37 accepted papers
Omnidirectional images (ODIs) provide full 360$^{\circ} \times$ 180$^{\circ}$ view which are widely adopted in VR, AR and embodied intelligence applications. While multi-modal large language models (MLLMs) have demonstrated remarkable performance on conventional 2D image and video understanding benc…
Spiking Federated Learning (SFL) has been widely studied with the energy efficiency of Spiking Neural Networks (SNNs). However, existing SFL methods require model homogeneity and assume all clients have sufficient computational resources, resulting in the exclusion of some resource-constrained clien
The increasing impact of climate change and extreme weather events has spurred growing interest in deep learning for weather research. However, existing studies often rely on weather data in pixel space, which presents several challenges such as smooth outputs in model outputs, limited applicability…
We study the problem of orthogonal time frequency space (OTFS) waveform design for joint sensing and communications. Our main objective is to achieve a low peak-to-average power ratio (PAPR) for the OTFS waveform with DFT spread to communication symbols, so that good parameter estimation and bit err…
In this paper, we focus on the multi-waveform design for the joint radar and communications, wherein the elements of waveforms are required to take binary values and to support both good integrated sidelobe level (ISL) and information embedding (IE) performances simultaneously. Since the binary wave…
We study the design of orthogonal frequency division multiplexing (OFDM) waveform for the joint sensing and communications (JSC), whose sub-carriers are to be optimally coded by a set of sequences. To obtain such waveform that simultaneously exploits frequency diversity and modulation flexibility fo…
Multimodal information plays an important role in the advanced Internet of Things (IoT) in the era of 6G, which provides reliable and comprehensive assistance for downstream tasks through further fusion and analysis via federated learning (FL). One of the primary challenges in FL is data heterogenei…
We study the problem of jointly designing spatial-slow-time unimodular waveforms and receive adaptive filter for dual-function radar communications with reconfigurable intelligent surface (RIS), which aims to mitigate interference for radar and meanwhile to transfer accurate symbols for communicatio…
Model predictive control (MPC) has been applied to many platforms in robotics and autonomous systems for its capability to predict a system's future behavior while incorporating constraints that a system may have. To enhance the performance of a system with an MPC controller, one can manually tune t
We study the problem of constant-envelope precoding in massive MIMO communications with interference exploitation, whose main challenge lies in the non-convexity introduced by its constant-modulus constraints. Different from conventional approaches that typically involve constant-modulus approximati…
Learning with reduced labeling standards, such as noisy label, partial label, and supplementary unlabeled data, which we generically refer to as imprecise label, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label…
In this paper, we focus on the orthogonal frequency division multiplexing (OFDM) waveform design for the joint multipleinput multiple-output radar and communications. An efficient method to simultaneously reduce the integrated sidelobe level (ISL) and peak-to-mean envelope power ratio (PMEPR) of OFD…
In this paper, we investigate a local average sampling and reconstruction problem using the fractional Fourier transform (FRFT). We present certain necessary and sufficient conditions under which there is an average sampling theorem for signals bandlimited in the FRFT domain.
Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model. This paper aims to understand the nature of noise in pre-tra…
Few-Shot Learning (FSL) has been rapidly developed in recent years, potentially eliminating the requirement for significant data acquisition. Few-shot fine-tuning has been demonstrated to be practically efficient and helpful, especially for out-of-distribution datum. In this work, we first observe t…
In this paper, we propose an efficient algorithm for designing large-scale multi-unimodular waveforms with low correlations. Different from existing approaches that commonly involve repetitive projections of complex values into their constant-modulus approximations, we conduct optimizations directly…
The large-scale pre-training image-text foundation models have excelled in a number of downstream applications. The majority of domain generalization techniques, however, have never focused on mining linguistic modal knowledge to enhance model generalization performance. Additionally, text informati…
Recently, many arbitrary-oriented object detection (AOOD) methods have been proposed and applied to remote sensing and other fields. For aerial platforms, lightweight structure and multimodal adaptations of convolutional neural network (CNN) models are urgently needed. Due to the limited model size,…
Crop management has a significant impact on crop yield, economic profit, and the environment. Although management guidelines exist, finding the optimal management practices is challenging. Previous work used reinforcement learning (RL) and crop simulators to solve the problem, but the trained polici…
Traditional phase retrieval is generally concerned with re-covering a signal from its Fourier magnitude measurements whose inherent ambiguities make this problem especially difficult. In this work, we present an efficient phase retrieval technique from the single fractional Fourier transform (FrFT)…
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulatio…
Most domain adaptation (DA) methods focus on the case where the source data (SD) and target data (TD) with the same classes are obtained by the same sensor in cross-scene hyperspectral image (HSI) classification tasks. However, the classification performance is significantly reduced when there are n…
Recently, some lightweight convolutional neural network (CNN) models have been proposed for airborne or spaceborne remote sensing object detection (RSOD) tasks. However, these lightweight detectors suffer from performance degradation due to the compromise of limited computing resources on embedded d…
Improving the spatial resolution of a hyperspectral image (HSI) is of great significance in the remotely sensed field. By fusing a high-spatial-resolution multispectral image (MSI) with an HSI collected from the same scene, hyperspectral and multispectral (HS–MS) fusion has been an emerging techniqu…
In recent works, utilizing a deep network trained on meta-training set serves as a strong baseline in few-shot learning. In this paper, we move forward to refine novel-class features by finetuning a trained deep network. Finetuning is designed to focus on reducing biases in novel-class feature distr…
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural netw…
We deal with the problem of unimodular waveform(s) design with low correlation levels for the case of large-scale code lengths that can reach tens of thousands. Our primary goals are to reduce the resulting complexity with high efficiency, and meanwhile, to ensure an integrated sidelobe level (ISL)…
We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent representations easily interpreted as well. We start by coupling StyleG…
In this paper, we focus on the multiple-waveform design for the joint multiple-input multiple-output radar and communications system, which aims to simultaneously attain low integrated sidelobe level (ISL) of waveforms and accurate fast-time modulation for information embedding (IE). We propose a no…
Due to the limitation of image acquisition, hyperspectral remote sensing imagery is hard to reflect in both high spatial and spectral resolutions. Super-resolution (SR) is a technique which can improve the spatial resolution. Inspired by recent achievements in deep convolutional neural network (CNN)…
Collaborative classification of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data is investigated using effective hierarchical random walk networks, denoted as HRWN. The proposed HRWN jointly optimizes dual-tunnel CNN, pixelwise affinity and seeds map via a novel random walk l…
We introduce the OxUvA dataset and benchmark for evaluating single-object tracking algorithms. Benchmarks have enabled great strides in the field of object tracking by defining standardized evaluations on large sets of diverse videos. However, these works have focused exclusively on sequences that a…
This paper introduces a novel anchor design principle to support anchor-based face detection for superior scale-invariant performance, especially on tiny faces. To achieve this, we explicitly address the problem that anchor-based detectors drop performance drastically on faces with tiny sizes, e.g.…
This paper strives to track a target object in a video. Rather than specifying the target in the first frame of a video by a bounding box, we propose to track the object based on a natural language specification of the target, which provides a more natural human-machine interaction as well as a mean…
Fast and accurate detection of elderly falls can significantly reduce the rate of morbidity and mortality. In the past decade, extensive research has been performed to achieve real-time fall monitoring solutions. In this paper, we consider the radar-based modality and utilize the family of fractiona…
In this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated on the popular online track…
This paper aims for generic instance search from one example where the instance can be an arbitrary 3D object like shoes, not just near-planar and one-sided instances like buildings and logos. Firstly, we evaluate state-of-the-art instance search methods on this problem. We observe that what works f…