85 accepted papers
Knee pain is prevalent in over 20% of the population, limiting the mobility of those affected. In turn, isokinetic dynamometers and robots have been used to facilitate rehabilitation for those still capable of ambulation. However, there are at most only a few wearable robots capable of delivering is…
Modern industrial quality control heavily relies on automated anomaly detection. While few-shot anomaly detection addresses the challenge of limited labeled data, real-world inspection faces a vast diversity of anomaly types, sizes, and shapes. We identify the primary cause for the anomaly detection
The emergence of foundation models has substantially advanced zero-shot generalization in monocular depth estimation (MDE), as exemplified by the Depth Anything series. However, given access to some data from downstream tasks, a natural question arises: can the performance of these models be further
Gait recognition has emerged as a promising biometric technique for long-distance and non-intrusive human identification. While Transformers have revolutionized vision tasks, their adaptation to gait recognition remains underexplored due to domain-specific challenges such as sparse silhouette modali
We introduce spatio-temporal omni-object video grounding, dubbed $\textbf{OmniSTVG}$, a new STVG task aiming to localize spatially and temporally all targets mentioned in the textual query within videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not onl…
Atmospheric turbulence causes spatially varying distortion and blur in long-range imaging, making restoration highly challenging in real-world applications. Supervised methods rely on synthetic training data, whose simulated degradation often cannot faithfully reflect real turbulence. Existing unsup
When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases computational costs and forces the model to spend extra training time e
When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases computational costs and forces the model to spend extra training time e…
Existing video editing methods face a critical trade-off: expert models offer precision but rely on task-specific priors like masks, hindering unification; conversely, unified temporal in-context learning models are mask-free but lack explicit spatial cues, leading to weak instruction-to-region mapp
Vision-based teleoperation systems are widely used due to their cost-effectiveness and intuitive operation. However, these systems often suffer from challenges such as hand occlusions, environmental variability, and the lack of tactile feedback, limiting their precision and applicability in complex
Recently, leveraging pre-trained vision-language models (VLMs) for building vision-language-action (VLA) models has emerged as a promising approach to effective robot manipulation learning. However, only few methods incorporate 3D signals into VLMs for action prediction, and they do not fully levera…
The advent of simulation engines has revolutionized learning and operational efficiency for robots, offering cost-effective and swift pipelines. However, the lack of a universal simulation platform tailored for chemical scenarios impedes progress in robotic manipulation and visualization of reaction
Collaborative learning enhances the performance and adaptability of multi-robot systems in complex tasks but faces significant challenges due to high communication overhead and data heterogeneity inherent in multi-robot tasks. To this end, we propose CoCoL, a Communication efficient decentralized Co
Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined masks, failing to capture heterogeneous attention patterns. T…
Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality features faces domain gaps from hardware diversity and deploy…
Transparent objects are common in daily life, while their optical properties pose challenges for RGB-D cameras to capture accurate depth information. This issue is further amplified when these objects are hand-held, as hand occlusions further complicate depth estimation. For assistant robots, howeve
Most existing decentralized learning methods with differential privacy (DP) guarantee rely on constant gradient clipping bounds and fixed-level DP Gaussian noises for each node throughout the training process, leading to a significant accuracy degradation compared to non-private counterparts. In thi
Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid objects with clear displacement and minimal occlusion. In th…
Pedestrian attribute recognition (PAR) seeks to predict multiple semantic attributes associated with a specific pedestrian. There are two types of approaches for PAR: unimodal framework and bimodal framework. The former one is to seek a robust visual feature. However, the lack of exploiting semantic…
The robotics community has consistently aimed to achieve generalizable robot manipulation with flexible natural language instructions. One primary challenge is that obtaining robot trajectories fully annotated with both actions and texts is time-consuming and labor-intensive. However, partially-anno
Vision-language models heavily rely on visual representations, yet ensuring its efficiency remains a critical challenge. Most existing approaches focus on reducing visual tokens either at the visual encoder phase or during the LLM decoder stage. Inspired by human visual cognition, where an initial g…
Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, inc…
Transformer has attracted increasing interest in spatio-temporal video grounding, or STVG, owing to its end-to-end pipeline and promising result. Existing Transformer-based STVG approaches often leverage a set of object queries, which are initialized simply using zeros and then gradually learn targe…
Aerial Vision-Dialog Navigation (AVDN) is a new task that requires drones to navigate to a target location based on human-robot dialog history. This paper focuses on the critical fine-grained cross-modal alignment problem in AVDN, requiring the drone to align language entities with visual landmarks…
Multimodal dialogue emotion recognition integrates data from multiple modalities to accurately identify emotional states in conversations. However, differences in expression and information density across modalities complicate the fusion of features. Traditional methods may introduce redundant infor…
This paper addresses the source localization problem by introducing RoLocMe, a multi-agent reinforcement learning system that integrates SkipNet - a skip-connection-based RSS estimation model - with parallel Q-learning. SkipNet predicts RSS propagation of the entire search region, enabling agents to
Obtaining word timestamp information from end-to-end (E2E) ASR models remains challenging due to the lack of explicit time alignment during training. This issue is further complicated in multilingual models. Existing methods, either rely on lexicons or introduce additional tokens, leading to scalabi…
Visuotactile sensors provide high-resolution tactile information but are incapable of perceiving the material features of objects. We present UltraTac, an integrated sensor that combines visuotactile imaging with ultrasound sensing through a coaxial optoacoustic architecture. The design shares struc
Low-light image enhancement (LLIE) aims to improve visibility and signal-to-noise ratio in images captured under poor lighting conditions. While deep learning has shown promise in this domain, current approaches require extensive paired training data, limiting their practical utility. We present a n…
In this paper, we explore the joint design of a transmit waveform and receive filter to enhance the detection performance of multiple-input multiple-output (MIMO) radar. Target echoes are assumed to be embedded in signal-dependent interference and colored Gaussian noise. As design metrics, we exploi…
A novel mmWave radar SLAM method is proposed to integrate multi-dimensional information, including velocity, spatial, RCS, and semantics to enable autonomous navigation in subterranean tunnel environments, which are characterized by low visibility and degraded conditions. By combining doppler odomet
In this paper, we show that applying adaptive methods directly to distributed minimax problems can result in non-convergence due to inconsistency in locally computed adaptive stepsizes. To address this challenge, we propose D-AdaST, a Distributed Adaptive minimax method with Stepsize Tracking. The k…
In this paper, we investigate and evaluate large language models’ capability in location prediction. We present experimental results with four models—FLAN-T5, FLAN-UL2, FLAN-Alpaca, and ChatGPT—in various instruction finetuning and exemplar settings. We analyze whether taking into account the contex…
In various domains such as surveillance and smart retail pedestrian retrieval centering on person re-identification (Re-ID) plays a pivotal role. Existing Re-ID methodologies often overlook subtle internal attribute variations which are crucial for accurately identifying individuals with changing ap…
Spatio-temporal video grounding (or STVG) task aims at locating a spatio-temporal tube for a specific instance given a text query. Despite advancements current methods easily suffer the distractors or heavy object appearance variations in videos due to insufficient object information from the text l…
To foster an immersive and natural human-robot interaction (HRI), the implementation of tactile perception and feedback becomes imperative, effectively bridging the conventional sensory gap. In this paper, we propose a dual-modal electronic skin (e-skin) that integrates magnetic tactile sensing and…
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approaches often fully fine-tune a dual-branch encoder-decoder framework with a complicated feature fusion strategy for achiev
Vision-and-Language Navigation (VLN) requires an agent to dynamically explore environments following natural language. The VLN agent, closely integrated into daily lives, poses a substantial threat to the security of privacy and property upon the occurrence of malicious behavior. However, this serio…
"Gait recognition is to seek correct matches for query individuals by their unique walking patterns. However, current methods focus solely on extracting individual-specific features, overlooking “interpersonal” relationships. In this paper, we propose a novel Relation Descriptor that captures not on…
Pre-trained vision-language models (VLMs) have achieved high performance on various downstream tasks which have been widely used for visual grounding tasks in a weakly supervised manner. However despite the performance gains contributed by large vision and language pre-training we find that state-of…
In this paper, we propose a differentially private decentralized learning method (termed PrivSGP-VR) which employs stochastic gradient push with variance reduction and guarantees (epsilon, delta)-differential privacy (DP) for each node. Our theoretical analysis shows that, under DP Gaussian noise wi…
Pedestrian Attribute Recognition (PAR) involves identifying the attributes of individuals in person images. Existing PAR methods typically rely on CNNs as the backbone network to extract pedestrian features. However, CNNs process only one adjacent region at a time, leading to the loss of long-range…
The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distr…
With the advance of language models, privacy protection is receiving more attention. Training data extraction is therefore of great importance, as it can serve as a potential tool to assess privacy leakage. However, due to the difficulty of this task, most of the existing methods are proof-of-concep…
Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through complex environments based on natural language instructions. In contrast to conventional approaches, which primarily focus on the spatial domain exploration, we propose a paradigm shift toward the F…
Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for debiasing, which are resource-intensive and costly. Furthermore, th…
Planar object tracking is a critical computer vision problem and has drawn increasing interest owing to its key roles in robotics, augmented reality, etc. Despite rapid progress, its further development, especially in the deep learning era, is largely hindered due to the lack of large-scale challeng…
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain. As an important tool of regularizing the distribution, batch normalization (BN) has been widely used in existing methods. However, they n…
Hyperspectral image (HSI) reconstruction is about recovering a 3D HSI from its 2D snapshot measurements, to which deep models have become a promising approach. However, most existing studies train deep models on large amounts of organized data, the collection of which can be difficult in many applic…
Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which are trained on millions or billions of paired images and texts. Different from them, this paper studies a new scenario as unpaired image-text matching, in which paired images and tex…
Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, most existing works focus more on learning with the explicit prior graph structure…
We develop a general framework unifying several gradient-based stochastic optimization methods for empirical risk minimization problems both in centralized and distributed scenarios. The framework hinges on the introduction of an augmented graph consisting of nodes modeling the samples and edges mod…
Long-Term person re-identification (LT-reID) exposes extreme challenges because of the longer time gaps between two recording footages where a person is likely to change clothing. There are two types of approaches for LT-reID: biometrics-based approach and data adaptation based approach. The former…
In recent years, single image dehazing deep models based on Atmospheric Scattering Model (ASM) have achieved remarkable results. But the dehazing outputs of those models suffer from color shift. Analyzing the ASM model shows that the atmospheric light factor (ALF) is set as a scalar which indicates…
Targeting both computing and coding efficiencies, we propose in this work a novel hierarchical bit-wise differential coding scheme to compress point cloud attributes. The encoder firstly quantizes and organizes the points into an octree structure and, for each internal node, picks its attribute(s) f…
While widely used in industry, recurrent neural networks (RNNs) are known to have deficiencies in dealing with long sequences (e.g. slow inference, vanishing gradients etc.). Recent research has attempted to accelerate RNN models by developing mechanisms to skip irrelevant words in input. Due to th…
In Vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions. Cross-modal alignment is one of the most critical challenges in VLN because the predicted trajectory needs to match the given instruction accurately. In this paper,…
Heatmap regression has become the most prevalent choice for nowadays human pose estimation methods. The ground-truth heatmaps are usually constructed by covering all skeletal keypoints by 2D gaussian kernels. The standard deviations of these kernels are fixed. However, for bottom-up methods, which n…
To maximize the signal-to-interference-plus-noise ratio (SINR) under a constant-envelope constraint, an efficient joint design of the transmit waveform and the receive filter for multipleinput multiple-output (MIMO) radars is essential. In this paper, we propose a novel optimization framework to sol…
We present our solution for unsupervised rapid speaker adaptation in a state-of-art presentation and intelligent meeting transcription system. We adopt the Kullback-Leibler (KL) divergence regularized model adaptation paradigm. For the adaptation architecture, we found that the linear projection lay…
We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains. With NLE method, we distill the knowledge from a powerful source-domain DNN into a dictionary of label embeddings,…
Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification. Recent studies have attempted to accelerate RNNs via various ad hoc mechanisms to skip irrelevant words in…
Low-resolution person re-identification (LR re-id) is a challenging task with low-resolution probes and high-resolution gallery images. To address the resolution mismatch, existing methods typically recover missing details for low-resolution probes by super-resolution. However, they usually pre-spec…
Even though most existing monocular 3D pose estimation approaches achieve very competitive results, they ignore the heterogeneity among human body parts by estimating them with the same network architecture. To accurately estimate 3D poses of different body parts, we attempt to build a part-aware 3D…
Previous methods decompose blind super resolution (SR) problem into two sequential steps: \textit{i}) estimating blur kernel from given low-resolution (LR) image and \textit{ii}) restoring SR image based on estimated kernel. This two-step solution involves two independently trained models, which may…
We propose to use the personalized speech synthesis and the neural language generator to synthesize content relevant personalized speech for rapid speaker adaptation. It has two distinct aspects: First, it relieves the general data sparsity issue in rapid adaptation via making use of additional synt…
Image and sentence matching has drawn much attention recently, but due to the lack of sufficient pairwise data for training, most previous methods still cannot well associate those challenging pairs of images and sentences containing rarely appeared regions and words, i.e., few-shot content. In this…
Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of pixel-level annotations which are expensive and time-consuming. To address this problem, it is a good choice to learn to…
Current studies on action detection in untrimmed videos are mostly designed for action classes, where an action is described at word level such as jumping, tumbling, swing, etc. This paper focuses on a rarely investigated problem of localizing an activity via a sentence query which would be more cha…
Encoding individual facial expressions via action units (AUs) coded by the Facial Action Coding System (FACS) has been found to be an effective approach in resolving the ambiguity issue among different expressions. While a number of methods have been proposed for AU detection, robust AU detection in…
Cross-domain person re-identification (re-ID) is challenging due to the bias between training and testing domains. We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces difficulties to extract robust pedestrian features, and thus compromis…
Domain shift, which occurs when there is a mismatch between the distributions of training (source) and testing (target) datasets, usually results in poor performance of the trained model on the target domain. Existing algorithms typically solve this issue by reducing the distribution discrepancy in…
Due to the complementary benefits of visible (RGB) and thermal infrared (T) data, RGB-T object tracking attracts more and more attention recently for boosting the performance under adverse illumination conditions. Existing RGB-T tracking methods usually localize a target object with a bounding box,…
Image and sentence matching has made great progress recently, but it remains challenging due to the large visual semantic discrepancy. This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic information as in its matched sentence. In this work, we pr…
Video captioning which automatically translates video clips into natural language sentences is a very important task in computer vision. By virtue of recent deep learning technologies, video captioning has made great progress. However, learning an effective mapping from the visual sequence space to…
Person Re-identification (ReID) is an important yet challenging task in computer vision. Due to the diverse background clutters, variations on viewpoints and body poses, it is far from solved. How to extract discriminative and robust features invariant to background clutters is the core problem. In…
Graph-structured data arise in wide applications, such as computer vision, bioinformatics, and social networks. Quantifying similarities among graphs is a fundamental problem. In this paper, we develop a framework for computing graph kernels, based on return probabilities of random walks. The advant…
In the era of deep learning, although beam-forming multi-channel signal processing is still very helpful, it was reported that single-channel robust front-ends usually cannot benefit deep learning models because the layer-by-layer structure of deep learning models provides a feature extraction strat…
Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we…
Surveillance cameras have been widely used in different scenes. Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification. This topic has gained increasing interests in computer vision recently. However, less attention has been paid to v…
Cats have protractible claws to fold their tips to keep them sharp. They protract claws while hunting and pawing on slippery surfaces. Protracted claws by tendons and muscles of toes can help cats anchoring themselves steady while their locomotion trends to slip and releasing the hold while they ret…
Discriminative sparse coding has emerged as a promising technique in image analysis and recognition, which couples the process of classifier training and the process of dictionary learning for improving the discriminability of sparse codes. Many existing approaches consider only a simple single lin…
Super resolving a low-resolution video is usually handled by either single-image super-resolution (SR) or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video super-res…
Relation learning is a fundamental operation in many computer vision tasks. Recently, high-order Boltzmann machine and its variants have exhibited the great power of modelling various data relation. However, most of them are unsupervised learning models which are not very discriminative and thus can…
Dynamic textures (DTs) are video sequences with stationary properties, which exhibit repetitive patterns over space and time. This paper aims at investigating the sparse coding based approach to characterizing local DT patterns for recognition. Owing to the high dimensionality of DT sequences, exist…