64 accepted papers
Learned image compression (LIC) outperforms traditional codecs but suffers from excessive peak memory usage when handling high-resolution images. Consequently, block-based LIC has been studied to reduce peak memory and peak computational cost, but it often introduces blocking artifacts that degrade
Collaborative planning under operational constraints is an essential capability for heterogeneous robot teams tackling complex large-scale real-world tasks. Unmanned Aerial Vehicles (UAVs) offer rapid environmental coverage, but flight time is often limited by energy constraints, whereas Unmanned Gr…
Visual agents employ tools such as zoom-in cropping within visual chains of thought to access fine-grained details. Prior work has primarily demonstrated the effectiveness of these tools on visual search tasks, leaving their applicability to more diverse and complex visual problems underexplored. In…
Tactile Walking Surface Indicators (TWSIs) are safety-critical landmarks that blind and low-vision (BLV) pedestrians use to locate crossings and hazard zones. From our observation sessions with BLV guide dog handlers, trainers, and an O&M specialist, we confirmed the critical importance of reliable …
This letter presents a hierarchical planning approach to the vehicle routing and scheduling problem (VRSP) for marsupial robotic systems, a specialized class of heterogeneous robotic systems in which one type of mobile robot is capable of carrying another. While traditional VRSPs have been widely st
This letter presents a hierarchical planning approach to the vehicle routing and scheduling problem (VRSP) for marsupial robotic systems, a specialized class of heterogeneous robotic systems in which one type of mobile robot is capable of carrying another. While traditional VRSPs have been widely st…
Relative pose estimation is crucial for coordinated multi-robot navigation. However, robots in close proximity often face intra-team occlusions, where teammates partially block each other's field of view, while dynamic environments further introduce environmental occlusions. Classical relative pose …
Sound source localization (SSL) is a fundamental task in spatial audio understanding, yet most deep neural network-based methods are constrained by fixed array geometries and predefined directional grids, limiting generalizability and scalability. To address these issues, we propose _audio-geometry-…
We address the task of universal compressed image restoration, which involves recovering high-quality images degraded by a wide range of codecs and compression levels. While prior methods have made significant progress, they typically target specific degradation types and struggle to generalize acro
An image captioning model flexibly switching its language pattern, e.g., descriptiveness and length, should be useful since it can be applied to diverse applications. However, despite the dramatic improvement in generative vision-language models, fine-grained control over the properties of generated…
How can we generate an image B' that satisfies A:A'::B:B', given the input images A,A' and B? Recent works have tackled this challenge through approaches like visual in-context learning or visual instruction. However, these methods are typically limited to specific models (InstructPix2Pix. Inpaintin…
Workload traces are essential to understand complex computer systems’ behavior and manage processing and memory resources. Since real-world traces are hard to obtain, synthetic trace generation is a promising alternative. This paper proposes a first-of-a-kind approach that relies on training a large
Composed Image Retrieval (CIR) seeks to retrieve a target image by using a reference image and conditioning text specifying desired modifications. While recent approaches have shown steady performance improvements on existing CIR benchmarks, we argue that it remains unclear whether these gains genui…
3D point clouds are increasingly vital for applications like autonomous driving and robotics, yet the raw data captured by sensors often suffer from noise and sparsity, creating challenges for downstream tasks. Consequently, point cloud upsampling becomes essential for improving density and uniformi…
In this paper, we consider new reconstruction loss together with a subband objective in the form of auxiliary loss function for artifacts-free speech super-resolution. Unlike prior work which mainly consider full band of frequency region for speech super-resolution, the proposed method alleviates di…
Scene Graph Generation (SGG) research has suffered from two fundamental challenges: the long-tailed predicate distribution and semantic ambiguity between predicates. These challenges lead to a bias towards head predicates in SGG models, favoring dominant general predicates while overlooking fine-gra…
The rapid evolution of large language models (LLMs) has revolutionized natural language processing (NLP) tasks such as text generation, translation, and comprehension. However, the increasing computational demands and inference costs of these models present significant challenges. This study investi…
Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annotation cost compared to Image Scene Graph Generation (ImgSGG). Although the annotation cost of VidSGG can be alleviated by…
Machine unlearning (MU) removes specific data points or concepts from deep learning models to enhance privacy and prevent sensitive content generation. Adversarial prompts can exploit unlearned models to generate content containing removed concepts, posing a significant security risk. However, exist…
Scene graph generation (SGG) models have suffered from inherent problems regarding the benchmark datasets such as the long-tailed predicate distribution and missing annotation problems. In this work, we aim to alleviate the long-tailed problem of SGG by utilizing unannotated triplets. To this end, w…
When legged robots perform agile movements, traditional RGB cameras often produce blurred images, posing a challenge for rapid perception. Event cameras have emerged as a promising solution for capturing rapid perception and coping with challenging lighting conditions thanks to their low latency, hi
Supervised deep learning has significantly improved bandwidth extension (BWE), whereas the emergence of self-supervised learning (SSL) has prompted the combined exploration of SSL and BWE. Although SSL-based deep learning models have shown to produce better representations than their supervised coun…
"This paper revives Densely Connected Convolutional Networks (DenseNets) and reveals the underrated effectiveness over predominant ResNet-style architectures. We believe DenseNets’ potential was overlooked due to untouched training methods and traditional design elements not fully revealing their ca…
"Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which reduces generalization to out-of-distribution (OOD) data and de…
In recent years, the role of robots across industries has become increasingly diverse, and they are now required to perform complex missions beyond simple repetitive tasks. However, robots used in confined spaces that humans cannot reach or in disaster field missions have challenges in performing va…
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard studies on WSSGG have utilized image captions to obtain unlocalized triplets while primarily focusing on groundi…
While advancements in Vision Language Models (VLMs) have significantly improved the alignment of visual and textual data, these models primarily focus on aligning images with short descriptive captions. This focus limits their ability to handle complex text interactions, particularly with longer tex…
We introduce StaccaToe, a human-scale, electric motor-powered single-leg robot designed to rival the agility of human locomotion through two distinctive attributes: an actuated toe and a co-actuation configuration inspired by the human leg. Leveraging the foundational design of HyperLeg’s lower leg…
Recent advances in 3D object detection leveraging multi-view cameras have demonstrated their practical and economical value in various challenging vision tasks. However, typical supervised learning approaches face challenges in achieving satisfactory adaptation toward unseen and unlabeled target dat…
Composed Image Retrieval (CIR) is a task that retrieves images similar to a query based on a provided textual modification. Current techniques rely on supervised learning for CIR models using labeled triplets of the <reference image text target image>. These specific triplets are not as commonly ava…
It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test data. However existing research predominantly focuses on cl…
In our daily life, when a small amount of sweat or water forms on a person's hand, we can empirically feel that the friction force of the hand increases, and the objects are gripped well. However, if sweat or water forms heavily, we can feel the friction decrease when holding an object. In this stud…
While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored. We identify that the domain gap can cause discrepancies in self-attention. Due to this gap, the transformer attends to spurious regions or pixels, which deteriorates…
Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of previously seen data, which increases memory costs and may viol…
Recently, large-scale pre-trained Vision-and-Language (VL) foundation models have demonstrated remarkable capabilities in many zero-shot downstream tasks, achieving competitive results for recognizing objects defined by as little as short text prompts. However, it has also been shown that VL models…
Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text allowing for numerous applications such as cross-modal retrieval, visual and multi-hop question answering, captioning, and many more. However, the aligned image-text spaces learned by all…
Our paper proposes a direct sparse visual odometry method that combines event and RGBD data to estimate the pose of agile-legged robots during dynamic locomotion and acrobatic behaviors. Event cameras offer high temporal resolution and dynamic range, which can eliminate the issue of blurred RGB imag…
Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural language prompts. However, recent works have uncovered a fundamen…
Pre-training on massive video datasets has become essential to achieve high action recognition performance on smaller downstream datasets. However, most large-scale video datasets contain images of people and hence are accompanied with issues related to privacy, ethics, and data protection, often pr…
Inspired by the great success of language model (LM)-based pre-training, recent studies in visual document understanding have explored LM-based pre-training methods for modeling text within document images. Among them, pre-training that reads all text from an image has shown promise, but often exhib…
A robot guide dog has compelling advantages over animal guide dogs for its cost-effectiveness, the potential for mass production, and low maintenance burden. However, despite the long history of guide dog robot research, previous studies were conducted with little or no consideration of how the guid…
Recently, learned image compression (LIC) has garnered increasing interest with its rapidly improving performance surpassing conventional codecs. A key ingredient of LIC is a hyperprior-based entropy model, where the underlying joint probability of the latent image features is modeled as a product o…
"Deep models must learn robust and transferable representations in order to perform well on new domains. While domain transfer methods (\eg, domain adaptation, domain generalization) have been proposed to learn transferable representations across domains, they are typically applied to ResNet backbon…
"While pose estimation is an important computer vision task, it requires expensive annotation and suffers from domain shift. In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on a synthetic source domain to a target domain without superv…
Active learning attempts to maximize a task model’s performance gain by obtaining a set of informative samples from an unlabeled data pool. Previous active learning methods usually rely on specific network architectures or task-dependent sample acquisition algorithms. Moreover, when selecting a batc…
Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models focusing on combining visual features from document images wit…
Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords, and utterance-level meaning. Feature transitions between utterances occur naturally. However, existing approaches fail to perceive the transitions because they extract features for the context at the coarse-gra…
Quadrupedal landing is a complex process involving large impacts, elaborate contact transitions, and is a crucial recovery behavior observed in many biological animals. This work presents a real-time, optimal landing controller that is free of pre-specified contact schedules. The controller determin…
This letter proposes and verifies a new method, the ring-pull mechanism, to overcome the disadvantages of existing wearable robotic gloves. By attaching a ring to the metacarpopha-langeal joint of the finger, the ring-pull mechanism supplements the grasping force of the user, while reducing the weig
We present a two-stage pre-training approach that improves the generalization ability of standard single-domain pre-training. While standard pre-training on a single large dataset (such as ImageNet) can provide a good initial representation for transfer learning tasks, this approach may result in bi…
Enabling mobile robots for solving challenging and diverse shape, texture, and motion related tasks with high fidelity vision requires the integration of novel multimodal imaging sensors and advanced fusion techniques. However, it is associated with high cost, power, hardware modification, and compu…
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data…
Today's robotic quadruped systems can robustly walk over a diverse range of rough but continuous terrains, where the terrain elevation varies gradually. Locomotion on discontinuous terrains, such as those with gaps or obstacles, presents a complementary set of challenges. In discontinuous settings,…
Semi-supervised learning (SSL) is an effective means to leverage unlabeled data to improve a model’s performance. Typical SSL methods like FixMatch assume that labeled and unlabeled data share the same label space. However, in practice, unlabeled data can contain categories unseen in the labeled set…
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled ta…
The ability to measure multi-axis contact forces and contact surface normals in real time is critical to allow robots to improve their dexterous manipulation and locomotion abilities. This paper presents a new fingertip sensor for 3-axis contact force and contact location detection, as well as impro…
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many langu…
Animal-level agility and robustness in robots cannot be accomplished by solely relying on blind locomotion controllers. A significant portion of a robot’s ability to traverse terrain comes from reacting to the external world through visual sensing. However, embedding the sensors and compute that pro…
Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap between the two domains. While some methods address target settings with either partial or open-set categories, they as…
In robotic tasks that require physical interactions such as manipulation and legged locomotion, it is important to simultaneously measure contact forces and contact angles. This paper presents a unified solution for simultaneously measuring three axis contact forces and contact angles for legged loc…
Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target domain. To address this semi-sup…
Deep models are state-of-the-art or many vision tasks including video action recognition and video captioning. Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions. Grounding decisions made by deep networks has been studied…
In this paper, we present a sampling-based kino-dynamic planning framework for a bipedal robot in complex environments. Unlike other footstep planning algorithms which typically plan footstep locations and the biped dynamics in separate steps, we handle both simultaneously. Three primary advantages…