| Monodtr: Monocular 3d object detection with depth-aware transformer KC Huang, TH Wu, HT Su, WH Hsu CVPR 2022, 2022 | 184 | 2022 |
| Dual-awareness attention for few-shot object detection TI Chen, YC Liu, HT Su, YC Chang, YH Lin, JF Yeh, WC Chen, W Hsu TMM, 2021 | 130 | 2021 |
| Redal: Region-based and diversity-aware active learning for point cloud semantic segmentation TH Wu, YC Liu, YK Huang, HY Lee, HT Su, PC Huang, WH Hsu ICCV 2021, 2021 | 91 | 2021 |
| Learning from 2d: Contrastive pixel-to-point knowledge transfer for 3d pretraining YC Liu, YK Huang, HY Chiang, HT Su, ZY Liu, CT Chen, CY Tseng, ... arXiv preprint arXiv:2104.04687, 2021 | 89 | 2021 |
| Class-agnostic few-shot object counting SD Yang, HT Su, WH Hsu, WC Chen WACV 2021, 2021 | 85 | 2021 |
| End-to-end video question-answer generation with generator-pretester network HT Su, CH Chang, PW Shen, YS Wang, YL Chang, YC Chang, PJ Cheng, ... TCSVT, 2021 | 34 | 2021 |
| Multivariate and propagation graph attention network for spatial-temporal prediction with outdoor cellular traffic CY Lin, HT Su, SL Tung, WH Hsu CIKM 2021, 2021 | 23 | 2021 |
| Gdn: A coarse-to-fine (c2f) representation for end-to-end 6-dof grasp detection KY Jeng, YC Liu, ZY Liu, JW Wang, YL Chang, HT Su, W Hsu CoRL 2020, 2021 | 22 | 2021 |
| S3: Learnable sparse signal superdensity for guided depth estimation YK Huang, YC Liu, TH Wu, HT Su, YC Chang, TL Tsou, YA Wang, ... CVPR 2021, 2021 | 22 | 2021 |
| DECCNet: Depth enhanced crowd counting SD Yang, HT Su, WH Hsu, WC Chen ICCVW 2019, 2019 | 21 | 2019 |
| Ocid-ref: A 3d robotic dataset with embodied language for clutter scene grounding KJ Wang*, YH Liu*, HT Su, JW Wang, YS Wang, WH Hsu, WC Chen NAACL 2021, 2021 | 18 | 2021 |
| Situation and behavior understanding by trope detection on films CH Chang*, HT Su*, JH Hsu, YS Wang, YC Chang, ZY Liu, YL Chang, ... WWW 2021, 2021 | 15 | 2021 |
| Video question generation via semantic rich cross-modal self-attention networks learning YS Wang*, HT Su*, CH Chang, ZY Liu, WH Hsu ICASSP 2020, 2020 | 11* | 2020 |
| Language models are causal knowledge extractors for zero-shot video question answering HT Su, Y Niu, X Lin, WH Hsu, SF Chang CVPRW 2023, 2023 | 9 | 2023 |
| Stage conscious attention network (scan): A demonstration-conditioned policy for few-shot imitation JF Yeh, CM Chung, HT Su, YT Chen, WH Hsu AAAI 2022, 2022 | 6 | 2022 |
| TrUMAn: Trope Understanding in Movies and Animations HT Su, PW Shen, BC Tsai, WF Cheng, KJ Wang, WH Hsu CIKM 2021, 2021 | 6 | 2021 |
| Cross-domain hallucination network for fine-grained object recognition JF Lin, YL Lin, EK King, HT Su, WH Hsu CVPRW 2018, 2018 | 5 | 2018 |
| BIRD-PCC: Bi-Directional Range Image-Based Deep Lidar Point Cloud Compression CS Liu, JF Yeh, H Hsu, HT Su, MS Lee, WH Hsu ICASSP 2023, 2023 | 4 | 2023 |
| Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change CC Chyou, HT Su, WH Hsu ICMLW 2023, 2023 | 3 | 2023 |
| Role aware multi-party dialogue question answering JH Hsu, PW Shen, HT Su, CH Chang, JF Yeh, WH Hsu ICASSP 2021, 2021 | 3 | 2021 |
Winston HsuProfessor at CS Dept., National Taiwan Univ. | co-founder at thingnario | ex-CTO/VP at MobileDriveZweryfikowany adres z ntu.edu.tw