Traffic accidents frequently lead to fatal injuries, contributing to over 50 million deaths until 2023. To mitigate driving hazards and ensure personal safety, it is crucial to assist vehicles in anticipating important objects during travel. Previous research on important object detection primarily assessed the importance of individual participants, treating them as independent entities and frequently overlooking the connections between these participants. Unfortunately, this approach has proven less effective in detecting important objects in complex scenarios. In response, we introduce Driving scene Relationship self-Understanding transformer (DRUformer), designed to enhance the important object detection task. The DRUformer is a transformer-based multi-modal important object detection model that takes into account the relationships between all the participants in the driving scenario. Recognizing that driving intention also significantly affects the detection of important objects during driving, we have incorporated a module for embedding driving intention. To assess the performance of our approach, we conducted a comparative experiment on the DRAMA dataset, pitting our model against other state-of-the-art (SOTA) models. The results demonstrated a noteworthy 16.2\% improvement in mIoU and a substantial 12.3\% boost in ACC compared to SOTA methods. Furthermore, we conducted a qualitative analysis of our model's ability to detect important objects across different road scenarios and classes, highlighting its effectiveness in diverse contexts. Finally, we conducted various ablation studies to assess the efficiency of the proposed modules in our DRUformer model.
In many sports, player re-identification is crucial for automatic video processing and analysis. However, most of the current studies on player re-identification in multi- or single-view sports videos focus on re-identification in the closed-world setting using labeled image dataset, and player re-identification in the open-world setting for automatic video analysis is not well developed. In this paper, we propose a runner re-identification system that directly processes single-view video to address the open-world setting. In the open-world setting, we cannot use labeled dataset and have to process video directly. The proposed system automatically processes raw video as input to identify runners, and it can identify runners even when they are framed out multiple times. For the automatic processing, we first detect the runners in the video using the pre-trained YOLOv8 and the fine-tuned EfficientNet. We then track the runners using ByteTrack and detect their shoes with the fine-tuned YOLOv8. Finally, we extract the image features of the runners using an unsupervised method using the gated recurrent unit autoencoder model. To improve the accuracy of runner re-identification, we use dynamic features of running sequence images. We evaluated the system on a running practice video dataset and showed that the proposed method identified runners with higher accuracy than one of the state-of-the-art models in unsupervised re-identification. We also showed that our unsupervised running dynamic feature extractor was effective for runner re-identification. Our runner re-identification system can be useful for the automatic analysis of running videos.
General-purpose mobile robots need to complete tasks without exact human instructions. Large language models (LLMs) is a promising direction for realizing commonsense world knowledge and reasoning-based planning. Vision-language models (VLMs) transform environment percepts into vision-language semantics interpretable by LLMs. However, completing complex tasks often requires reasoning about information beyond what is currently perceived. We propose latent compositional semantic embeddings z* as a principled learning-based knowledge representation for queryable spatio-semantic memories. We mathematically prove that z* can always be found, and the optimal z* is the centroid for any set Z. We derive a probabilistic bound for estimating separability of related and unrelated semantics. We prove that z* is discoverable by iterative optimization by gradient descent from visual appearance and singular descriptions. We experimentally verify our findings on four embedding spaces incl. CLIP and SBERT. Our results show that z* can represent up to 10 semantics encoded by SBERT, and up to 100 semantics for ideal uniformly distributed high-dimensional embeddings. We demonstrate that a simple dense VLM trained on the COCO-Stuff dataset can learn z* for 181 overlapping semantics by 42.23 mIoU, while improving conventional non-overlapping open-vocabulary segmentation performance by +3.48 mIoU compared with a popular SOTA model.
This study introduces a novel training paradigm, audio difference learning, for improving audio captioning. The fundamental concept of the proposed learning method is to create a feature representation space that preserves the relationship between audio, enabling the generation of captions that detail intricate audio information. This method employs a reference audio along with the input audio, both of which are transformed into feature representations via a shared encoder. Captions are then generated from these differential features to describe their differences. Furthermore, a unique technique is proposed that involves mixing the input audio with additional audio, and using the additional audio as a reference. This results in the difference between the mixed audio and the reference audio reverting back to the original input audio. This allows the original input's caption to be used as the caption for their difference, eliminating the need for additional annotations for the differences. In the experiments using the Clotho and ESC50 datasets, the proposed method demonstrated an improvement in the SPIDEr score by 7% compared to conventional methods.
Transformer-based models have gained popularity in the field of natural language processing (NLP) and are extensively utilized in computer vision tasks and multi-modal models such as GPT4. This paper presents a novel method to enhance the explainability of Transformer-based image classification models. Our method aims to improve trust in classification results and empower users to gain a deeper understanding of the model for downstream tasks by providing visualizations of class-specific maps. We introduce two modules: the ``Relationship Weighted Out" and the ``Cut" modules. The ``Relationship Weighted Out" module focuses on extracting class-specific information from intermediate layers, enabling us to highlight relevant features. Additionally, the ``Cut" module performs fine-grained feature decomposition, taking into account factors such as position, texture, and color. By integrating these modules, we generate dense class-specific visual explainability maps. We validate our method with extensive qualitative and quantitative experiments on the ImageNet dataset. Furthermore, we conduct a large number of experiments on the LRN dataset, specifically designed for automatic driving danger alerts, to evaluate the explainability of our method in complex backgrounds. The results demonstrate a significant improvement over previous methods. Moreover, we conduct ablation experiments to validate the effectiveness of each module. Through these experiments, we are able to confirm the respective contributions of each module, thus solidifying the overall effectiveness of our proposed approach.
Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on- and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in a continuous state space that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.
The application of visual tracking to the performance analysis of sports players in dynamic competitions is vital for effective coaching. In racket sports, most previous studies have focused on analyzing and assessing singles players without occlusion in broadcast videos and discrete representations (e.g., stroke) that ignore meaningful spatial distributions. In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance. We present an efficient framework of deep neural networks that enables the calculation of full probability surfaces, which utilizes the embedding of a Gaussian mixture map of players' positions and graph convolution of their poses. In the experiment, we verify our approach by comparing various baselines and discovering the correlations between the score and control area. Furthermore, we propose the practical application of assessing optimal positioning to provide instructions during a game. Our approach can visually and quantitatively evaluate players' movements, providing valuable insights into doubles teamwork.
Human beings cooperatively navigate rule-constrained environments by adhering to mutually known navigational patterns, which may be represented as directional pathways or road lanes. Inferring these navigational patterns from incompletely observed environments is required for intelligent mobile robots operating in unmapped locations. However, algorithmically defining these navigational patterns is nontrivial. This paper presents the first self-supervised learning (SSL) method for learning to infer navigational patterns in real-world environments from partial observations only. We explain how geometric data augmentation, predictive world modeling, and an information-theoretic regularizer enables our model to predict an unbiased local directional soft lane probability (DSLP) field in the limit of infinite data. We demonstrate how to infer global navigational patterns by fitting a maximum likelihood graph to the DSLP field. Experiments show that our SSL model outperforms two SOTA supervised lane graph prediction models on the nuScenes dataset. We propose our SSL method as a scalable and interpretable continual learning paradigm for navigation by perception. Code released upon publication.
Cognitive scientists believe adaptable intelligent agents like humans perform reasoning through learned causal mental simulations of agents and environments. The problem of learning such simulations is called predictive world modeling. Recently, reinforcement learning (RL) agents leveraging world models have achieved SOTA performance in game environments. However, understanding how to apply the world modeling approach in complex real-world environments relevant to mobile robots remains an open question. In this paper, we present a framework for learning a probabilistic predictive world model for real-world road environments. We implement the model using a hierarchical VAE (HVAE) capable of predicting a diverse set of fully observed plausible worlds from accumulated sensor observations. While prior HVAE methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only. We experimentally demonstrate accurate spatial structure prediction of deterministic regions achieving 96.21 IoU, and close the gap to perfect prediction by 62 % for stochastic regions using the best prediction. By extending HVAEs to cases where complete ground truth states do not exist, we facilitate continual learning of spatial prediction as a step towards realizing explainable and comprehensive predictive world models for real-world mobile robotics applications.
Automatic fault detection is a major challenge in many sports. In race walking, referees visually judge faults according to the rules. Hence, ensuring objectivity and fairness while judging is important. To address this issue, some studies have attempted to use sensors and machine learning to automatically detect faults. However, there are problems associated with sensor attachments and equipment such as a high-speed camera, which conflict with the visual judgement of referees, and the interpretability of the fault detection models. In this study, we proposed a fault detection system for non-contact measurement. We used pose estimation and machine learning models trained based on the judgements of multiple qualified referees to realize fair fault judgement. We verified them using smartphone videos of normal race walking and walking with intentional faults in several athletes including the medalist of the Tokyo Olympics. The validation results show that the proposed system detected faults with an average accuracy of over 90%. We also revealed that the machine learning model detects faults according to the rules of race walking. In addition, the intentional faulty walking movement of the medalist was different from that of university walkers. This finding informs realization of a more general fault detection model. The code and data are available at https://github.com/SZucchini/racewalk-aijudge.