224 citations · 278 across the 14 of their papers we have counts for
15 papers
HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection
Ji Liu, Dong Li, Zekun Li +4
Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do…
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification
Haowei Zhu, Wenjing Ke, Dong Li +3
Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information.…
Dynamic Sparse R-CNN
Qinghang Hong, Fengming Liu, Dong Li +3
Sparse R-CNN is a recent strong object detection baseline by set prediction on sparse, learnable proposal boxes and proposal features. In this work, we propose to improve Sparse R-…
Compare learning: bi-attention network for few-shot learning
Li Ke, Meng Pan, Weigao Wen +1
Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only. One of the Few-shot learning methods cal…
Representing Videos as Discriminative Sub-graphs for Action Recognition
Dong Li, Zhaofan Qiu, Yingwei Pan +3
Human actions are typically of combinatorial structures or patterns, i.e., subjects, objects, plus spatio-temporal interactions in between. Discovering such structures is therefore…
Towards Discriminative Representation Learning for Unsupervised Person Re-identification
Takashi Isobe, Dong Li, Lu Tian +3
In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods t…