37 accepted papers
Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models evaluate the quality of retrieval based on proximity, which cannot guarantee that the retrieved pattern has the strongest…
Machine unlearning, as a post-hoc processing technique, has gained widespread adoption in addressing challenges like bias mitigation and robustness enhancement. However, existing non-privacy unlearning-based solutions persist in using a binary data removal framework designed for privacy-driven motiv
Developing a universal graph model capable of generalizing across diverse graph domains has consistently been a key objective in graph learning. Recently, many studies have focused on achieving in-context learning (ICL) on graphs, which can generalize to novel tasks without the need for fine-tuning,
Visually cataloging and quantifying the natural world requires pushing the boundaries of both detailed visual classification and counting at scale. Despite significant progress, particularly in crowd and traffic analysis, the fine-grained, taxonomy-aware plant counting remains underexplored in visio
This letter presents empirical research on the non-reproducibility of light detection and ranging sensor (LiDAR)-inertial odometry (LIO) systems. Although the LIO community has made commendable efforts toward reproducible localization accuracy, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"
This letter presents empirical research on the non-reproducibility of light detection and ranging sensor (LiDAR)-inertial odometry (LIO) systems. Although the LIO community has made commendable efforts toward reproducible localization accuracy, noteworthy non-reproducibility remains, thus hindering …
The proliferation of recursive synthetic data training promises to alleviate data scarcity but introduces the existential risk of model collapse, wherein recursive training on synthetic data erodes distributional tails and homogenizes outputs. Current literature identifies data selection as a pivota…
Sparse convolution, operating convolutions on sparsely sampled areas via a learnable mask, has witnessed its powerful ability to accelerate detector inference speed on high-resolution drone images. However, the sparse mask in existing sparse convolution-based detection methods often struggles with a…
Due to privacy and cost issues, the lack of large-scale labeled datasets limits the advancement of person re-identification. Existing methods use generative adversarial networks or game engine rendering for data augmentation to improve re-identification performance. However, these approaches struggl…
Random Forests are widely recognized for establishing efficacy in classification and regression tasks, standing out in various domains such as medical diagnosis, finance, and personalized recommendations. These domains, however, are inherently sensitive to privacy concerns, as personal and confident…
Untethered magnetic manipulation of biomedical millirobots has a high potential for minimally invasive surgical applications. However, it is still challenging to exert high actuation forces on the small robots over a large distance. Permanent magnets offer stronger magnetic torques and forces than e
Magnetic helical micro-robots (microbots) have attracted strong interest due to their unique propulsion mechanisms and potential applications in biomedical fields, particularly in minimally-invasive surgical procedures. Earlier research primarily focused on studying helical microbots in viscous liqu
Machine unlearning strives to uphold the data owners' right to be forgotten by enabling models to selectively forget specific data. Recent advances suggest pre-computing and storing statistics extracted from second-order information and implementing unlearning through Newton-style updates. However,…
False correspondence removal is a persistent challenge in image feature-matching-based applications, especially in complex scenes. Traditional methods often rely on the consistency assumption to model the motion of correct correspondences, which neglects non-consistent correct correspondences, resul…
We present Perm, a learned parametric representation of human 3D hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair structure and local curl patterns, we propose to disentangle them using a PCA-based strand representation in the fr…
Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to effectively preprocess such low-light inputs, as they fail to…
Early detection of gastrointestinal (GI) cancer is critical for improving treatment outcomes and survival rates. Yet conventional endoscopic techniques remain invasive and labor-intensive, thus presenting significant challenges for cancer screening on large populations. Current commercially availabl
Table question answering (TQA) requires accurate retrieval and reasoning over tabular data. Existing approaches attempt to retrieve query-relevant content before leveraging large language models (LLMs) to reason over long tables. However, these methods often fail to accurately retrieve contextually
Surgical planning and training based on machine learning requires a large amount of 3D anatomical models reconstructed from medical imaging, which is currently one of the major bottlenecks. Obtaining these data from real patients and during surgery is very demanding, if even possible, due to legal,
Mobile edge computing (MEC) is a promising paradigm for real-time applications with intensive computational needs (e.g., autonomous driving), as it can reduce the processing delay. In this work, we focus on the timeliness of computational-intensive updates, measured by Age-of-Information (AoI), and…
Differentially Private Federated Learning (DP-FL) is a promising paradigm for training models on large-scale decentralized data under Differential Privacy (DP) guarantees which confronts two challenges: 1) providing a privacy guarantee without sacrificing model performance; 2) tackling system hetero…
On social media platforms, users’ emotions are triggered when they encounter particular content from other users,where such emotions are different from those that spontaneously emerged, owing to the “responsive” nature. Analyzing the aforementioned responsive emotions from user interactions is a tas…
Most of the research to date focuses on bilingual sign language translation (BSLT). However, such models are inefficient in building multilingual sign language translation systems. To solve this problem, we introduce the multilingual sign language translation (MSLT) task. It aims to use a single mod…
This paper attacks the challenging problem of sign language translation (SLT), which involves not only visual and textual understanding but also additional prior knowledge learning (i.e. performing style, syntax). However, the majority of existing methods with vanilla encoder-decoder structures fail…
Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant parallel data with a pivot language. Naturally, the key to triangular machine translation is the successful exploitatio…
Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT). Different from prior works where pre-trained models usually adopt an unidirectional decoder, this paper demonstrates that pre-training a sequence-to-sequence model but with a bidirectional decoder c…
Sentiment analysis on user-generated content has achieved notable progress by introducing user information to consider each individual’s preference and language usage. However, most existing approaches ignore the data sparsity problem, where the content of some users is limited and the model fails t…
One of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention network is O(n2), increasing quadratically with sequence length. By contrast, th…
Neural Machine Translation (NMT) has shown a strong ability to utilize local context to disambiguate the meaning of words. However, it remains a challenge for NMT to leverage broader context information like topics. In this paper, we propose heterogeneous ways of embedding topic information at the s…
Quality estimation (QE) of machine translation (MT) aims to evaluate the quality of machine-translated sentences without references and is important in practical applications of MT. Training QE models require massive parallel data with hand-crafted quality annotations, which are time-consuming and l…
Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each corpus in the training, so that the learning process is bal…
To obtain synchronized gait assistance, this paper presents a new delayless adaptive dual-oscillator (ADO) scheme to address the inherent delay issue. In the ADO structure, a new oscillator is coupled with the primitive one but the phase is adaptively feed-forward compensated. It’s remarkable that t…
While an important problem in the vision community is to design algorithms that can automatically caption images, few publicly-available datasets for algorithm development directly address the interests of real users. Observing that people who are blind have relied on (human-based) image captioning…
Photorealistic style transfer is the task of transferring the artistic style of an image onto a content target, producing a result that is plausibly taken with a camera. Recent approaches, based on deep neural networks, produce impressive results but are either too slow to run at practical resolutio…
This study aims to develop a wearable robotic exoskeleton to provide walking assistance for elderly and disabled people with weakened skeletal muscles. Our developed hip exoskeleton is powered by two electrical series elastic actuators covering both hip extension/flexion joints. For exoskeleton cont
Discovering social relations, e.g., kinship, friendship, etc., from visual contents can make machines better interpret the behaviors and emotions of human beings. Existing studies mainly focus on recognizing social relations from still images while neglecting another important media--video. On one h…
There are inter-frame and inter-element correlations in audio signal which we called correlated topography structure in this paper. The structure will be perturbed when a message is hided into the audio. Inspired by this principle, we propose a novel adaptive steganography scheme on audio by means o…