40 accepted papers
Purple flare, a diffuse chromatic aberration artifact commonly found around highlight areas, severely degrades the tone transition and color of the image. Existing traditional methods are based on hand-crafted features, which lack flexibility and rely entirely on fixed priors, while the scarcity of
Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional solutions rely on complex and expensive apochromatic (APO) lens hardware and the extraction of handcrafted features, ig
3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing
We propose LiveGesture, the first fully streamable, speech-driven full-body gesture generation framework that operates with zero look-ahead and supports arbitrary sequence length. Unlike existing co-speech gesture methods--which are designed for offline generation and either treat body regions indep
Temporal Action Detection (TAD) in untrimmed videos poses significant challenges, particularly for Activities of Daily Living (ADL) requiring models to (1) process long-duration videos, (2) capture temporal variations in actions, and (3) simultaneously detect dense overlapping actions. Existing CNN
Parameter-efficient fine-tuning (PEFT) is a scalable approach for adapting large speech foundation models to new domains. While methods such as LoRA and its state-of-the-art variants reduce adaptation costs, they typically allocate parameters uniformly across model subspaces, which limits their effi…
Recent advances in dance generation have enabled the automatic synthesis of 3D dance motions. However, existing methods still face significant challenges in simultaneously achieving high realism, precise dance-music synchronization, diverse motion expression, and physical plausibility. To address th
In this paper, we propose an algorithm for the removal of ghost targets based on angle estimation termed GREST (Ghost targets Removal using ESTAR). In the proposed GREST, the tentative targets reports, including the azimuth angles, is obtained through the conventional 3-D coherent integrations and s…
Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a given 2D image. However, HMR from a single image is an ill-posed…
Designing optimal prompts and reasoning processes for large language models (LLMs) on domain-specific tasks is both necessary and challenging in real-world applications. Determining how to integrate domain knowledge, enhance reasoning efficiency, and even provide domain experts with refined knowledg…
Rehabilitation robotics has attracted increasing attention due to its ability to provide continuous, precise, and adaptive treatment programs for stroke patients during their recovery. Accurately assessing lower-limb motor function is crucial in effectively implementing robot-assisted rehabilitation
Current Large Language Vision Models (LLVMs) trained on web videos perform well in general video understanding but struggle with fine-grained details, complex human-object interactions (HOI), and view-invariant representation learning essential for Activities of Daily Living (ADL). This limitation s…
Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while maintaining high-quality motion generation. To address these challenges, we propose MaskControl, the first approach to intr…
Reconstructing a 3D hand mesh from a single RGB image is challenging due to complex articulations, self-occlusions, and depth ambiguities. Traditional discriminative methods, which learn a deterministic mapping from a 2D image to a single 3D mesh, often struggle with the inherent ambiguities in 2D-t…
The introduction of vision-language models like CLIP has enabled the development of foundational video models capable of generalizing to unseen videos and human actions. However, these models are typically trained on web videos, which often fail to capture the challenges present in Activities of Dai…
How to integrate and verify spatial intelligence in foundation models remains an open challenge. Current practice often proxies Visual-Spatial Intelligence (VSI) with purely textual prompts and VQA-style scoring, which obscures geometry, invites linguistic shortcuts, and weakens attribution to genui…
Collaborative perception significantly enhances individual vehicle perception performance through the exchange of sensory information among agents. However, real-world deployment faces challenges due to bandwidth constraints and inevitable calibration errors during information exchange. To address t…
"Generating human motion from text has been dominated by denoising motion models either through diffusion or generative masking process. However, these models face great limitations in usability by requiring prior knowledge of the motion length. Conversely, autoregressive motion models address this…
Recent advances in text-to-motion generation using diffusion and autoregressive models have shown promising results. However these models often suffer from a trade-off between real-time performance high fidelity and motion editability. To address this gap we introduce MMM a novel yet simple motion g…
This paper considers object detection with millimeter-wave (mmWave) Wi-Fi beam training frames, e.g., beacon frames, in a monostatic passive directional multi-gigabit (DMG) sensing configuration. We derive an explicit signal model that accounts for the preamble, frame-to-frame antenna gains, and clu…
In contrast to existing multi-band Wi-Fi fusion in a frame-to-frame basis for simple classification, this paper considers asynchronous sequence-to-sequence fusion between sub-7GHz channel state information (CSI) and 60GHz beam SNR for more challenging downstream tasks such as continuous regression.…
Due to the noise and low spatial resolution in automotive radar data, exploring temporal relations of learnable features over consecutive 2 radar frames has shown performance gain on downstream tasks (e.g., object detection and tracking) in our previous study [1]. In this paper, we further enhance r…
Conventional radar feature extraction faces limitations due to low spatial resolution noise multipath reflection the presence of ghost targets and motion blur. Such limitations can be exacerbated by nonlinear object motion particularly from an ego-centric viewpoint. It becomes evident that to addres…
Indoor monitoring systems are in high demand to protect vulnerable people, especially when they are alone at home, in nursing homes, hospitals, etc. Although surveillance systems in public spaces use cameras and microphones to find incidents, indoor monitoring in personal spaces needs to protect pri…
We consider the problem of simultaneously learning a convex penalty function and its proximity operator for image reconstruction from incomplete measurements. Our goal is to apply Accelerated Proximal Gradient Method (APGM) using a learned proximity operator in place of the true proximity operator o…
Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities. The less-investigated skeleton-based gait recognition methods directly learn the gait dynamics from 2D/3D human skeleton sequences, which are theoreti…
This paper considers spatial-domain detector design for mutual interference mitigation among automotive MIMO-FMCW radars. This detector design is based on our previously derived interference signal model that fully accounts for the time-frequency incoherence and the slow-time code incoherence betwee…
We leverage standards-compliant beam training measurements from commercial-of-the-shelf (COTS) 802.11ad/ay devices for localization of a moving object. Two technical challenges need to be addressed: (1) the beam training measurements are intermittent due to beam scanning overhead control and content…
Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a nov…
We consider the object recognition problem in autonomous driving using automotive radar sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all-weather conditions for perception in autonomous driving. However, radar signals suffer from low angular resolution and precision in r…
"Unsupervised domain adaptation (UDA) borrows well-labeled source knowledge to solve the specific task on unlabeled target domain with the assumption that both domains are from a single sensor, e.g., RGB or depth images. To boost model performance, multiple sensors are deployed on new-produced devic…
Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL a…
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localization as a multi-modal sequence regression problem, a multi-stream recurrent fusion method is proposed to combine the curr…
Recent advances in solving imaging inverse problems have witnessed the combination of deep learning models with classical image models for better signal representation. One such approach, DeepRED, combines the deep image prior (DIP) with the regularization by denoising (RED) framework to boost the p…
This paper introduces a B-spline chained ellipses model representation for extended object tracking (EOT) using high-resolution automotive radar measurements. With offline automotive radar training datasets, the proposed model parameters are learned using the expectation-maximization (EM) algorithm.…
Motivated by real-world automotive radar measurements that are distributed around object (e.g., vehicles) edges with a certain volume, a novel hierarchical truncated Gaussian measurement model is proposed to resemble the underlying spatial distribution of radar measurements. With the proposed measur…
This paper considers object detection in the case of imperfect waveform separation, in the context of automotive radars with a slow-time MIMO-FMCW signaling scheme. We develop an explicit signal model that accounts for waveform separation residuals and propose a Kronecker subspace-based object detec…
This paper studies parameter estimation of a coupled mixture of polynomial phase signal (PPS) and sinusoidal frequency modulated (FM) signal, a newly introduced model motivated by industrial applications. Particularly, we analytically evaluate the estimation performance (or performance loss) via the…
In this paper, we propose a Bayesian inference approach to extract the binary reflectance pattern of samples from compressed measurements in the terahertz (THz) frequency band. Compared with existing compressed THz imaging methods relying on the sparsity of the reflectance pattern, the proposed Baye…
This paper considers adaptive signal detection in stochastic homogeneous environments where the disturbance covariance matrix of both test and training signals, R, is assumed to be a random matrix with a priori knowledge of R. Unlike existing detectors assuming a known hyperparameter associated with…