We propose a consistent end-to-end video instance segmentation framework with Inter-Frame Recurrent Attention to model both the temporal instance consistency for adjacent frames and the global temporal context.
Improving the generalization capability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge.
In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.
This dataset provides a more reliable benchmark of multi-camera, multi-object tracking systems in cluttered and crowded environments.
TransMOT effectively models the interactions of a large number of objects by arranging the trajectories of the tracked objects as a set of sparse weighted graphs, and constructing a spatial graph transformer encoder layer, a temporal transformer encoder layer, and a spatial graph transformer decoder layer based on the graphs.
Ranked #2 on Multi-Object Tracking on 2DMOT15 (using extra training data)
The average video length of LaSOT is around 2, 500 frames, where each video contains various challenge factors that exist in real world video footage, such as the targets disappearing and re-appearing.
Real-world data often follow a long-tailed distribution as the frequency of each class is typically different.
Ranked #19 on Long-tail Learning on Places-LT
However, the 3D identification and association of large-scale glomeruli on renal pathology is challenging due to large tissue deformation, missing tissues, and artifacts from WSI.
Development of next-generation electronic devices for applications call for the discovery of quantum materials hosting novel electronic, magnetic, and topological properties.
For the analysis component, given the tracking results on all sequences, it investigates the behavior of the tracker under each individual factor and generates the report automatically.
The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet).
Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters.
To address this issue, in this paper we propose an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models.
Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units.
In this paper, we present LaSOT, a high-quality benchmark for Large-scale Single Object Tracking.