55 accepted papers
Effective dexterous manipulation hinges on the dynamic integration of visual context with fine-grained tactile feedback. This remains a significant challenge, as existing methods often rely on static fusion strategies and struggle to learn from isolated tactile features. To address this, we propose
Sampling-based path planning algorithms like the Fast Marching Tree (FMT<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup>) often suffer from redundant exploration and inefficient sampling in complex 3D environments. To tackle these issues, this pa
Combining predictions from heterogeneous classifiers—such as in-house deep learning models, human experts, and large language models (LLMs)—is a key challenge, especially in data-scarce environments such as humanitarian operations. We propose a flexible Bayesian framework to effectively fuse these d
Scalable Vector Graphics (SVG) are central to digital design due to their inherent scalability and editability. Despite significant advancements in content generation enabled by Visual Language Models (VLMs), existing text-to-SVG generation methods are limited by a core challenge: the autoregressive
Vision-language models (VLMs) have progressed rapidly with large-scale high-quality data and adaptation strategies, yet remain brittle under real-world corruptions, where both visual recognition and language-grounded reasoning degrade. Beyond cascaded image restoration, a natural alternative is para…
Humanoid robots are promising to learn a diverse set of human-like locomotion behaviors, including standing up, walking, running, and jumping. However, existing methods predominantly require training independent policies for each skill, yielding behavior-specific controllers that exhibit limited gen
Existing deep learning-based models for remote sensing pansharpening exhibit exceptional performance on training datasets. However, due to sensor-specific characteristics and varying imaging conditions, these models suffer from substantial performance degradation when applied to unseen satellite dat…
Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that h…
Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities. Previous event studies, constrained by static single-companies analyses and simplistic assumptions, fail to capture these ripple effects. While large language models (LLMs) offer emergent reason…
The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich in semantic information, have fewer occurrences in tokenized…
Multi-intent utterances processing remains a persistent challenge due to intricate intent-slot dependencies and semantic ambiguities. Traditional methods struggle to model these complex interactions, particularly when handling overlapping slot structures across multiple intents. This paper introduce
In visual object tracking via unmanned aerial vehicle (UAV), discriminative correlation filtering (DCF) is one of the major methods owing to circulant samples which can be utilized not only for computing economically but also to hasten the optimization of filters. The universal DCF methods are seen…
Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their operation at the individual sample point level and the need for n…
Automatic Radiology Report Generation (RRG) is an important topic for alleviating the substantial workload of radiologists. Existing RRG approaches rely on supervised regression based on different architectures or additional knowledge injection, while the generated report may not align optimally wit…
Robot task planning is an important problem for autonomous robots in long-horizon challenging tasks. As large pre-trained models have demonstrated superior planning ability, recent research investigates utilizing large models to achieve autonomous planning for robots in diverse tasks. However, sinc…
Deep reinforcement learning (DRL) has achieved remarkable success in various domains, yet its reliance on neural networks results in a lack of transparency, which limits its practical applications in safety-critical and human-agent interaction domains. Decision trees, known for their notable explain…
Deep learning approaches for multimodal aspect-level sentiment classification (MALSC) often require extensive data, which is costly and time-consuming to obtain. To mitigate this, current methods typically fine-tune small-scale pretrained models like BERT and BART with few-shot examples. While these…
Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors which is an effective condition for facial expression manipulation. However publicly available datasets containing intensity annotations for multiple AUs remain severely limited often featuring a…
Previous probabilistic models for 3D Human Pose Estimation (3DHPE) aimed to enhance pose accuracy by generating multiple hypotheses. However, most of the hypotheses generated deviate substantially from the true pose. Compared to deterministic models, the excessive uncertainty in probabilistic models…
Differentiable Architecture Search (DARTS) has achieved a rapid search for excellent architectures by optimizing architecture parameters through gradient descent. However, this efficiency comes with a significant challenge: the risk of premature convergence to local optima, resulting in subpar perfo…
Object detection (OD) in computer vision has made significant progress in recent years, transitioning from closed-set labels to open-vocabulary detection (OVD) based on large-scale vision-language pre-training (VLP). However, current evaluation methods and datasets are limited to testing generalizat…
Distribution shifts over time are common in real-world machine-learning applications. This scenario is formulated as Evolving Domain Generalization (EDG), where models aim to generalize well to unseen target domains in a time-varying system by learning and leveraging the underlying evolving pattern…
Existing saliency object detection (SOD) methods struggle to satisfy fast inference and accurate results simultaneously in high resolution scenes. They are limited by the quality of public datasets and efficient network modules for high-resolution images. To alleviate these issues, we propose to con…
Video summarization involves creating a succinct overview by merging the valuable parts of a video. Existing video summarization methods approach this task as a problem of selecting keyframes by frame- and shot-level techniques with unimodal or bimodal information. Besides underestimated inter-relat…
Weakly-supervised Temporal Action Localization (W-TAL) is a challenging task aiming to achieve both action class identification and localization of temporal boundaries using video-level label learning. Recent methods resort to basic cascading or integration of appearance and optical flow features, o…
High-accuracy positioning has become a fundamental enabler for intelligent connected devices. Nevertheless, the present wireless networks still rely on model-driven approaches to achieve positioning functionality, which are susceptible to performance degradation in practical scenarios, primarily due…
Norwegian, spoken by only 5 million population, is under-representative within the most impressive breakthroughs in NLP tasks. To the best of our knowledge, there has not yet been a comprehensive evaluation of the existing language models (LMs) on Norwegian generation tasks during the article writin…
With the rapid advancement of Natural Language Processing in recent years, numerous studies have shown that generic summaries generated by Large Language Models (LLMs) can sometimes surpass those annotated by experts, such as journalists, according to human evaluations. However, there is limited res…
Molecule synthesis through machine learning is one of the fundamental problems in drug discovery. Current data-driven strategies employ one-step retrosynthesis models and search algorithms to predict synthetic routes in a top-bottom manner. Despite their effective performance, these strategies face…
Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for collecting expert datasets. Therefore, these methods may fail to w…
Miniature rotation actuators have been extensively developed and utilized in optical coherence tomography (OCT) endoscopy, enabling distortion-free OCT imaging in complex and tortuous environments. However, the use of electrical-driven rotation actuators raises safety concerns. Although magnetic-dri…
Image-to-video (I2V) generation aims to create a video sequence from a single image, which requires high temporal coherence and visual fidelity. However, existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. Moreover, they require a large amoun…
Nowadays, neural vocoders are preferred for their ability to synthesize high-fidelity audio. However, training a neural vocoder requires a massive corpus of high-quality real audio, and the audio recording process is often labor-intensive. In this work, we propose a synthetic corpus generation metho…
Bayesian Optimization (BO) has recently received increasing attention due to its efficiency in optimizing expensive-to-evaluate functions. For some practical problems, it is essential to consider the path-dependent switching cost between consecutive sampling locations given a total traveling budget…
In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI objective tends to learn simple and static skills and may hinder e…
Recently, most transformer-based approaches have achieved considerable success on vision tasks, even better than those with convolution neural networks (CNNs). In this paper, we present a novel transformer-based model, named detecting text with transformers (DTTR), for scene text detection. In DTTR,…
One of the most challenging problems in federated learning is the convergence speed problem caused by heterogeneity. We propose a novel structure called FedSD, a new method to accelerate the model convergence. We change the one-stage-cycle iteration structure to a 2-stage-cycle one to get the latest…
Image matting is a fundamental technique in visual understanding and has become one of the most significant capabilities in mobile phones. Despite the development of mobile storage and computing power, achieving diverse mobile Artificial Intelligence Generated Content (AIGC) applications remains a g…
Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training and evaluating on multiple corpora from different domains are less studied. This paper explores methods of generating rele…
Offline Reinforcement Learning (RL) aims to learn policies from previously collected datasets without exploring the environment. Directly applying off-policy algorithms to offline RL usually fails due to the extrapolation error caused by the out-of-distribution (OOD) actions. Previous methods tackle…
Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not known to hold generally with dependent samples, such as in onl…
Jumping motion is an effective way to overcome large obstacles, especially for the miniature robots. However, controlling of the jumping trajectory on a centimeter scale robot is not easy due to the limitation of size and payload. None of the jumping robots lighter than 90 g achieved the feedback co…
Although multi-person human pose estimation has made great progress in recent years, the challenges such as various scales of persons, occluded keypoints, and crowded backgrounds in complex scenes are still remained to be solved. In this paper, we propose a novel multi-level pose estimation network…
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards. However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dyn…
The study of keyword spotting, a subfield within the broader field of speech recognition that centers around identifying individual keywords in speech audio, has gained particular importance in recent years with the rise of personal voice assistants such as Alexa. As voice assistants aim to rapidly…
The development and control of biological actuators have been an active research field. Biological actuators revealed high mobility with compact dimensions, which is critical for the design of microrobots. The powerful kicking motion of the locust is important for its quick jumping. Herein, we exami…
One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with Deep Reinforcement Learning (DRL). In this paper, we propose a…
Synthesizing fluent code-switched (CS) speech with consistent voice using only monolingual corpora is still a challenging task, since language alternation seldom occurs during training and the speaker identity is directly correlated with language. In this paper, we present a bilingual phonetic poste…
Accurate bounding box estimation has recently attracted much attention in the tracking community because traditional multi-scale search strategies cannot estimate tight bounding boxes in many challenging scenarios involving changes to the target. A tracker capable of detecting target corners can fle…
This paper presents a novel feature-based method that is built upon a convolutional neural network (CNN) to learn the deep representation for multimodal retinal image registration. We coined the algorithm deep step patterns, in short DeepSPa. Most existing deep learning based methods require a set o…
In this paper, we study the problem of multitask metric learning (mtML). We first examine the generalization bound of the regularized mtML formulation based on the notion of algorithmic stability, proving the convergence rate of mtML and revealing the trade-off between the tasks. Moreover, we also e…
Bidirectional long short-term memory (BLSTM) based speech synthesis has shown great potential in improving the quality of the synthetic speech. However, for low-resource languages, it is difficult to obtain a high quality BLSTM model. BLSTM based speech synthesis can be viewed as a transformation be…
Emotion is expressed in multiple modalities, yet most research has considered at most one or two. This stems in part from the lack of large, diverse, well-annotated, multimodal databases with which to develop and test algorithms. We present a well-annotated, multimodal, multidimensional spontaneous…
To solve the acoustic-to-articulatory inversion problem, this paper proposes a deep bidirectional long short term memory recurrent neural network and a deep recurrent mixture density network. The articulatory parameters of the current frame may have correlations with the acoustic features many frame…
We consider the joint channel and power allocation problem for the OFDMA system. The problem is to find a joint channel and power allocation strategy to minimize the total transmission power subject to quality of service constraints and the OFDMA constraint (i.e, at most one user is allowed to acces…