Search Results for author: Kaer Huang

Found 9 papers, 1 papers with code

ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframing

no code implementations3 Jan 2025 Nisha Huang, Kaer Huang, Yifan Pu, Jiangshan Wang, Jie Guo, Yiqiang Yan, Xiu Li

However, despite their capabilities, direct conditional guidance approaches often face challenges in balancing the expressiveness of textual semantics with the diversity of output results while capturing stylistic features.

Diversity Style Transfer

PCIE_EgoHandPose Solution for EgoExo4D Hand Pose Challenge

1 code implementation18 Jun 2024 Feng Chen, Ling Ding, Kanokphan Lertniphonphan, Jian Li, Kaer Huang, Zhepeng Wang

Our approach achieved the 1st position in the Hand Pose challenge with 25. 51 MPJPE and 8. 49 PA-MPJPE.

Position

ACTrack: Adding Spatio-Temporal Condition for Visual Object Tracking

no code implementations27 Feb 2024 Yushan Han, Kaer Huang

Efficiently modeling spatio-temporal relations of objects is a key challenge in visual object tracking (VOT).

Object Visual Object Tracking

ReIDTracker Sea: the technical report of BoaTrack and SeaDronesSee-MOT challenge at MaCVi of WACV24

no code implementations12 Nov 2023 Kaer Huang, Weitu Chong

At the same time, most of the current Multi-Object Tracking algorithms still require video annotation data which is costly to obtain for training.

Multi-Object Tracking Object +1

1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges

no code implementations8 Aug 2023 Kaer Huang

for the open-world challenges, we only use 64 classes (Intersection classes of BURST Train subset and COCO dataset, without LVIS dataset) annotations data training, and testing on BURST test set data and get 61. 4 OWTAall, ranking 1st in the benchmark.

Instance Segmentation Semantic Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.