Abstract: In this paper, we present a novel hand –based Video Question Answering framework, entitled Multi-View Video Question Answering (MV-VQA), employing the Single Shot Detector (SSD), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT), and Co-Attention mechanism with RGB videos as the inputs. Our model includes three main blocks: vision, language, and attention. In the vision block, we employ a novel representation to obtain some efficient multiview features from the hand object using the combination of five 3DCNNs and one LSTM network. To obtain the question embedding, we use the BERT model in language block. Finally, we employ a co-attention mechanism on vision and language features to recognize the final answer. For the first time, we propose such a hand-based Video-QA framework including the multi-view hand skeleton features combined with the question embedding and co-attention mechanism. Our framework is capable of processing the arbitrary numbers of questions in the dataset annotations. There are different application domains for this framework. Here, as an application domain, we applied our framework to dynamic hand gesture recognition for the first time. Since the main object in dynamic hand gesture recognition is the human hand, we performed a step-by-step analysis of the hand detection and multi-view hand skeleton impact on the model performance. Evaluation results on five datasets, including two datasets in VideoQA, two datasets in dynamic hand gesture, and one dataset in hand action recognition show that MV-VQA outperforms state-of-the-art alternatives.

Abstract: This paper presents the results of two tracks from the fourth Thermal Image Super-Resolution (TISR) challenge, held at the Perception Beyond the Visible Spectrum (PBVS) 2023 workshop. Track-1 uses the same thermal image dataset as previous challenges, with 951 training images and 50 validation images at each resolution. In this track, two evaluations were conducted: the first consists of generating a SR image from a HR thermal noisy image downsampled by four, and the second consists of generating a SR image from a mid-resolution image and compare it with its semi-registered HR image (acquired with another camera). The results of Track-1 outperformed those from last year’s challenge. On the other hand, Track-2 uses a new acquired dataset consisting of 160 registered visible and thermal images of the same scenario for training and 30 validation images. This year, more than 150 teams participated in the challenge tracks, demonstrating the community’s ongoing interest in this topic.

Abstract: Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new challenges for interpretability, as the rationale behind model predictions may change over time, leading to interpretability concept drift. We address this problem by proposing Interpretable Class-InCremental LEarning (ICICLE), an exemplar-free approach that adopts a prototypical part-based approach. It consists of three crucial novelties: interpretability regularization that distills previously learned concepts while preserving user-friendly positive reasoning; proximity-based prototype initialization strategy dedicated to the fine-grained setting; and task-recency bias compensation devoted to prototypical parts. Our experimental results demonstrate that ICICLE reduces the interpretability concept drift and outperforms the existing exemplar-free methods of common class-incremental learning when applied to concept-based models.

Abstract: In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a transformer-based architecture that incorporates three pretext tasks as learning objectives to be optimized during pre-training without the usage of labelled data. Each of the pretext objectives is specifically tailored for the final downstream tasks. We conduct several ablation experiments that confirm the design choice of the selected pretext tasks. Importantly, the proposed model does not exhibit limitations of previous state-of-the-art methods based on contrastive losses, while at the same time requiring substantially fewer data samples to converge. Finally, we demonstrate that our method surpasses the state-of-the-art in existing supervised and self-supervised settings in handwritten and scene text recognition and document image enhancement. Our code and trained models will be made publicly available at https://github.com/dali92002/SSL-OCR

Abstract: Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical evaluation, we evaluate various methods from the literature that tackle online continual learning. More specifically, we focus on the class-incremental setting in the context of image classification, where the learner must learn new classes incrementally from a stream of data. We compare these methods on the Split-CIFAR100 and Split-TinyImagenet benchmarks, and measure their average accuracy, forgetting, stability, and quality of the representations, to evaluate various aspects of the algorithm at the end but also during the whole training period. We find that most methods suffer from stability and underfitting issues. However, the learned representations are comparable to i.i.d. training under the same computational budget. No clear winner emerges from the results and basic experience replay, when properly tuned and implemented, is a very strong baseline. We release our modular and extensible codebase at this https URL based on the avalanche framework to reproduce our results and encourage future research.

Abstract: This paper presents an innovative architecture based on a Cycle Generative Adversarial Network (CycleGAN) for the synthesis of high-quality depth maps from monocular images. The proposed architecture leverages a diverse set of loss functions, including cycle consistency, contrastive, identity, and least square losses, to facilitate the generation of depth maps that exhibit realism and high fidelity. A notable feature of the approach is its ability to synthesize depth maps from grayscale images without the need for paired training data. Extensive comparisons with different state-of-the-art methods show the superiority of the proposed approach in both quantitative metrics and visual quality. This work addresses the challenge of depth map synthesis and offers significant advancements in the field.

Abstract: Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a simplification of real-world scenarios. Hence, we propose to validate test-time adaptation methods using the recently introduced datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift, often resulting in degraded performance that falls below that of the source model. We noticed that the root of the problem lies in the inability to preserve the knowledge of the source model and adapt to dynamically changing, temporally correlated data streams. Therefore, we enhance well-established self-training framework by incorporating a small memory buffer to increase model stability and at the same time perform dynamic adaptation based on the intensity of domain shift. The proposed method, named AR-TTA, outperforms existing approaches on both synthetic and more real-world benchmarks and shows robustness across a variety of TTA scenarios.

Abstract: Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.