Zong-Tai Li

Zong-Tai Li

Auto-generated profile, based on publicly available information

Zong-Tai Li

Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 November 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YZYu Zheng
Yu Zheng
YDYueqi Duan
Yueqi Duan
ZLZongtai Li
Zongtai Li
JZJie Zhou
Jie Zhou
JLJiwen Lu
Jiwen Lu
In this paper, we propose a dynamic 3D object detector named HyperDet3D, which is adaptively adjusted based on the hyper scene-level knowledge on the fly. Existing methods strive for object-level representations of local elements and their relations without scene-level priors, which suffer from ambiguity between similarly-structured objects only based on the understanding of individual points and object candidates. Instead, we design scene-conditioned hypernetworks to simultaneously learn scene-agnostic embeddings to exploit sharable abstracts from various 3D scenes, and scene-specific knowledge which adapts the 3D detector to the given scene at test time. As a result, the lower-level ambiguity in object representations can be addressed by hierarchical context in scene priors. However, since the upstream hypernetwork in HyperDet3D takes raw scenes as input which contain noises and redundancy, it leads to sub-optimal parameters produced for the 3D detector simply under the constraint of downstream detection losses. Based on the fact that the downstream 3D detection task can be factorized into object-level semantic classification and bounding box regression, we furtherly propose HyperFormer3D by correspondingly designing their scene-level prior tasks in upstream hypernetworks, namely Semantic Occurrence and Objectness Localization . To this end, we design a transformer-based hypernetwork that translates the task-oriented scene priors into parameters of the downstream detector, which refrains from noises and redundancy of the scenes. Extensive experimental results on the ScanNet, SUN RGB-D and MatterPort3D datasets demonstrate the effectiveness of the proposed methods.

1 December 2020
Verified
Conference Paper
Closed access
WLWei-Chen Lin
Wei-Chen Lin
WHWei-Tzer Huang
Wei-Tzer Huang
HCHsin-Ching Chih
Hsin-Ching Chih
KYKai-chao Yao
Kai-chao Yao
ZLZong-Tai Li
Zong-Tai Li
CMChun-Chiang Ma
Chun-Chiang Ma
Three-phase balancing can improve the operation efficiency of distribution networks. The common approach is phase arrangement of each tapped-off point in unbalanced distribution networks. This complex problem requires searching for an optimal combination. Metaheuristic algorithms can efficiently solve this complicated problem. In this study, 10 common metaheuristic algorithms are applied in the IEEE 37- bus test system for optimal phase arrangement, and the performance of each of them is compared and discussed. The outcomes of this work are helpful for realizing energy loss reduction by phase balancing, which applies metaheuristic algorithms in unbalanced distribution networks.