Abstract: This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.

Abstract: Colorectal cancer is one of the main causes of cancer death worldwide. Colonoscopy is the gold standard screening tool as it allows lesion detection and removal during the same procedure. During the last decades, several efforts have been made to develop CAD systems to assist clinicians in lesion detection and classification. Regarding the latter, and in order to be used in the exploration room as part of resect and discard or leave-in-situ strategies, these systems must identify correctly all different lesion types. This is a challenging task, as the data used to train these systems presents great inter-class similarity, high class imbalance, and low representation of clinically relevant histology classes such as serrated sessile adenomas.
In this paper, a new polyp segmentation and classification method, Swin-Expand, is introduced. Based on Swin-Transformer, it uses a simple and lightweight decoder. The performance of this method has been assessed on a novel dataset, comprising 1126 high-definition images representing the three main histological classes. Results show a clear improvement in both segmentation and classification performance, also achieving competitive results when tested in public datasets. These results confirm that both the method and the data are important to obtain more accurate polyp representations.

Abstract: Dual-camera systems commonly employed in surveillance serve as the foundation for RGB-infrared (IR) cross-modality person re-identification (ReID). However, significant modality differences give rise to inferior performance compared to single-modality scenarios. Furthermore, most existing studies in this area rely on supervised training with meticulously labeled datasets. Labeling RGB-IR image pairs is more complex than labeling conventional image data, and deploying pretrained models on unlabeled datasets can lead to catastrophic performance degradation. In contrast to previous solutions that focus solely on cross-modality or domain adaptation issues, this article presents an end-to-end unsupervised domain adaptation (UDA) framework for the cross-modality person ReID, which can simultaneously address both of these challenges. This model employs source domain classes, target domain clusters, and unclustered instance samples for the training, maximizing the comprehensive use of the dataset. Moreover, it addresses the problem of mismatched clustering labels between the two modalities in the target domain by incorporating a label matching module that reassigns reliable clusters with labels, ensuring correspondence between different modality labels. We construct the loss function by incorporating distinctiveness loss and multiplicity loss, both of which are determined by the similarity of neighboring features in the predicted feature space and the difference between distant features. This approach enables efficient feature clustering and cluster class assignment to occur concurrently. Eight UDA cross-modality person ReID experiments are conducted on three real datasets and six synthetic datasets. The experimental results unequivocally demonstrate that the proposed model outperforms the existing state-of-the-art algorithms to a significant degree. Notably, in RegDB → RegDB_light, the Rank-1 accuracy exhibits a remarkable improvement of 8.24%.

Abstract: Scene text detection and recognition is a crucial task in computer vision with numerous real-world applications. Transformer-based approaches are behind all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training and inference times without sacrificing performance, striking a balance between accuracy and speed. We have applied this pruning technique to our own end-to-end transformer-based scene text understanding architecture. Our method uses a separate detection branch to guide the pruning of uninformative image features, which significantly reduces the number of tokens at the input of the transformer. Experimental results show how our network is able to obtain competitive results on multiple public benchmarks while running at significantly higher speeds.

Abstract: Recently, video text detection, tracking and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenario, while ignore extreme video texts challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a video text reading benchmark, named DSText, which focuses on dense and small text reading challenge in the video with various scenarios. Compared with the previous datasets, the proposed dataset mainly include three new challenges: 1) Dense video texts, new challenge for video text spotter. 2) High-proportioned small texts. 3) Various new scenarios, e.g., ‘Game’, ‘Sports’, etc. The proposed DSText includes 100 video clips from 12 open scenarios, supporting two tasks (i.e., video text tracking (Task 1) and end-to-end video text spotting (Task2)). During the competition period (opened on 15th February, 2023 and closed on 20th March, 2023), a total of 24 teams participated in the three proposed tasks with around 30 valid submissions, respectively. In this article, we describe detailed statistical information of the dataset, tasks, evaluation protocols and the results summaries of the ICDAR 2023 on DSText competition. Moreover, we hope the benchmark will promise the video text research in the community.

Abstract: Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of 3, 222 driving videos collected from multiple countries, annotated with 10, 500 questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa.