A Gated Attention Transformer for Multi-Person Pose Tracking
원문 초록
Multi-person pose tracking is an important element for many applications and requires to estimate the human poses of all persons in a video and to track them over time. The association of poses across frames remains an open research problem, in particular for online tracking methods, due to motion blur, crowded scenes and occlusions. To tackle the association challenge, we propose a Gated Attention Transformer. The core aspect of our model is the gating mechanism that automatically adapts the impact of appearance embeddings and embeddings based on temporal pose similarity in the attention layers. In order to re-identify persons that have been occluded, we incorporate a pose-conditioned re-identification network that provides initial embeddings and allows to match persons even if the number of visible joints differ between frames. We further propose a matching layer based on gated attention for pose-to-track association and duplicate removal. We evaluate our approach on PoseTrack 2018 and PoseTrack21.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
Embracing Dynamics: Dynamics-aware 4D Gaussian Splatting SLAM
Stereo Event-based, 6-DOF Pose Tracking for Uncooperative Spacecraft
Segment Anything in Light Fields for Real-Time Applications via Constrained Prompting
ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
토론
이 논문과 연결된 포럼 글이 아직 없습니다.