Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT).
In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
Bilingual terminologies are important resources for natural language processing (NLP) applications.
We extend the classical tracking-by-detection paradigm to this tracking-any-object task.
Ranked #1 on Multi-Object Tracking on TAO (using extra training data)
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses.
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
Experiments on this dataset showed that the proposed method can substantially reduce the training time while obtaining highly effective features and coherent temporal structures.
Relationships among objects play a crucial role in image understanding.