France, October 2023. (ICCV-2023)

• Yen-Chi Hsu, Cheng-Yao Hong, Ming-Sui Lee, Davi Geiger and Tyng-Luh Liu,  ABC-Norm Regularization for Fine-Grained and Long-Tailed Image Classification,  IEEE Transactions on Image Processing, volume 32, pages 3885-3896, July 2023. (TIP)

• Yu-Min Chu, Chieh Liu, Ting-I Hsieh, Hwann-Tzong Chen and Tyng-Luh Liu, Shape-Guided Dual-Memory Learning for 3D Anomaly Detection, 40th International Conference on Machine Learning , Hawaii, USA, July 2023. (ICML-2023)

• Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen and Yann LeCun, Decoupled Contrastiv Learning, 17th European Conference on Computer Vision, Tel-Aviv, Israel, October 2022. (ECCV-2022)

• Jhih-Ciang Wu, He-Yen Hsieh, Ding-Jie Chen, Chiou-Shann Fuh and Tyng-Luh Liu, Self-Supervised Sparse Representation for Video Anomaly Detection, 17th European Conference on Computer Vision, Tel-Aviv, Israel, October 2022. (ECCV-2022)

• Wen-Li Wei, Jen-Chun Lin, Tyng-Luh Liu, and Hong-Yuan Mark Liao, Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video, IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2022. (CVPR-2022)

• Ta-Ying Cheng, Hsuan-ru Yang, Niki Trigoni, Hwann-Tzong Chen and Tyng-Luh Liu, Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction, Thirty-Sixth AAAI Conference on Artificial Intelligence, February 2022. (AAAI-2022)

• Jhih-Ciang Wu, Ding-Jie Chen, Chiou-Shann Fuh, Tyng-Luh Liu, Learning Unsupervised Metaformer for Anomaly Detection, International Conference on Computer Vision, October 2021. (ICCV-2021)

• Ding-Jie Chen, He-Yen Hsieh and Tyng-Luh Liu, Adaptive Image Transformer for One-Shot Object Detection, IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2021. (CVPR-2021)

• Yu-Ying Chou, Hsuan-Tien Lin and Tyng-Luh Liu, Adaptive and Generative Zero-Shot Learning, Ninth International Conference on Learning Representations, May 2021. (ICLR-2021)

• Ding-Jie Chen, He-Yen Hsieh and Tyng-Luh Liu, Referring Image Segmentation via Language-Driven Attention, International Conference on Robotics and Automation, May 2021. (ICRA-2021)

• Pin-Hao Huang, Han-Hung Lee, Hwann-Tzong Chen and Tyng-Luh Liu, Text-guided Graph Neural Networks for Referring 3D Instance Segmentation, Thirty-Fifth AAAI Conference on Artificial Intelligence, February 2021. (AAAI-2021)

• Jen-Chun Lin, Wen-Li Wei, Yen-Yu Lin, Tyng-Luh Liu, and Hong-Yuan Mark Liao, Learning From Music to Visual Storytelling of Shots: A Deep Interactive Learning Mechanism, ACM Multimedia Conference, Online (Seattle, USA), October 2020. (MM-2020)

• Hsien-Tzu Cheng, Chun-Fu Yeh, Po-Chen Kuo, Andy Wei, Keng-Chi Liu, Mong-Chi Ko, Kuan-Hua Chao, Yu-Ching Peng, and Tyng-Luh Liu, Self-similarity Student for Partial Label Histopathology Image Segmentation, 16th European Conference on Computer Vision, August 2020. (ECCV-2020)

• Yen-Chi Hsu, Cheng-Yao Hong, Ming-Sui Lee and Tyng-Luh Liu, Query-Driven Multi-Instance Learning, Thirty-Fourth AAAI Conference on Artificial Intelligence, February 2020. (AAAI-2020)

• Ting-I Hsieh, Yi-Chen Lo, Hwann-Tzong Chen, and Tyng-Luh Liu, One-Shot Object Detection with Co-Attention and Co-Excitation, Thirty-third Conference on Neural Information Processing Systems, December 2019. (NeurIPS-2019)

• Jen-Chun Lin, Wen-Li Wei, Tyng-Luh Liu, C.-C. Jay Kuo and Mark Liao, Tell Me Where It is Still Blurry: Adversarial Blurred Region Mining and Refining, ACM Multimedia Conference, October 2019. (MM-2019)

• Ding-Jie Chen, Songhao Jia, Yi-Chen Lo, Hwann-Tzong Chen, and Tyng-Luh Liu, See-through-Text Grouping for Referring Image Segmentation, International Conference on Computer Vision, October 2019. (ICCV-2019)

• Ding-Jie Chen, Jui-Ting Chien, Hwann-Tzong Chen, and Tyng-Luh Liu, Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects, Thirty-Third AAAI Conference on Artificial Intelligence, January 2019. (AAAI-2019)

• Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, and Min Sun, Cube Padding for Weakly-Supervised Saliency Prediction in 360 Videos, IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, June 2018. (CVPR-2018)

• Jyh-Jing Hwang and Tyng-Luh Liu, "Pixel-wise Deep Learning for Contour Detection," International Conference on Learning Representations, May 2015. (ICLR- 2015)

• Kai-Yueh Chang, Tyng-Luh Liu*, Hwann-Tzong Chen, and Shang-Hong Lai. Fusing Generic Objectness and Visual Saliency for Salient Object Detection. 13th International Conference on Computer Vision, Barcelona, Spain, November 2011. (ICCV-2011)

• Kai-Yueh Chang, Tyng-Luh Liu*, and Shang-Hong Lai. From Co-saliency to Co-segmentation: An Efficient and Fully Unsupervised Energy Minimization Model. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, June 2011. (CVPR-2011)

• Yen-Yu Lin, Tyng-Luh Liu*, and Chiou-Shann Fuh. Multiple Kernel Learning for Dimensionality Reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 6, pp. 1147-1160, 2011. (TPAMI)

• Yen-Yu Lin, Tyng-Luh Liu*, and Chiou-Shann Fuh. Clustering Complex Data with Group-Dependent Feature Selection. 11th European Conference on Computer Vision, Crete, Greece, September 2010. (ECCV-2010)

• Yen-Yu Lin, Jyun-Fan Tsai, and Tyng-Luh Liu*. Efficient Discriminative Local Learning for Object Recognition. 12th IEEE International Conference on Computer Vision, Kyoto, Japan, September 2009. (ICCV-2009)

• Kai-Yueh Chang, Tyng-Luh Liu*, and Shang-Hong Lai. Learning Partially Observed Hidden Conditional Random Fields for Facial Expression Recognition. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009. (CVPR-2009)

• Yen-Yu Lin, Tyng-Luh Liu*, and Chiou-Shann Fuh. Dimensionality Reduction for Data in Multiple Feature Representations. Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, Canada, December 2008. (NIPS-2008)

• Tien-Lung Chang, Tyng-Luh Liu*, and Jen-Hui Chuang. Improving Local Learning for Object Categorization by Exploring the Effects of Ranking. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, June 2008. (CVPR-2008)

• Yen-Yu Lin, Tyng-Luh Liu*, and Chiou-Shann Fuh. Local Ensemble Kernel Learning for Object Category Recognition. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, June 2007. (CVPR-2007)

• Hwann-Tzong Chen, Tyng-Luh Liu*, and Chiou-Shann Fuh. Segmenting Highly Articulated Video Objects with Weak-Prior Random Forests. 9th European Conference on Computer Vision, Lecture Notes in Computer Science 3954, pp. 373-385, Graz, Austria, May 2006. (ECCV-2006)

• Tien-Lung Chang, Tyng-Luh Liu*, and Jen-Hui Chuang. Direct Energy Minimization for Super-Resolution on Nonlinear Manifolds. 9th European Conference on Computer Vision, Lecture Notes in Computer Science 3954, pp. 281-294, Graz, Austria, May 2006. (ECCV-2006)

• Hwann-Tzong Chen, Tyng-Luh Liu*, and Chiou-Shann Fuh. Tone Reproduction: A Perspective from Luminance-Driven Perceptual Grouping. International Journal of Computer Vision, vol. 65, no. 1-2, pp. 73-96, November 2005. (IJCV)

• Yen-Yu Lin, Tyng-Luh Liu*, and Hwann-Tzong Chen. Semantic Manifold Learning for Image Retrieval. 13th Annual ACM International Conference on Multimedia, pp. 249-258, Singapore, November 2005. (ACM MM-2005, Best Student Papers Session)

• Hwann-Tzong Chen, Tyng-Luh Liu*, and Chiou-Shann Fuh. Learning Effective Image Metrics from Few Pairwise Examples. 10th IEEE International Conference on Computer Vision, Beijing, China, October 2005. (ICCV-2005)

• Hwann-Tzong Chen, Huang-Wei Chang, and Tyng-Luh Liu*. Local Discriminant Embedding and Its Variants. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 846-853, San Diego, CA, USA, June 2005. (CVPR-2005)

• Yen-Yu Lin and Tyng-Luh Liu*. Robust Face Detection with Multi-Class Boosting. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 679-686, San Diego, CA, USA, June 2005. (CVPR-2005)

• Hwann-Tzong Chen, Tyng-Luh Liu*, and Tien-Lung Chang. Tone Reproduction: A Perspective from Luminance-Driven Perceptual Grouping. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 369-376, San Diego, CA, USA, June 2005. (CVPR-2005)

• Yen-Yu Lin, Tyng-Luh Liu*, and Chiou-Shann Fuh. Fast Object Detection with Occlusions. 8th European Conference on Computer Vision, Lecture Notes in Computer Science 3021, pp. 402-413, Prague, Czech Republic, May 2004. (ECCV-2004)

• Tyng-Luh Liu* and Hwann-Tzong Chen. Real-Time Tracking Using Trust-Region Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 3, pp. 397-402, March 2004. (TPAMI)

• Davi Geiger, Tyng-Luh Liu, and Robert V. Kohn. Representation and Self-Similarity of Shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 1, pp. 86-99, January 2003. (TPAMI)

• Hwann-Tzong Chen, Horng-Horng Lin, and Tyng-Luh Liu*. Multi-Object Tracking Using Dynamical Graph Matching. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 210-217, Kauai, Hawaii, December 2001. (CVPR-2001)

• Hwann-Tzong Chen and Tyng-Luh Liu*. Trust-Region Methods for Real-Time Tracking. 8th International Conference on Computer Vision, Vol. 2, pp. 717-722, Vancouver, Canada, July 2001. (ICCV-2001)

• Davi Geiger, Tyng-Luh Liu, and Michael J. Donahue. Sparse Representations for Image Decompositions, International Journal of Computer Vision, vol. 33(2), pp. 139-156, September 1999. (IJCV)

• Tyng-Luh Liu* and Davi Geiger. Approximate Tree Matching and Shape Similarity. 7th International Conference on Computer Vision, pp. 456-462, Kerkyra, Greece, September 1999. (ICCV-1999)

• Tyng-Luh Liu, Davi Geiger, and Robert V. Kohn. Representation and Self-Similarity of Shapes. 6th International Conference on Computer Vision, pp. 1129-1135, Bombay, India, January 1998. (ICCV-1998)

• Mike Donahue, Davi Geiger, Robert Hummel, and Tyng-Luh Liu. Sparse Representations for Image Decomposition with Occlusions. Proc. Computer Vision and Pattern Recognition, pp. 7-12, San Francisco, 1996. (CVPR-1996)

• Tyng-Luh Liu, Mike Donahue, Davi Geiger, and Robert Hummel. Image Recognition with Occlusions. 4th European Conf. on Computer Vision, Lecture Notes in Computer Science 1064, pp. 556-565, Cambridge, UK, 1996. (ECCV-1996)

Other Publications

• Tsung-Yu Lin and Tyng-Luh Liu. Efficient Binary Codes for Extremely High-dimensional Data. IEEE International Conference on Image Processing, October 2014, (ICIP-2014)

• Tyng-Luh Liu, Kai-Yueh Chang and Shang-Hong Lai. Exploring Depth Information for Object Segmentation and Detection. International Conference on Pattern Recognition, August 2014, (ICPR-2014)

• Chun-Wei Liu and Tyng-Luh Liu. A Sparse Linear Model for Saliency-Guided Decolorization. IEEE International Conference on Image Processsing, Melbourne, Australia, September 2013, (ICIP-2013)

• Ching-Ting Tu, Kung-Hung Lin and Tyng-Luh Liu. A Two-dimensional Direct Combined Model for Facial Hallucination. IAPR International Conference on Machine Vision Applications, Kyoto, Japan, May 2013.

• Horng-Horng Lin, Jen-Hui Chuang, and Tyng-Luh Liu. Regularized Background Adaptation: A Novel Learning Rate Control Scheme for Gaussian Mixture Modeling. IEEE Transactions on Image Processing, volume 20, number 3, pages 822-836, March 2011. (TIP)

• Yu-Wu Chu and Tyng-Luh Liu. Co-occurrence Random Forests for Object Localization and Classification. 9th Asian Conference on Computer Vision, Xian, China, September 2009. (ACCV-2009)

• Horng-Horng Lin, Tyng-Luh Liu, and Jen-Hui Chuang. Learning a Scene Background Model via Classification. IEEE Transactions on Signal Processing, Vol. 57, No. 5, pp. 1641-1654, May 2009. (TSP)

• Hwann-Tzong Chen and Tyng-Luh Liu. Finding Familiar Objects and Their Depth from a Single Image. IEEE International Conference on Image Processing, San Antonio, Texas, USA, September 2007. (ICIP-2007)

• Yen-Yu Lin and Tyng-Luh Liu. Shape Recognition Using Fast Boosted Filtering. IEEE International Conference on Image Processing, Genova, Italy, September 2005. (ICIP-2005)

• Hwann-Tzong Chen, Tyng-Luh Liu, and Chiou-Shann Fuh. Probabilistic Tracking with Adaptive Feature Selection. International Conference on Pattern Recognition, Cambridge, UK, August 2004. (ICPR-2004)

• Tien-Lung Chang and Tyng-Luh Liu. Detecting Deformable Objects with Flexible Shape Priors. 17th International Conference on Pattern Recognition, Cambridge, UK, August 2004. (ICPR-2004)

• Hwann-Tzong Chen, Tyng-Luh Liu, and Chiou-Shann Fuh. On the Distribution-Based Tracking Systems. IEEE International Conference on Networking, Sensing and Control, March 2004. (Invited paper)

• Horng-Horng Lin, Tyng-Luh Liu, and Jen-Hui Chuang. Probabilistic SVM Approach for Background Scene Initialization. IEEE International Conference on Image Processing, Rochester, New York, September 2002. (ICIP-2002)

• Hwann-Tzong Chen and Tyng-Luh Liu. Probabilistic Tracking with Optimal Scale and Orientation Selection. 16th International Conference on Pattern Recognition, Quebec, Canada, August 2002. (ICPR-2002)

• Tyng-Luh Liu and Hwann-Tzong Chen. A Variational Approach for Digital Watermarking. IEEE International Conference on Image Processing, Vancouver, Canada, September 2000. (ICIP-2000)

• Tyng-Luh Liu. A Generalized Shape-Axis Model for Planar Shapes. 15th International Conference on Pattern Recognition, Barcelona, Spain, September 2000. (ICPR-2000)

• Tyng-Luh Liu, Davi Geiger, and Alan Yuille. Segmenting by Seeking the Symmetry Axis. 14th International Conference on Pattern Recognition, pp. 994-998, Brisbane, Australia, August 1998. (ICPR-1998)

• Tyng-Luh Liu and Davi Geiger. Visual Deconstruction: Recognizing Articulated Objects. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, Lecture Notes in Computer Science 1223, pp. 295-309, Venice, Italy, 1997. (EMMCVPR-1997)

• Davi Geiger and Tyng-Luh Liu. Recognizing Articulated Objects with Information Theoretic Methods. 2nd International Conference on Automatic Face and Gesture Recognition, pp. 45-50, Killington, Vermont, 1996. (FG-1996)