4 papers
First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training
Gyudong Kim, Hyukju Na, Jin Hyeon Kim +6
As training billion-scale transformers becomes increasingly common, employing multiple distributed GPUs along with parallel training methods has become a standard practice. However…
Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields
Taewoo Kim, Yujeong Chae, Hyun-Kurl Jang +1
Video Frame Interpolation (VFI) aims to generate intermediate video frames between consecutive input frames. Since the event cameras are bio-inspired sensors that only encode brigh…
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Ilhoon Yoon, Hyeongjun Kwon, Jin Kim +3
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing sign…
Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
Linh Van Ma, Tran Thien Dat Nguyen, Ba-Ngu Vo +2
We propose a 3D multi-object tracking (MOT) solution using only 2D detections from monocular cameras, which automatically initiates/terminates tracks as well as resolves track appe…