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: The power requirements of video-oculography systems can be prohibitive for high-speed operation on portable devices. Recently, low-power alternatives such as photosensors have been evaluated, providing gaze estimates at high frequency with a trade-off in accuracy and robustness. Potentially, an approach combining slow/high-fidelity and fast/low-fidelity sensors should be able to exploit their complementarity to track fast eye motion accurately and robustly. To foster research on this topic, we introduce OpenSFEDS, a near-eye gaze estimation dataset containing approximately 2M synthetic camera-photosensor image pairs sampled at 500 Hz under varied appearance and camera position. We also formulate the task of sensor fusion for gaze estimation, proposing a deep learning framework consisting in appearance-based encoding and temporal eye-state dynamics. We evaluate several single- and multi-rate fusion baselines on OpenSFEDS, achieving 8.7% error decrease when tracking fast eye movements with a multi-rate approach vs. a gaze forecasting approach operating with a low-speed sensor alone.

Abstract: Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods.

Abstract: Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploit regularization (e.g., knowledge distillation) to maintain previous knowledge in the current model. However, distillation alone often yields limited gain to the model since only the representations of old and new models are restricted to be consistent. In this paper, we propose a simple yet effective method to obtain a model with strong memory of old knowledge, named Endpoints Weight Fusion (EWF). In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions. In addition, we analyze the relation between our fusion strategy and a popular moving average technique EMA, which reveals why our method is more suitable for class-incremental learning. To facilitate parameter fusion with closer distance in the parameter space, we use distillation to enhance the optimization process. Furthermore, we conduct experiments on two widely used datasets, achieving the state-of-the-art performance.

Abstract: This paper unveils the discoveries and outcomes of the inaugural iteration of the Multi-modal Aerial View Image Challenge (MAVIC) aimed at image translation. The primary objective of this competition is to stimulate research efforts towards the development of models capable of translating co-aligned images between multiple modalities. To accomplish the task of image translation, the competition utilizes images obtained from both synthetic aperture radar (SAR) and electro-optical (EO) sources. Specifically, the challenge centers on the translation from the SAR modality to the EO modality, an area of research that has garnered attention. The inaugural challenge demonstrates the feasibility of the task. The dataset utilized in this challenge is derived from the UNIfied COincident Optical and Radar for recognitioN (UNICORN) dataset. We introduce an new version of the UNICORN dataset that is focused on enabling the sensor translation task. Performance evaluation is conducted using a combination of measures to ensure high fidelity and high accuracy translations.

Abstract: This paper presents the findings and results of the third edition of the Multi-modal Aerial View Object Classification (MAVOC) challenge in a detailed and comprehensive manner. The challenge consists of two tracks. The primary aim of both tracks is to encourage research into building recognition models that utilize both synthetic aperture radar (SAR) and electro-optical (EO) imagery. Participating teams are encouraged to develop multi-modal approaches that incorporate complementary information from both domains. While the 2021 challenge demonstrated the feasibility of combining both modalities, the 2022 challenge expanded on the capability of multi-modal models. The 2023 challenge introduces a refined version of the UNICORN dataset and demonstrates significant improvements made. The 2023 challenge adopts an updated UNIfied CO-incident Optical and Radar for recognitioN (UNICORN V2) dataset and competition format. Two tasks are featured: SAR classification and SAR + EO classification. In addition to measuring accuracy of models, we also introduce out-of-distribution measures to encourage model robustness.The majority of this paper is dedicated to discussing the top performing methods and evaluating their performance on our blind test set. It is worth noting that all of the top ten teams outperformed the Resnet-50 baseline. The top team for SAR classification achieved a 173% performance improvement over the baseline, while the top team for SAR + EO classification achieved a 175% improvement.