The following schedule is a work in progress. Once we have the full seminar details including title, abstract and speaker bio, we will publish these talks under upcoming seminars.
| Date | Speaker | Title | Abstract |
|---|---|---|---|
| 2024-08-08 11:00 | Changsheng Lu | General Keypoint Detection: Few-shot, Zero-shot and Beyond | This talk presents the advancements in computer vision and machine learning through the lens of keypoint detection, especially relating to few-shot learning, uncertainty learning, vision transformers, and multi-modal foundation models. Existing machine learning models rely heavily on extensive human-labelled data, leading to the problem of 'no intelligence without human annotations'. To ease this issue and break the limitation of keypoint types to be detected, we introduce a versatile Few-shot Keypoint Detection (FSKD) with uncertainty learning, which can not only detect a varying number of keypoints of different kinds but also provides uncertainty estimation. Secondly, building robust keypoint representations is crucial to the success of FSKD. To achieve this, we propose a novel visual prior guided vision transformer and explore i) transductive extension of FSKD and ii) FSKD with masking and alignment (MAA). Thirdly, despite the versatility of existing FSKD models, they suffer from the scalability issue w.r.t. the number of keypoints and the large domain shift of keypoints between seen and unseen species. To address these issues, we propose a lightweight FSKD model capable of evaluating a large number of keypoints (e.g., 1000 keypoints) and improve our model with mean feature based contrastive learning to bridge the domain shift. Fourthly, we observe that our FSKD aligns with the popular 'prompt' based models used across various vision and language tasks, if treating the support image and keypoints as 'visual prompt'. Thus, we expand the prompt diversity from three aspects: modality, semantics (seen v.s. unseen), and language, to enable a more generalized zero- and few-shot keypoint detection (Z-FSKD). Finally, we demonstrate the FSKD beyond supervised setting and discuss the future directions for general keypoint detection. |
| 2024-08-15 11:00 | |||
| 2024-08-22 11:00 | |||
| 2024-08-29 11:00 | |||
| 2024-09-05 11:00 | |||
| 2024-09-12 11:00 | |||
| 2024-09-19 11:00 | |||
| 2024-09-26 11:00 | |||
| 2024-10-03 11:00 | |||
| 2024-10-10 11:00 | |||
| 2024-10-17 11:00 | |||
| 2024-10-24 11:00 | |||
| 2024-10-31 11:00 | |||
| 2024-11-07 11:00 | |||
| 2024-11-14 11:00 | |||
| 2024-11-21 11:00 | |||
| 2024-11-28 11:00 | |||
| 2024-12-05 11:00 | |||
| 2024-12-12 11:00 | |||
| 2024-12-19 11:00 | |||
| 2024-12-26 11:00 |