Akihiro Sugimoto

Khoa Vo, Kashu Yamazaki, Sang Truong et al. · cmu

Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great achievement in TAPG, most existing works ignore the human perception of interaction between agents and the surrounding environment by applying a deep learning model as a black-box to the untrimmed videos to extract video visual representation. Therefore, it is beneficial and potentially improve the performance of TAPG if we can capture these interactions between agents and the environment. In this paper, we propose a novel framework named Agent-Aware Boundary Network (ABN), which consists of two sub-networks (i) an Agent-Aware Representation Network to obtain both agent-agent and agents-environment relationships in the video representation, and (ii) a Boundary Generation Network to estimate the confidence score of temporal intervals. In the Agent-Aware Representation Network, the interactions between agents are expressed through local pathway, which operates at a local level to focus on the motions of agents whereas the overall perception of the surroundings are expressed through global pathway, which operates at a global level to perceive the effects of agents-environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks (i.e C3D, SlowFast and Two-Stream) show that our proposed ABN robustly outperforms state-of-the-art methods regardless of the employed backbone network on TAPG. We further examine the proposal quality by leveraging proposals generated by our method onto temporal action detection (TAD) frameworks and evaluate their detection performances. The source code can be found in this URL https://github.com/vhvkhoa/TAPG-AgentEnvNetwork.git.

Duc Minh Vo, Hong Chen, Akihiro Sugimoto et al.

Novel object captioning aims at describing objects absent from training data, with the key ingredient being the provision of object vocabulary to the model. Although existing methods heavily rely on an object detection model, we view the detection step as vocabulary retrieval from an external knowledge in the form of embeddings for any object's definition from Wiktionary, where we use in the retrieval image region features learned from a transformers model. We propose an end-to-end Novel Object Captioning with Retrieved vocabulary from External Knowledge method (NOC-REK), which simultaneously learns vocabulary retrieval and caption generation, successfully describing novel objects outside of the training dataset. Furthermore, our model eliminates the requirement for model retraining by simply updating the external knowledge whenever a novel object appears. Our comprehensive experiments on held-out COCO and Nocaps datasets show that our NOC-REK is considerably effective against SOTAs.

Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama

We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training by transferring immense knowledge from a well-trained teacher model through instructive attention maps. We train the pruning and distillation processes simultaneously on a well-known GAN architecture in an end-to-end manner. After training, all redundant parameters as well as the mask layers are discarded, yielding a lighter network while retaining the performance. We comprehensively illustrate, on ImageNet 128x128 dataset, PPCD-GAN reduces up to 5.2x (81%) parameters against state-of-the-arts while keeping better performance.

Trung-Nghia Le, Tam V. Nguyen, Minh-Quan Le et al.

The retrieval of 3D objects has gained significant importance in recent years due to its broad range of applications in computer vision, computer graphics, virtual reality, and augmented reality. However, the retrieval of 3D objects presents significant challenges due to the intricate nature of 3D models, which can vary in shape, size, and texture, and have numerous polygons and vertices. To this end, we introduce a novel SHREC challenge track that focuses on retrieving relevant 3D animal models from a dataset using sketch queries and expedites accessing 3D models through available sketches. Furthermore, a new dataset named ANIMAR was constructed in this study, comprising a collection of 711 unique 3D animal models and 140 corresponding sketch queries. Our contest requires participants to retrieve 3D models based on complex and detailed sketches. We receive satisfactory results from eight teams and 204 runs. Although further improvement is necessary, the proposed task has the potential to incentivize additional research in the domain of 3D object retrieval, potentially yielding benefits for a wide range of applications. We also provide insights into potential areas of future research, such as improving techniques for feature extraction and matching and creating more diverse datasets to evaluate retrieval performance. https://aichallenge.hcmus.edu.vn/sketchanimar

Duc Minh Vo, Quoc-An Luong, Akihiro Sugimoto et al.

Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time. In order to emulate this ability, we introduce a novel task called Anticipation Captioning, which generates a caption for an unseen oracle image using a sparsely temporally-ordered set of images. To tackle this new task, we propose a model called A-CAP, which incorporates commonsense knowledge into a pre-trained vision-language model, allowing it to anticipate the caption. Through both qualitative and quantitative evaluations on a customized visual storytelling dataset, A-CAP outperforms other image captioning methods and establishes a strong baseline for anticipation captioning. We also address the challenges inherent in this task.

Trung-Nghia Le, Tam V. Nguyen, Minh-Quan Le et al.

3D object retrieval is an important yet challenging task that has drawn more and more attention in recent years. While existing approaches have made strides in addressing this issue, they are often limited to restricted settings such as image and sketch queries, which are often unfriendly interactions for common users. In order to overcome these limitations, this paper presents a novel SHREC challenge track focusing on text-based fine-grained retrieval of 3D animal models. Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval. Despite the increased difficulty, we believe this task can potentially drive useful applications in practice and facilitate more intuitive interactions with 3D objects. Five groups participated in our competition, submitting a total of 114 runs. While the results obtained in our competition are satisfactory, we note that the challenges presented by this task are far from fully solved. As such, we provide insights into potential areas for future research and improvements. We believe we can help push the boundaries of 3D object retrieval and facilitate more user-friendly interactions via vision-language technologies. https://aichallenge.hcmus.edu.vn/textanimar

Jiaxuan Li, Duc Minh Vo, Akihiro Sugimoto et al.

Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data; yet novel objects occur frequently, necessitating the requirement of sustaining up-to-date object knowledge for open-world comprehension. Instead of relying on large amounts of data and/or scaling up network parameters, we introduce a highly effective retrieval-augmented image captioning method that prompts LLMs with object names retrieved from External Visual--name memory (EVCap). We build ever-changing object knowledge memory using objects' visuals and names, enabling us to (i) update the memory at a minimal cost and (ii) effortlessly augment LLMs with retrieved object names by utilizing a lightweight and fast-to-train model. Our model, which was trained only on the COCO dataset, can adapt to out-of-domain without requiring additional fine-tuning or re-training. Our experiments conducted on benchmarks and synthetic commonsense-violating data show that EVCap, with only 3.97M trainable parameters, exhibits superior performance compared to other methods based on frozen pre-trained LLMs. Its performance is also competitive to specialist SOTAs that require extensive training.

Jiaxuan Li, Junwen Mo, MinhDuc Vo et al.

Multimodal Large Language Models (MLLMs) have made notable advances in visual understanding, yet their abilities to recognize objects modified by specific attributes remain an open question. To address this, we explore MLLMs' reasoning capabilities in object recognition, ranging from commonsense to beyond-commonsense scenarios. We introduce a novel benchmark, NEMO, which comprises 900 images of origiNal fruits and their corresponding attributE-MOdified ones; along with a set of 2,700 questions including open-, multiple-choice-, unsolvable types. We assess 26 recent open-sourced and commercial models using our benchmark. The findings highlight pronounced performance gaps in recognizing objects in NEMO and reveal distinct answer preferences across different models. Although stronger vision encoders improve performance, MLLMs still lag behind standalone vision encoders. Interestingly, scaling up the model size does not consistently yield better outcomes, as deeper analysis reveals that larger LLMs can weaken vision encoders during fine-tuning. These insights shed light on critical limitations in current MLLMs and suggest potential pathways toward developing more versatile and resilient multimodal models.

Maëlic Neau, Zoe Falomir, Cédric Buche et al.

Scene Graph Generation (SGG) encodes visual relationships between objects in images as graph structures. Thanks to the advances of Vision-Language Models (VLMs), the task of Open-Vocabulary SGG has been recently proposed where models are evaluated on their functionality to learn a wide and diverse range of relations. Current benchmarks in SGG, however, possess a very limited vocabulary, making the evaluation of open-source models inefficient. In this paper, we propose a new reference-free metric to fairly evaluate the open-vocabulary capabilities of VLMs for relation prediction. Another limitation of Open-Vocabulary SGG is the reliance on weakly supervised data of poor quality for pre-training. We also propose a new solution for quickly generating high-quality synthetic data through region-specific prompt tuning of VLMs. Experimental results show that pre-training with this new data split can benefit the generalization capabilities of Open-Voc SGG models.

Paul Grimal, Michaël Soumm, Hervé Le Borgne et al.

State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or unintended blending of distinct concepts. We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt, ensuring that generated images faithfully reflect the corresponding prompts. Our method explicitly models the signal component during the denoising process, offering fine-grained control that mitigates over-optimization and out-of-distribution artifacts. Moreover, our framework is training-free and seamlessly integrates with both existing diffusion and flow matching architectures. It also supports additional conditioning modalities -- such as bounding boxes -- for enhanced spatial alignment. Extensive experiments demonstrate that our approach outperforms current state-of-the-art methods. The code is available at https://github.com/grimalPaul/gsn-factory.

Francesco Di Sario, Riccardo Renzulli, Marco Grangetto et al.

3D Gaussian Splatting enhances real-time performance in novel view synthesis by representing scenes with mixtures of Gaussians and utilizing differentiable rasterization. However, it typically requires large storage capacity and high VRAM, demanding the design of effective pruning and compression techniques. Existing methods, while effective in some scenarios, struggle with scalability and fail to adapt models based on critical factors such as computing capabilities or bandwidth, requiring to re-train the model under different configurations. In this work, we propose a novel, model-agnostic technique that organizes Gaussians into several hierarchical layers, enabling progressive Level of Detail (LoD) strategy. This method, combined with recent approach of compression of 3DGS, allows a single model to instantly scale across several compression ratios, with minimal to none impact to quality compared to a single non-scalable model and without requiring re-training. We validate our approach on typical datasets and benchmarks, showcasing low distortion and substantial gains in terms of scalability and adaptability.

Jaroslav Moravec, Radim Šára, Akihiro Sugimoto

Maintaining long-term accuracy of stereo camera calibration parameters is important for autonomous systems' perception. This work proposes Online Tracking of Essential Matrix by Stochastic Optimization (TESO). The core mechanisms of TESO are: 1) a robust loss function based on kernel correlation over tentative correspondences, 2) an adaptive online stochastic optimization on the essential manifold. TESO has low CPU and memory requirements, relies on a few hyperparameters, and eliminates the need for data-driven training, enabling the usage in resource-constrained online perception systems. We evaluated the influence of TESO on geometric precision, rectification quality, and stereo depth consistency. On the large-scale MAN TruckScenes dataset, TESO tracks rotational calibration drift with 0.12 deg precision in the Y-axis (critical for stereo accuracy) while the X- and Z-axes are five times more precise. Tracking applied to sequences with simulated drift shows similar precision with respect to the reference as tracking applied to no-drift sequences, indicating the tracker is unbiased. On the KITTI dataset, TESO revealed systematic inconsistencies in extrinsic parameters across stereo pairs, confirming previous published findings. We verified that intrinsic decalibration affected these errors, as evidenced by the conflicting behavior of the rectification and depth metrics. After correcting the reference calibration, TESO improved its rotation precision around the Y-axis 20 times to 0.025 deg and its depth accuracy 50 times. Despite its lightweight design, direct optimization of the proposed TESO loss function alone achieves accuracy comparable to that of neural network-based single-frame methods.

Viet-Khoa Vo-Ho, Ngan Le, Kashu Yamazaki et al.

Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process of understanding the video context due to lack of attention mechanism to express the concept of an action or an agent who performs the action or the interaction between the agent and the environment. Based on the action definition that a human, known as an agent, interacts with the environment and performs an action that affects the environment, we propose a contextual Agent-Environment Network. Our proposed contextual AEN involves (i) agent pathway, operating at a local level to tell about which humans/agents are acting and (ii) environment pathway operating at a global level to tell about how the agents interact with the environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks, i.e C3D and SlowFast, show that our method robustly exhibits outperformance against state-of-the-art methods regardless of the employed backbone network.

Trung-Nghia Le, Tam V. Nguyen, Zhongliang Nie et al.

Camouflaged objects attempt to conceal their texture into the background and discriminating them from the background is hard even for human beings. The main objective of this paper is to explore the camouflaged object segmentation problem, namely, segmenting the camouflaged object(s) for a given image. This problem has not been well studied in spite of a wide range of potential applications including the preservation of wild animals and the discovery of new species, surveillance systems, search-and-rescue missions in the event of natural disasters such as earthquakes, floods or hurricanes. This paper addresses a new challenging problem of camouflaged object segmentation. To address this problem, we provide a new image dataset of camouflaged objects for benchmarking purposes. In addition, we propose a general end-to-end network, called the Anabranch Network, that leverages both classification and segmentation tasks. Different from existing networks for segmentation, our proposed network possesses the second branch for classification to predict the probability of containing camouflaged object(s) in an image, which is then fused into the main branch for segmentation to boost up the segmentation accuracy. Extensive experiments conducted on the newly built dataset demonstrate the effectiveness of our network using various fully convolutional networks. \url{https://sites.google.com/view/ltnghia/research/camo}

Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto et al.

The internal geometry of most modern consumer cameras is not adequately described by the perspective projection. Almost all cameras exhibit some radial lens distortion and are equipped with an electronic rolling shutter that induces distortions when the camera moves during the image capture. When focal length has not been calibrated offline, the parameters that describe the radial and rolling shutter distortions are usually unknown. While for global shutter cameras, minimal solvers for the absolute camera pose and unknown focal length and radial distortion are available, solvers for the rolling shutter were missing. We present the first minimal solutions for the absolute pose of a rolling shutter camera with unknown rolling shutter parameters, focal length, and radial distortion. Our new minimal solvers combine iterative schemes designed for calibrated rolling shutter cameras with fast generalized eigenvalue and Groebner basis solvers. In a series of experiments, with both synthetic and real data, we show that our new solvers provide accurate estimates of the camera pose, rolling shutter parameters, focal length, and radial distortion parameters.

Hayato Onizuka, Zehra Hayirci, Diego Thomas et al.

Recovering the 3D shape of a person from its 2D appearance is ill-posed due to ambiguities. Nevertheless, with the help of convolutional neural networks (CNN) and prior knowledge on the 3D human body, it is possible to overcome such ambiguities to recover detailed 3D shapes of human bodies from single images. Current solutions, however, fail to reconstruct all the details of a person wearing loose clothes. This is because of either (a) huge memory requirement that cannot be maintained even on modern GPUs or (b) the compact 3D representation that cannot encode all the details. In this paper, we propose the tetrahedral outer shell volumetric truncated signed distance function (TetraTSDF) model for the human body, and its corresponding part connection network (PCN) for 3D human body shape regression. Our proposed model is compact, dense, accurate, and yet well suited for CNN-based regression task. Our proposed PCN allows us to learn the distribution of the TSDF in the tetrahedral volume from a single image in an end-to-end manner. Results show that our proposed method allows to reconstruct detailed shapes of humans wearing loose clothes from single RGB images.

Duc Minh Vo, Akihiro Sugimoto

Style transfer is to render given image contents in given styles, and it has an important role in both computer vision fundamental research and industrial applications. Following the success of deep learning based approaches, this problem has been re-launched recently, but still remains a difficult task because of trade-off between preserving contents and faithful rendering of styles. Indeed, how well-balanced content and style are is crucial in evaluating the quality of stylized images. In this paper, we propose an end-to-end two-stream Fully Convolutional Networks (FCNs) aiming at balancing the contributions of the content and the style in rendered images. Our proposed network consists of the encoder and decoder parts. The encoder part utilizes a FCN for content and a FCN for style where the two FCNs have feature injections and are independently trained to preserve the semantic content and to learn the faithful style representation in each. The semantic content feature and the style representation feature are then concatenated adaptively and fed into the decoder to generate style-transferred (stylized) images. In order to train our proposed network, we employ a loss network, the pre-trained VGG-16, to compute content loss and style loss, both of which are efficiently used for the feature injection as well as the feature concatenation. Our intensive experiments show that our proposed model generates more balanced stylized images in content and style than state-of-the-art methods. Moreover, our proposed network achieves efficiency in speed.

Duc Minh Vo, Akihiro Sugimoto

We propose an end-to-end network for image generation from given structured-text that consists of the visual-relation layout module and the pyramid of GANs, namely stacking-GANs. Our visual-relation layout module uses relations among entities in the structured-text in two ways: comprehensive usage and individual usage. We comprehensively use all available relations together to localize initial bounding-boxes of all the entities. We also use individual relation separately to predict from the initial bounding-boxes relation-units for all the relations in the input text. We then unify all the relation-units to produce the visual-relation layout, i.e., bounding-boxes for all the entities so that each of them uniquely corresponds to each entity while keeping its involved relations. Our visual-relation layout reflects the scene structure given in the input text. The stacking-GANs is the stack of three GANs conditioned on the visual-relation layout and the output of previous GAN, consistently capturing the scene structure. Our network realistically renders entities' details in high resolution while keeping the scene structure. Experimental results on two public datasets show outperformances of our method against state-of-the-art methods.

Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto et al.

This paper presents new efficient solutions to the rolling shutter camera absolute pose problem. Unlike the state-of-the-art polynomial solvers, we approach the problem using simple and fast linear solvers in an iterative scheme. We present several solutions based on fixing different sets of variables and investigate the performance of them thoroughly. We design a new alternation strategy that estimates all parameters in each iteration linearly by fixing just the non-linear terms. Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster. In addition, a linear non-iterative solver is presented that requires a non-minimal number of 9 correspondences but provides even better results than the state-of-the-art R6P. Moreover, all proposed linear solvers provide a single solution while the state-of-the-art R6P provides up to 20 solutions which have to be pruned by expensive verification.

Trung-Nghia Le, Akihiro Sugimoto

Focusing on only semantic instances that only salient in a scene gains more benefits for robot navigation and self-driving cars than looking at all objects in the whole scene. This paper pushes the envelope on salient regions in a video to decompose them into semantically meaningful components, namely, semantic salient instances. We provide the baseline for the new task of video semantic salient instance segmentation (VSSIS), that is, Semantic Instance - Salient Object (SISO) framework. The SISO framework is simple yet efficient, leveraging advantages of two different segmentation tasks, i.e. semantic instance segmentation and salient object segmentation to eventually fuse them for the final result. In SISO, we introduce a sequential fusion by looking at overlapping pixels between semantic instances and salient regions to have non-overlapping instances one by one. We also introduce a recurrent instance propagation to refine the shapes and semantic meanings of instances, and an identity tracking to maintain both the identity and the semantic meaning of instances over the entire video. Experimental results demonstrated the effectiveness of our SISO baseline, which can handle occlusions in videos. In addition, to tackle the task of VSSIS, we augment the DAVIS-2017 benchmark dataset by assigning semantic ground-truth for salient instance labels, obtaining SEmantic Salient Instance Video (SESIV) dataset. Our SESIV dataset consists of 84 high-quality video sequences with pixel-wisely per-frame ground-truth labels.

Trung-Nghia Le, Akihiro Sugimoto

Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and dynamic features computed from the low and middle levels are combined together. Our method utilizes such combined features spatially over each frame and, at the same time, temporally across frames using consistency between consecutive frames. Saliency cues in our method are analyzed through a multiscale segmentation model, and fused across scale levels, yielding to exploring regions efficiently. An adaptive temporal window using motion information is also developed to combine saliency values of consecutive frames in order to keep temporal consistency across frames. Performance evaluation on several popular benchmark datasets validates that our method outperforms existing state-of-the-arts.

Trung-Nghia Le, Akihiro Sugimoto

This paper presents a method for detecting salient objects in videos where temporal information in addition to spatial information is fully taken into account. Following recent reports on the advantage of deep features over conventional hand-crafted features, we propose a new set of SpatioTemporal Deep (STD) features that utilize local and global contexts over frames. We also propose new SpatioTemporal Conditional Random Field (STCRF) to compute saliency from STD features. STCRF is our extension of CRF to the temporal domain and describes the relationships among neighboring regions both in a frame and over frames. STCRF leads to temporally consistent saliency maps over frames, contributing to the accurate detection of salient objects' boundaries and noise reduction during detection. Our proposed method first segments an input video into multiple scales and then computes a saliency map at each scale level using STD features with STCRF. The final saliency map is computed by fusing saliency maps at different scale levels. Our experiments, using publicly available benchmark datasets, confirm that the proposed method significantly outperforms state-of-the-art methods. We also applied our saliency computation to the video object segmentation task, showing that our method outperforms existing video object segmentation methods.