Abstract: The automatic processing of handwritten historical documents is considered a hard problem in pattern recognition. In addition to the challenges given by modern handwritten data, a lack of training data as well as effects caused by the degradation of documents can be observed. In this scenario, keyword spotting arises to be a viable solution to make documents amenable for searching and browsing. For this task we propose the adaptation of shape descriptors used in symbol recognition. By treating each word image as a shape, it can be represented using the Blurred Shape Model and the De-formable Blurred Shape Model. Experiments on the George Washington database demonstrate that this approach is able to outperform the commonly used Dynamic Time Warping approach.

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: The Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in various dyadic interaction scenarios, with all participants competing strictly under the same conditions. The goal of the challenge is to provide the first benchmark test set for multi-modal information processing and to foster collaboration among the audio, visual, and audio-visual behaviour analysis and behaviour generation (a.k.a generative AI) communities, to compare the relative merits of the approaches to automatic appropriate facial reaction generation under different spontaneous dyadic interaction conditions. This paper presents: (i) the novelties, contributions and guidelines of the REACT2023 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2023.

Abstract: Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information given, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. The same Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to the specific context allowing us to explore the limits of the model to adjust captions to different contextual information. Dealing with out-of-dictionary words and Named Entities is a challenging task in this domain. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task results to significantly improved models. Furthermore, we verify that a model pre-trained in Wikipedia generalizes well to News Captioning datasets. We further define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model.

Abstract: Automated skill assessment in sports using video-based analysis holds great potential for revolutionizing coaching methodologies. This paper focuses on the problem of skill determination in golfers by leveraging deep learning models applied to a large database of video recordings of golf swings. We investigate different regression, ranking and classification based methods and compare to a simple baseline approach. The performance is evaluated using mean squared error (MSE) as well as computing the percentages of correctly ranked pairs based on the Kendall correlation. Our results demonstrate an improvement over the baseline, with a 35% lower mean squared error and 68% correctly ranked pairs. However, achieving fine-grained skill assessment remains challenging. This work contributes to the development of AI-driven coaching systems and advances the understanding of video-based skill determination in the context of golf.