110 citations · 202 across the 10 of their papers we have counts for
10 papers
Divert More Attention to Vision-Language Object Tracking
Mingzhe Guo, Zhipeng Zhang, Liping Jing +2
Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundament…
Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection
Zhenyu Li, Zhipeng Zhang, Heng Fan +4
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework. Specifically, having observed that the bottleneck of this…
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection
Linfeng Zhang, Yukang Shi, Hung-Shuo Tai +4
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. Howev…
Divert More Attention to Vision-Language Tracking
Mingzhe Guo, Zhipeng Zhang, Heng Fan +1
Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by l…
Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information
Zhipeng Zhang, Xinglin Hou, Kai Niu +5
Recently, online shopping has gradually become a common way of shopping for people all over the world. Wonderful merchandise advertisements often attract more people to buy. These…
One More Check: Making "Fake Background" Be Tracked Again
Chao Liang, Zhipeng Zhang, Xue Zhou +2
The one-shot multi-object tracking, which integrates object detection and ID embedding extraction into a unified network, has achieved groundbreaking results in recent years. Howev…
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
Xiao Wang, Xiujun Shu, Zhipeng Zhang +4
Tracking by natural language specification is a new rising research topic that aims at locating the target object in the video sequence based on its language description. Compared…
Rethinking the competition between detection and ReID in Multi-Object Tracking
Chao Liang, Zhipeng Zhang, Xue Zhou +3
Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However,…
Ocean: Object-aware Anchor-free Tracking
Zhipeng Zhang, Houwen Peng, Jianlong Fu +2
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying…
Deeper and Wider Siamese Networks for Real-Time Visual Tracking
Zhipeng Zhang, Houwen Peng
Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone networks used in Siamese trackers are relatively…