Feature extractor plays a critical role in text recognition (TR), but customizing its architecture is relatively less explored due to expensive manual tweaking. In this work, inspired by the success of neural architecture search (NAS), we propose to search for suitable feature extractors. We design a domain-specific search space by exploring principles for having good feature extractors. The space includes a 3D-structured space for the spatial model and a transformed-based space for the sequential model. As the space is huge and complexly structured, no existing NAS algorithms can be applied. We propose a two-stage algorithm to effectively search in the space. In the first stage, we cut the space into several blocks and progressively train each block with the help of an auxiliary head. We introduce the latency constraint into the second stage and search sub-network from the trained supernet via natural gradient descent. In experiments, a series of ablation studies are performed to better understand the designed space, search algorithm, and searched architectures. We also compare the proposed method with various state-of-the-art ones on both hand-written and scene TR tasks. Extensive results show that our approach can achieve better recognition performance with less latency.

Semantic mapping is the task of providing a robot with a map of its environment beyond the open, navigable space of traditional Simultaneous Localization and Mapping (SLAM) algorithms by attaching semantics to locations. The system presented in this work reads door placards to annotate the locations of offices. Whereas prior work on this system developed hand-crafted detectors, this system leverages YOLOv5 for sign detection and EAST for text recognition. Placards are localized by computing their pose from a point cloud in a RGB-D camera frame localized by a modified ORB-SLAM. Semantic mapping is accomplished in a post-processing step after robot exploration from video recording. System performance is reported in terms of the number of placards identified, the accuracy of their placement onto a SLAM map, the accuracy of the map built, and the correctness transcribed placard text.

This report describes our speaker verification systems for the tasks of the CN-Celeb Speaker Recognition Challenge 2022 (CNSRC 2022). This challenge includes two tasks, namely speaker verification(SV) and speaker retrieval(SR). The SV task involves two tracks: fixed track and open track. In the fixed track, we only used CN-Celeb.T as the training set. For the open track of the SV task and SR task, we added our open-source audio data. The ResNet-based, RepVGG-based, and TDNN-based architectures were developed for this challenge. Global statistic pooling structure and MQMHA pooling structure were used to aggregate the frame-level features across time to obtain utterance-level representation. We adopted AM-Softmax and AAM-Softmax combined with the Sub-Center method to classify the resulting embeddings. We also used the Large-Margin Fine-Tuning strategy to further improve the model performance. In the backend, Sub-Mean and AS-Norm were used. In the SV task fixed track, our system was a fusion of five models, and two models were fused in the SV task open track. And we used a single system in the SR task. Our approach leads to superior performance and comes the 1st place in the open track of the SV task, the 2nd place in the fixed track of the SV task, and the 3rd place in the SR task.

In this paper, we describe the top-scoring submissions for team RTZR VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22) in the closed dataset, speaker verification Track 1. The top performed system is a fusion of 7 models, which contains 3 different types of model architectures. We focus on training models to learn extra-temporal information. Therefore, all models were trained with 4-6 second frames for each utterance. Also, we apply the Large Margin Fine-tuning strategy which has shown good performance on the previous challenges for some of our fusion models. While the evaluation process, we apply the scoring methods with adaptive symmetric normalization (AS-Norm) and matrix score average (MSA). Finally, we mix up models with logistic regression to fuse all the trained models. The final submission achieves 0.165 DCF and 2.912% EER on the VoxSRC22 test set.

In this technical report, we describe the Royalflush submissions for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). Our submissions contain track 1, which is for supervised speaker verification and track 3, which is for semi-supervised speaker verification. For track 1, we develop a powerful U-Net-based speaker embedding extractor with a symmetric architecture. The proposed system achieves 2.06% in EER and 0.1293 in MinDCF on the validation set. Compared with the state-of-the-art ECAPA-TDNN, it obtains a relative improvement of 20.7% in EER and 22.70% in MinDCF. For track 3, we employ the joint training of source domain supervision and target domain self-supervision to get a speaker embedding extractor. The subsequent clustering process can obtain target domain pseudo-speaker labels. We adapt the speaker embedding extractor using all source and target domain data in a supervised manner, where it can fully leverage both domain information. Moreover, clustering and supervised domain adaptation can be repeated until the performance converges on the validation set. Our final submission is a fusion of 10 models and achieves 7.75% EER and 0.3517 MinDCF on the validation set.

Graph similarity measurement, which computes the distance/similarity between two graphs, arises in various graph-related tasks. Recent learning-based methods lack interpretability, as they directly transform interaction information between two graphs into one hidden vector and then map it to similarity. To cope with this problem, this study proposes a more interpretable end-to-end paradigm for graph similarity learning, named Similarity Computation via Maximum Common Subgraph Inference (INFMCS). Our critical insight into INFMCS is the strong correlation between similarity score and Maximum Common Subgraph (MCS). We implicitly infer MCS to obtain the normalized MCS size, with the supervision information being only the similarity score during training. To capture more global information, we also stack some vanilla transformer encoder layers with graph convolution layers and propose a novel permutation-invariant node Positional Encoding. The entire model is quite simple yet effective. Comprehensive experiments demonstrate that INFMCS consistently outperforms state-of-the-art baselines for graph-graph classification and regression tasks. Ablation experiments verify the effectiveness of the proposed computation paradigm and other components. Also, visualization and statistics of results reveal the interpretability of INFMCS.

The problem and promise of artificial intelligence (AI) is people. This has always been true, whatever our hopes (and fears) of robotic overlords taking over. In AI, and data science more generally, the trick is to blend the best of humans and machines. For some time, the AI industry's cheerleaders have tended to stress the machine side of the equation. But as Spring Health data scientist Elena Dyachkova intimates, data (and the machines behind it) are only as useful as the people interpreting it are smart.

Don't get tripped up by thinking of the wrong kind of artificial intelligence (AI) when it comes to testing scenarios. In fact, this second type of AI is already being used in some testing scenarios. But before looking at automation-testing examples affected by machine learning, you need to define what machine learning (ML) actually is. At its core, ML is a pattern-recognition technology--it uses patterns identified by your machine learning algorithms to predict future trends. ML can consume tons of complex information and find patterns that are predictive, and then alert you to those differences.

A novel framework is proposed for handling the complex task of modelling and analysis of longitudinal, multivariate, heterogeneous clinical data. This method uses temporal abstraction to convert the data into a more appropriate form for modelling, temporal pattern mining, to discover patterns in the complex, longitudinal data and machine learning models of survival analysis to select the discovered patterns. The method is applied to two real-world studies of Alzheimer's disease (AD), a progressive neurodegenerative disease that has no cure. The patterns discovered were predictive of AD in survival analysis models with a Concordance index of up to 0.8. This is the first work that performs survival analysis of AD data using temporal data collections for AD. A visualisation module also provides a clear picture of the discovered patterns for ease of interpretability.

AlgoDocs is a powerful web-based AI Platform for Data Extraction that is developed using the latest technologies. Export extracted data to Excel or many other integrations such as accounting software.