Yoshimitsu Aoki

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

Event cameras respond to scene dynamics and offer advantages to estimate motion. Following recent image-based deep-learning achievements, optical flow estimation methods for event cameras have rushed to combine those image-based methods with event data. However, it requires several adaptations (data conversion, loss function, etc.) as they have very different properties. We develop a principled method to extend the Contrast Maximization framework to estimate optical flow from events alone. We investigate key elements: how to design the objective function to prevent overfitting, how to warp events to deal better with occlusions, and how to improve convergence with multi-scale raw events. With these key elements, our method ranks first among unsupervised methods on the MVSEC benchmark, and is competitive on the DSEC benchmark. Moreover, our method allows us to expose the issues of the ground truth flow in those benchmarks, and produces remarkable results when it is transferred to unsupervised learning settings. Our code is available at https://github.com/tub-rip/event_based_optical_flow

Shintaro Shiba, Friedhelm Hamann, Yoshimitsu Aoki et al.

Schlieren imaging is an optical technique to observe the flow of transparent media, such as air or water, without any particle seeding. However, conventional frame-based techniques require both high spatial and temporal resolution cameras, which impose bright illumination and expensive computation limitations. Event cameras offer potential advantages (high dynamic range, high temporal resolution, and data efficiency) to overcome such limitations due to their bio-inspired sensing principle. This paper presents a novel technique for perceiving air convection using events and frames by providing the first theoretical analysis that connects event data and schlieren. We formulate the problem as a variational optimization one combining the linearized event generation model with a physically-motivated parameterization that estimates the temporal derivative of the air density. The experiments with accurately aligned frame- and event camera data reveal that the proposed method enables event cameras to obtain on par results with existing frame-based optical flow techniques. Moreover, the proposed method works under dark conditions where frame-based schlieren fails, and also enables slow-motion analysis by leveraging the event camera's advantages. Our work pioneers and opens a new stack of event camera applications, as we publish the source code as well as the first schlieren dataset with high-quality frame and event data. https://github.com/tub-rip/event_based_bos

Kazuki Ozeki, Shun Kenney, Yuto Shibata et al.

Although dynamic 3D (i.e., 4D) reconstruction from a monocular dynamic camera has recently advanced, it remains fundamentally limited by depth ambiguity. In this paper, we focus on an alternative practical way, i.e., sparse dynamic camera setup, where a handful of independently moving cameras capture the same subjects. While keeping capture costs low, this setup introduces multi-view constraints and remains practical for real-world video production such as sports, concerts, and TV shows. Despite its potential, our experiments show that naive extensions of existing monocular or dense-fixed camera-based methods are insufficient since they fail to resolve the complex spatiotemporal inconsistencies across views and time. To fill this gap, we propose a simple yet effective 3D track initialization method designed to ensure spatiotemporal consistency by integrating inter-camera feature matching with intra-camera point tracking. Additionally, we incorporate a noise-robust depth-ordering regularization loss and a spatiotemporally diverse batch sampling strategy to enhance optimization stability and cross-view generalization. Furthermore, to address the lack of standardized benchmarks for this task, we introduce LetCamsGo, a new real-world video dataset with 5 sequences across 4 diverse environments, recorded by three independently moving cameras and one fixed camera. Comprehensive benchmarking on LetCamsGo demonstrated that our proposed framework improves 4D reconstruction quality in dynamic regions compared with baselines, paving the way for a low-cost 4D reconstruction paradigm in the wild.

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space-time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models.

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

Event cameras are novel bio-inspired sensors that offer advantages over traditional cameras (low latency, high dynamic range, low power, etc.). Optical flow estimation methods that work on packets of events trade off speed for accuracy, while event-by-event (incremental) methods have strong assumptions and have not been tested on common benchmarks that quantify progress in the field. Towards applications on resource-constrained devices, it is important to develop optical flow algorithms that are fast, light-weight and accurate. This work leverages insights from neuroscience, and proposes a novel optical flow estimation scheme based on triplet matching. The experiments on publicly available benchmarks demonstrate its capability to handle complex scenes with comparable results as prior packet-based algorithms. In addition, the proposed method achieves the fastest execution time (> 10 kHz) on standard CPUs as it requires only three events in estimation. We hope that our research opens the door to real-time, incremental motion estimation methods and applications in real-world scenarios.

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras.

Naofumi Akimoto, Yuhi Matsuo, Yoshimitsu Aoki

We address the problem of generating a 360-degree image from a single image with a narrow field of view by estimating its surroundings. Previous methods suffered from overfitting to the training resolution and deterministic generation. This paper proposes a completion method using a transformer for scene modeling and novel methods to improve the properties of a 360-degree image on the output image. Specifically, we use CompletionNets with a transformer to perform diverse completions and AdjustmentNet to match color, stitching, and resolution with an input image, enabling inference at any resolution. To improve the properties of a 360-degree image on an output image, we also propose WS-perceptual loss and circular inference. Thorough experiments show that our method outperforms state-of-the-art (SOTA) methods both qualitatively and quantitatively. For example, compared to SOTA methods, our method completes images 16 times larger in resolution and achieves 1.7 times lower Frechet inception distance (FID). Furthermore, we propose a pipeline that uses the completion results for lighting and background of 3DCG scenes. Our plausible background completion enables perceptually natural results in the application of inserting virtual objects with specular surfaces.

Yuto Shibata, Kashu Yamazaki, Lalit Jayanti et al. · cmu

Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce a broad range of human motions, these behaviors are primarily limited to contact-less social interactions or isolated movements. Assistive scenarios, by contrast, require continuous awareness of a human partner and rapid adaptation to their evolving posture and dynamics. In this paper, we formulate the imitation of closely interacting, force-exchanging human-human motion sequences as a multi-agent reinforcement learning problem. We jointly train partner-aware policies for both the supporter (assistant) agent and the recipient agent in a physics simulator to track assistive motion references. To make this problem tractable, we introduce a partner policies initialization scheme that transfers priors from single-human motion-tracking controllers, greatly improving exploration. We further propose dynamic reference retargeting and contact-promoting reward, which adapt the assistant's reference motion to the recipient's real-time pose and encourage physically meaningful support. We show that AssistMimic is the first method capable of successfully tracking assistive interaction motions on established benchmarks, demonstrating the benefits of a multi-agent RL formulation for physically grounded and socially aware humanoid control.

Go Ohtani, Ryu Tadokoro, Ryosuke Yamada et al.

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models.

Haruya Ishikawa, Yoshimitsu Aoki

In this paper, we present the Semantic Boundary Conditioned Backbone (SBCB) framework, a simple yet effective training framework that is model-agnostic and boosts segmentation performance, especially around the boundaries. Motivated by the recent development in improving semantic segmentation by incorporating boundaries as auxiliary tasks, we propose a multi-task framework that uses semantic boundary detection (SBD) as an auxiliary task. The SBCB framework utilizes the nature of the SBD task, which is complementary to semantic segmentation, to improve the backbone of the segmentation head. We apply an SBD head that exploits the multi-scale features from the backbone, where the model learns low-level features in the earlier stages, and high-level semantic understanding in the later stages. This head perfectly complements the common semantic segmentation architectures where the features from the later stages are used for classification. We can improve semantic segmentation models without additional parameters during inference by only conditioning the backbone. Through extensive evaluations, we show the effectiveness of the SBCB framework by improving various popular segmentation heads and backbones by 0.5% ~ 3.0% IoU on the Cityscapes dataset and gains 1.6% ~ 4.1% in boundary Fscores. We also apply this framework on customized backbones and the emerging vision transformer models and show the effectiveness of the SBCB framework.

Toranosuke Manabe, Yuto Shibata, Shinnosuke Takamichi et al.

Deep learning models have improved sign language-to-text translation and made it easier for non-signers to understand signed messages. When the goal is spoken communication, a naive approach is to convert signed messages into text and then synthesize speech via Text-to-Speech (TTS). However, this two-stage pipeline inevitably treat text as a bottleneck representation, causing the loss of rich non-verbal information originally conveyed in the signing. To address this limitation, we propose a novel task, \emph{Sign-to-Speech Prosody Transfer}, which aims to capture the global prosodic nuances expressed in sign language and directly integrate them into synthesized speech. A major challenge is that aligning sign and speech requires expert knowledge, making annotation extremely costly and preventing the construction of large parallel corpora. To overcome this, we introduce \emph{SignRecGAN}, a scalable training framework that leverages unimodal datasets without cross-modal annotations through adversarial learning and reconstruction losses. Furthermore, we propose \emph{S2PFormer}, a new model architecture that preserves the expressive power of existing TTS models while enabling the injection of sign-derived prosody into the synthesized speech. Extensive experiments demonstrate that the proposed method can synthesize speech that faithfully reflects the emotional content of sign language, thereby opening new possibilities for more natural sign language communication. Our code will be available upon acceptance.

Haruya Ishikawa, Yoshimitsu Aoki

With the increase in demands for service robots and automated inspection, agents need to localize in its surrounding environment to achieve more natural communication with humans by shared contexts. In this work, we propose a novel but straightforward task of precise target view localization for look around agents called the FindView task. This task imitates the movements of PTZ cameras or user interfaces for 360 degree mediums, where the observer must "look around" to find a view that exactly matches the target. To solve this task, we introduce a rule-based agent that heuristically finds the optimal view and a policy learning agent that employs reinforcement learning to learn by interacting with the 360 degree scene. Through extensive evaluations and benchmarks, we conclude that learned methods have many advantages, in particular precise localization that is robust to corruption and can be easily deployed in novel scenes.

Yasufumi Kawano, Yoshimitsu Aoki

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due to the limited predefined categories in supervised learning, models typically struggle with infrequent classes and are unable to predict novel classes. To address these limitations, we propose MaskDiffusion, an innovative approach that leverages pretrained frozen Stable Diffusion to achieve open-vocabulary semantic segmentation without the need for additional training or annotation, leading to improved performance compared to similar methods. We also demonstrate the superior performance of MaskDiffusion in handling open vocabularies, including fine-grained and proper noun-based categories, thus expanding the scope of segmentation applications. Overall, our MaskDiffusion shows significant qualitative and quantitative improvements in contrast to other comparable unsupervised segmentation methods, i.e. on the Potsdam dataset (+10.5 mIoU compared to GEM) and COCO-Stuff (+14.8 mIoU compared to DiffSeg). All code and data will be released at https://github.com/Valkyrja3607/MaskDiffusion.

Yasufumi Kawano, Yoshimitsu Aoki

Semantic segmentation is a crucial task in computer vision, where each pixel in an image is classified into a category. However, traditional methods face significant challenges, including the need for pixel-level annotations and extensive training. Furthermore, because supervised learning uses a limited set of predefined categories, models typically struggle with rare classes and cannot recognize new ones. Unsupervised and open-vocabulary segmentation, proposed to tackle these issues, faces challenges, including the inability to assign specific class labels to clusters and the necessity of user-provided text queries for guidance. In this context, we propose a novel approach, TAG which achieves Training, Annotation, and Guidance-free open-vocabulary semantic segmentation. TAG utilizes pre-trained models such as CLIP and DINO to segment images into meaningful categories without additional training or dense annotations. It retrieves class labels from an external database, providing flexibility to adapt to new scenarios. Our TAG achieves state-of-the-art results on PascalVOC, PascalContext and ADE20K for open-vocabulary segmentation without given class names, i.e. improvement of +15.3 mIoU on PascalVOC. All code and data will be released at https://github.com/Valkyrja3607/TAG.

Yuki Hirakawa, Takashi Wada, Ryotaro Shimizu et al.

Given a person image and a garment image, image-based Virtual Try-ON (VTON) synthesizes a try-on image of the person wearing the target garment. As VTON systems become increasingly important in practical applications such as fashion e-commerce, reliable evaluation of their outputs has emerged as a critical challenge. In real-world scenarios, ground-truth images of the same person wearing the target garment are typically unavailable, making reference-based evaluation impractical. Moreover, widely used distribution-level metrics such as Fréchet Inception Distance and Kernel Inception Distance measure dataset-level similarity and fail to reflect the perceptual quality of individual generated images. To address these limitations, we propose Image Quality Assessment for Virtual Try-On (VTON-IQA), a reference-free framework for human-aligned, image-level quality assessment without requiring ground-truth images. To model human perceptual judgments, we construct VTON-QBench, a large-scale human-annotated benchmark comprising 62,688 try-on images generated by 14 representative VTON models and 431,800 quality annotations collected from 13,838 qualified annotators. To the best of our knowledge, this is the largest dataset to date for human subjective evaluation in virtual try-on. Evaluating virtual try-on quality requires verifying both garment fidelity and the preservation of person-specific details. To explicitly model such interactions, we introduce an Interleaved Cross-Attention module that extends standard transformer blocks by inserting a cross-attention layer between self-attention and MLP in the latter blocks. Extensive experiments show that VTON-IQA achieves reliable human-aligned image-level quality prediction. Moreover, we conduct a comprehensive benchmark evaluation of 14 representative VTON models using VTON-IQA.

Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego et al.

Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estimation. However, it has been unclear how event-based 3D Gaussian Splatting (3DGS) approaches could leverage fine-grained temporal information of sparse events. This work proposes a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS. Our key idea is to decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering, by using ray-tracing and the image of warped events. The extensive evaluation shows that our method achieves state-of-the-art performance on the real-world datasets and competitive performance on the synthetic dataset. Also, the proposed method works without prior information (e.g., pretrained image reconstruction models) or COLMAP-based initialization, is more flexible in the event selection number, and achieves sharp reconstruction on scene edges with fast training time. We hope that this work deepens our understanding of the sparse nature of events for 3D reconstruction. The code will be released.

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

Event cameras are emerging vision sensors whose noise is challenging to characterize. Existing denoising methods for event cameras are often designed in isolation and thus consider other tasks, such as motion estimation, separately (i.e., sequentially after denoising). However, motion is an intrinsic part of event data, since scene edges cannot be sensed without motion. We propose, to the best of our knowledge, the first method that simultaneously estimates motion in its various forms (e.g., ego-motion, optical flow) and noise. The method is flexible, as it allows replacing the one-step motion estimation of the widely-used Contrast Maximization framework with any other motion estimator, such as deep neural networks. The experiments show that the proposed method achieves state-of-the-art results on the E-MLB denoising benchmark and competitive results on the DND21 benchmark, while demonstrating effectiveness across motion estimation and intensity reconstruction tasks. Our approach advances event-data denoising theory and expands practical denoising use-cases via open-source code. Project page: https://github.com/tub-rip/ESMD

Ryo Yamaki, Shintaro Shiba, Guillermo Gallego et al.

Event cameras provide rich signals that are suitable for motion estimation since they respond to changes in the scene. As any visual changes in the scene produce event data, it is paramount to classify the data into different motions (i.e., motion segmentation), which is useful for various tasks such as object detection and visual servoing. We propose an iterative motion segmentation method, by classifying events into background (e.g., dominant motion hypothesis) and foreground (independent motion residuals), thus extending the Contrast Maximization framework. Experimental results demonstrate that the proposed method successfully classifies event clusters both for public and self-recorded datasets, producing sharp, motion-compensated edge-like images. The proposed method achieves state-of-the-art accuracy on moving object detection benchmarks with an improvement of over 30%, and demonstrates its possibility of applying to more complex and noisy real-world scenes. We hope this work broadens the sensitivity of Contrast Maximization with respect to both motion parameters and input events, thus contributing to theoretical advancements in event-based motion segmentation estimation. https://github.com/aoki-media-lab/event_based_segmentation_vcmax

Yuchi Ishikawa, Masayoshi Kondo, Yoshimitsu Aoki

Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the promising ways to solve these issues, yet pre-training solely on synthetic data has its own challenges. In this paper, we introduce an effective self-supervised learning framework for videos that leverages readily available and less costly static images. Specifically, we define the Pseudo Motion Generator (PMG) module that recursively applies image transformations to generate pseudo-motion videos from images. These pseudo-motion videos are then leveraged in masked video modeling. Our approach is applicable to synthetic images as well, thus entirely freeing video pre-training from data collection costs and other concerns in real data. Through experiments in action recognition tasks, we demonstrate that this framework allows effective learning of spatio-temporal features through pseudo-motion videos, significantly improving over existing methods which also use static images and partially outperforming those using both real and synthetic videos. These results uncover fragments of what video transformers learn through masked video modeling.

Shun Kato, Yasushi Kondo, Shuntaro Saito et al.

Rheumatoid arthritis (RA) is an autoimmune disease characterized by systemic joint inflammation. Early diagnosis and tight follow-up are essential to the management of RA, as ongoing inflammation can cause irreversible joint damage. The detection of arthritis is important for diagnosis and assessment of disease activity; however, it often takes a long time for patients to receive appropriate specialist care. Therefore, there is a strong need to develop systems that can detect joint inflammation easily using RGB images captured at home. Consequently, we tackle the task of RA inflammation detection from RGB hand images. This task is highly challenging due to general issues in medical imaging, such as the scarcity of positive samples, data imbalance, and the inherent difficulty of the task itself. However, to the best of our knowledge, no existing work has explicitly addressed these challenges in RGB-based RA inflammation detection. This paper quantitatively demonstrates the difficulty of visually detecting inflammation by constructing a dedicated dataset, and we propose a inflammation detection framework with global local encoder that combines self-supervised pretraining on large-scale healthy hand images with imbalance-aware training to detect RA-related joint inflammation from RGB hand images. Our experiments demonstrated that the proposed approach improves F1-score by 0.2 points and Gmean by 0.25 points compared with the baseline model.

Yusuke Oumi, Yuto Shibata, Go Irie et al.

This paper explores the problem of 3D human pose estimation from only low-level acoustic signals. The existing active acoustic sensing-based approach for 3D human pose estimation implicitly assumes that the target user is positioned along a line between loudspeakers and a microphone. Because reflection and diffraction of sound by the human body cause subtle acoustic signal changes compared to sound obstruction, the existing model degrades its accuracy significantly when subjects deviate from this line, limiting its practicality in real-world scenarios. To overcome this limitation, we propose a novel method composed of a position discriminator and reverberation-resistant model. The former predicts the standing positions of subjects and applies adversarial learning to extract subject position-invariant features. The latter utilizes acoustic signals before the estimation target time as references to enhance robustness against the variations in sound arrival times due to diffraction and reflection. We construct an acoustic pose estimation dataset that covers diverse human locations and demonstrate through experiments that our proposed method outperforms existing approaches.

Yuchi Ishikawa, Shota Nakada, Hokuto Munakata et al.

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked autoencoders, enabling the model to learn across audio, visual and text modalities. To train LG-CAV-MAE, we introduce an automatic method to generate audio-visual-text triplets from unlabeled videos. We first generate frame-level captions using an image captioning model and then apply CLAP-based filtering to ensure strong alignment between audio and captions. This approach yields high-quality audio-visual-text triplets without requiring manual annotations. We evaluate LG-CAV-MAE on audio-visual retrieval tasks, as well as an audio-visual classification task. Our method significantly outperforms existing approaches, achieving up to a 5.6% improvement in recall@10 for retrieval tasks and a 3.2% improvement for the classification task.

Yuto Shibata, Keitaro Tanaka, Yoshiaki Bando et al.

In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametrically synthesized through formula-driven methods. Specifically, we outline detailed procedures and evaluate their effectiveness for sound event detection (SED). The SED task, which involves estimating the types and timings of sound events, is particularly challenged by the difficulty of acquiring a sufficient quantity of accurately labeled training data. Moreover, it is well known that manually annotated labels often contain noises and are significantly influenced by the subjective judgment of annotators. To address these challenges, we propose a novel pre-training method that utilizes a synthetic dataset, Formula-SED, where acoustic data are generated solely based on mathematical formulas. The proposed method enables large-scale pre-training by using the synthesis parameters applied at each time step as ground truth labels, thereby eliminating label noise and bias. We demonstrate that large-scale pre-training with Formula-SED significantly enhances model accuracy and accelerates training, as evidenced by our results in the DESED dataset used for DCASE2023 Challenge Task 4. The project page is at https://yutoshibata07.github.io/Formula-SED/

Kai Kohyama, Shintaro Shiba, Yoshimitsu Aoki

Capturing a 3D human body is one of the important tasks in computer vision with a wide range of applications such as virtual reality and sports analysis. However, conventional frame cameras are limited by their temporal resolution and dynamic range, which imposes constraints in real-world application setups. Event cameras have the advantages of high temporal resolution and high dynamic range (HDR), but the development of event-based methods is necessary to handle data with different characteristics. This paper proposes a novel event-based method for 3D pose estimation and human mesh recovery. Prior work on event-based human mesh recovery require frames (images) as well as event data. The proposed method solely relies on events; it carves 3D voxels by moving the event camera around a stationary body, reconstructs the human pose and mesh by attenuated rays, and fit statistical body models, preserving high-frequency details. The experimental results show that the proposed method outperforms conventional frame-based methods in the estimation accuracy of both pose and body mesh. We also demonstrate results in challenging situations where a conventional camera has motion blur. This is the first to demonstrate event-only human mesh recovery, and we hope that it is the first step toward achieving robust and accurate 3D human body scanning from vision sensors. https://florpeng.github.io/event-based-human-scan/

Yuchi Ishikawa, Toranosuke Manabe, Tatsuya Komatsu et al.

Audio-visual captioning aims to generate holistic scene descriptions by jointly modeling sound and vision. While recent methods have improved performance through sophisticated modality fusion, it remains unclear to what extent the two modalities are complementary in current audio-visual captioning models and how robust these models are when one modality is degraded. We address these questions by conducting systematic modality robustness tests on LAVCap, a state-of-the-art audio-visual captioning model, in which we selectively suppress or corrupt the audio or visual streams to quantify sensitivity and complementarity. The analysis reveals a pronounced bias toward the audio stream in LAVCap. To evaluate how balanced audio-visual captioning models are in their use of both modalities, we augment AudioCaps with textual annotations that jointly describe the audio and visual streams, yielding the AudioVisualCaps dataset. In our experiments, we report LAVCap baseline results on AudioVisualCaps. We also evaluate the model under modality robustness tests on AudioVisualCaps and the results indicate that LAVCap trained on AudioVisualCaps exhibits less modality bias than when trained on AudioCaps.

Ryunosuke Hayashi, Kohei Torimi, Rokuto Nagata et al.

Real-time 3D trajectory player tracking in sports plays a crucial role in tactical analysis, performance evaluation, and enhancing spectator experience. Traditional systems rely on multi-camera setups, but are constrained by the inherently two-dimensional nature of video data and the need for complex 3D reconstruction processing, making real-time analysis challenging. Basketball, in particular, represents one of the most difficult scenarios in the MOT field, as ten players move rapidly and complexly within a confined court space, with frequent occlusions caused by intense physical contact. To address these challenges, this paper constructs BasketLiDAR, the first multimodal dataset in the sports MOT field that combines LiDAR point clouds with synchronized multi-view camera footage in a professional basketball environment, and proposes a novel MOT framework that simultaneously achieves improved tracking accuracy and reduced computational cost. The BasketLiDAR dataset contains a total of 4,445 frames and 3,105 player IDs, with fully synchronized IDs between three LiDAR sensors and three multi-view cameras. We recorded 5-on-5 and 3-on-3 game data from actual professional basketball players, providing complete 3D positional information and ID annotations for each player. Based on this dataset, we developed a novel MOT algorithm that leverages LiDAR's high-precision 3D spatial information. The proposed method consists of a real-time tracking pipeline using LiDAR alone and a multimodal tracking pipeline that fuses LiDAR and camera data. Experimental results demonstrate that our approach achieves real-time operation, which was difficult with conventional camera-only methods, while achieving superior tracking performance even under occlusion conditions. The dataset is available upon request at: https://sites.google.com/keio.jp/keio-csg/projects/basket-lidar

Haruya Ishikawa, Yoshimitsu Aoki

Semi-supervised semantic segmentation (SS-SS) aims to mitigate the heavy annotation burden of dense pixel labeling by leveraging abundant unlabeled images alongside a small labeled set. While current consistency regularization methods achieve strong results, most do not explicitly model boundaries as a separate learning objective. In this paper, we propose BoundMatch, a novel multi-task SS-SS framework that explicitly integrates semantic boundary detection into a teacher-student consistency regularization pipeline. Our core mechanism, Boundary Consistency Regularized Multi-Task Learning (BCRM), enforces prediction agreement between teacher and student models on both segmentation masks and detailed semantic boundaries, providing complementary supervision from two independent tasks. To further enhance performance and encourage sharper boundaries, BoundMatch incorporates two lightweight fusion modules: Boundary-Semantic Fusion (BSF) injects learned boundary cues into the segmentation decoder, while Spatial Gradient Fusion (SGF) refines boundary predictions using mask gradients, yielding more reliable boundary pseudo-labels. This framework is built upon SAMTH, a strong teacher-student baseline featuring a Harmonious Batch Normalization (HBN) update strategy for improved stability. Extensive experiments on diverse datasets including Cityscapes and Pascal VOC show that BoundMatch achieves competitive performance against current state-of-the-art methods. Our approach achieves state-of-the-art results on the new Cityscapes benchmark with DINOv2 foundation model. Ablation studies highlight BoundMatch's ability to improve boundary-specific evaluation metrics, its effectiveness in realistic large-scale unlabeled data scenario, and applicability to lightweight architectures for mobile deployment.

Erika Mori, Yue Qiu, Hirokatsu Kataoka et al.

Social intelligence, the ability to interpret emotions, intentions, and behaviors, is essential for effective communication and adaptive responses. As robots and AI systems become more prevalent in caregiving, healthcare, and education, the demand for AI that can interact naturally with humans grows. However, creating AI that seamlessly integrates multiple modalities, such as vision and speech, remains a challenge. Current video-based methods for social intelligence rely on general video recognition or emotion recognition techniques, often overlook the unique elements inherent in human interactions. To address this, we propose the Looped Video Debating (LVD) framework, which integrates Large Language Models (LLMs) with visual information, such as facial expressions and body movements, to enhance the transparency and reliability of question-answering tasks involving human interaction videos. Our results on the Social-IQ 2.0 benchmark show that LVD achieves state-of-the-art performance without fine-tuning. Furthermore, supplementary human annotations on existing datasets provide insights into the model's accuracy, guiding future improvements in AI-driven social intelligence.

Yuto Shibata, Yusuke Oumi, Go Irie et al.

We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals. Unlike existing approaches that significantly limit practicality by employing intrusive chirp signals within the audible range, our method utilizes natural music that causes minimal discomfort to humans. Estimating human poses from standard music presents significant challenges. In contrast to sound sources specifically designed for measurement, regular music varies in both volume and pitch. These dynamic changes in signals caused by music are inevitably mixed with alterations in the sound field resulting from human motion, making it hard to extract reliable cues for pose estimation. To address these challenges, BGM2Pose introduces a Contrastive Pose Extraction Module that employs contrastive learning and hard negative sampling to eliminate musical components from the recorded data, isolating the pose information. Additionally, we propose a Frequency-wise Attention Module that enables the model to focus on subtle acoustic variations attributable to human movement by dynamically computing attention across frequency bands. Experiments suggest that our method outperforms the existing methods, demonstrating substantial potential for real-world applications. Our datasets and code will be made publicly available.

Kohei Torimi, Ryosuke Yamada, Daichi Otsuka et al.

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compared to 2D vision. Recent advances in generative models have achieved unprecedented realism in synthetic data production, and recent research shows the potential for using generated data as training data. Here, naturally raising the question: Can synthetic 3D data generated by generative models be used as expanding limited 3D datasets? In response, we present a synthetic 3D dataset expansion method, Textguided Geometric Augmentation (TeGA). TeGA is tailored for language-image-3D pretraining, which achieves SoTA in zero-shot 3D classification, and uses a generative textto-3D model to enhance and extend limited 3D datasets. Specifically, we automatically generate text-guided synthetic 3D data and introduce a consistency filtering strategy to discard noisy samples where semantics and geometric shapes do not match with text. In the experiment to double the original dataset size using TeGA, our approach demonstrates improvements over the baselines, achieving zeroshot performance gains of 3.0% on Objaverse-LVIS, 4.6% on ScanObjectNN, and 8.7% on ModelNet40. These results demonstrate that TeGA effectively bridges the 3D data gap, enabling robust zero-shot 3D classification even with limited real training data and paving the way for zero-shot 3D vision application.

Haruya Ishikawa, Takumi Iida, Yoshinori Konishi et al.

Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we address these challenges by leveraging the abundance of unlabeled data available. We propose the Perspective Cue Training (PCT) framework, a novel training framework that utilizes pseudo-labels generated from unlabeled perspective images using publicly available semantic segmentation models trained on large street-view datasets. PCT applies a perspective view task head to the image encoder shared with the BEV segmentation head, effectively utilizing the unlabeled data to be trained with the generated pseudo-labels. Since image encoders are present in nearly all camera-based BEV segmentation architectures, PCT is flexible and applicable to various existing BEV architectures. PCT can be applied to various settings where unlabeled data is available. In this paper, we applied PCT for semi-supervised learning (SSL) and unsupervised domain adaptation (UDA). Additionally, we introduce strong input perturbation through Camera Dropout (CamDrop) and feature perturbation via BEV Feature Dropout (BFD), which are crucial for enhancing SSL capabilities using our teacher-student framework. Our comprehensive approach is simple and flexible but yields significant improvements over various baselines for SSL and UDA, achieving competitive performances even against the current state-of-the-art.

Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki et al.

We propose an effective framework for the temporal action segmentation task, namely an Action Segment Refinement Framework (ASRF). Our model architecture consists of a long-term feature extractor and two branches: the Action Segmentation Branch (ASB) and the Boundary Regression Branch (BRB). The long-term feature extractor provides shared features for the two branches with a wide temporal receptive field. The ASB classifies video frames with action classes, while the BRB regresses the action boundary probabilities. The action boundaries predicted by the BRB refine the output from the ASB, which results in a significant performance improvement. Our contributions are three-fold: (i) We propose a framework for temporal action segmentation, the ASRF, which divides temporal action segmentation into frame-wise action classification and action boundary regression. Our framework refines frame-level hypotheses of action classes using predicted action boundaries. (ii) We propose a loss function for smoothing the transition of action probabilities, and analyze combinations of various loss functions for temporal action segmentation. (iii) Our framework outperforms state-of-the-art methods on three challenging datasets, offering an improvement of up to 13.7% in terms of segmental edit distance and up to 16.1% in terms of segmental F1 score. Our code will be publicly available soon.

Seito Kasai, Yuchi Ishikawa, Masaki Hayashi et al.

In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work takes on the novel task of action highlighting, which visualizes where and when actions occur in an untrimmed video setting. Action highlighting is a fine-grained task, compared to conventional action recognition tasks which focus on classification or window-based localization. Leveraging weak supervision from annotated captions, our framework acquires spatiotemporal relevance maps and generates local embeddings which relate to the nouns and verbs in captions. Through experiments, we show that our model generates various maps conditioned on different actions, in which conventional visual reasoning methods only go as far as to show a single deterministic saliency map. Also, our model improves retrieval recall over our baseline without alignment by 2-3% on the MSR-VTT dataset.

Naofumi Akimoto, Huachun Zhu, Yanghua Jin et al.

We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions. The resulting layers from decomposition pave the way for applications that benefit from layer-based editing, such as recoloring and compositing of images and videos. The current state-of-the-art approach for this problem is hindered by slow processing time due to its iterative nature, and consequently does not scale to certain real-world scenarios. To address this issue, we propose a neural network based method for this task that decomposes a given image into multiple layers in a single forward pass. Furthermore, our method separately decomposes the color layers and the alpha channel layers. By leveraging a novel training objective, our method achieves proper assignment of colors amongst layers. As a consequence, our method achieve promising quality without existing issue of inference speed for iterative approaches. Our thorough experimental analysis shows that our method produces qualitative and quantitative results comparable to previous methods while achieving a 300,000x speed improvement. Finally, we utilize our proposed method on several applications, and demonstrate its speed advantage, especially in video editing.

Tomoyuki Suzuki, Hirokatsu Kataoka, Yoshimitsu Aoki et al.

In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation. The proposed AdaLEA allows a model to gradually learn an earlier anticipation as training progresses. The loss function adaptively assigns penalty weights depending on how early the model can an- ticipate a traffic accident at each epoch. Additionally, we construct a Near-miss Incident DataBase for anticipation. This database contains an enormous number of traffic near- miss incident videos and annotations for detail evaluation of two tasks, risk anticipation and risk-factor anticipation. In our experimental results, we found our proposal achieved the highest scores for risk anticipation (+6.6% better on mean average precision (mAP) and 2.36 sec earlier than previous work on the average time-to-collision (ATTC)) and risk-factor anticipation (+4.3% better on mAP and 0.70 sec earlier than previous work on ATTC).

Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata et al.

In this paper, we propose a framework for recognizing human activities that uses only in-topic dominant codewords and a mixture of intertopic vectors. Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities. In LDA topic modeling, action videos (documents) are represented by a bag-of-words (input from a dictionary), and these are based on improved dense trajectories. The output topics correspond to human motion primitives, such as finger moving or subtle leg motion. We eliminate the impurities, such as missed tracking or changing light conditions, in each motion primitive. The assembled vector of motion primitives is an improved representation of the action. We demonstrate our method on four different datasets.