130 accepted papers
Soft robots have gained widespread attention due to their lightweight nature and inherent safety. Among them, soft growing robots (SGRs) are inspired by the growth mechanism of vines, achieving movement through tip eversion. However, their load-bearing capacity remains a significant challenge due to…
Recent advances in text-to-image (T2I) generation can produce highly resembling images of copyrighted characters, often indistinguishable from official depictions, raising serious concerns about intellectual property infringement. Consequently, robust detection of copyright character infringement is
Image-based feature representation plays a critical role in visual localization, enabling robots to estimate their position and orientation in GPS-denied environments. However, this task is often undermined by significant variations in camera viewpoints and scene appearances. Recently, map-free visu
Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive reuse often incurs noticeable quality degradation. In this work…
Degradation-agnostic image restoration aims to handle diverse corruptions with one unified model, but faces fundamental challenges in balancing efficiency and performance across different degradation types. Existing approaches either sacrifice efficiency for versatility or fail to capture the distin…
Motion generation in dynamic environments is crucial for human-machine interaction with redundant manipulators. In this context, we propose the Enhancing Safety and Manipulability (ESM) scheme, which integrates geometry-based dynamic obstacle avoidance, manipulability optimization,trajectory trackin…
Implicit representations for LiDAR-based Simultaneous Localization and Mapping (SLAM) offer significant advantages in storage efficiency and expressive power over traditional explicit maps. However, a critical limitation for implicit SLAM is their deterministic nature, which prevents the quantificat…
Achieving safe manipulation-oriented navigation for humanoid robots is fundamentally challenged by two factors: locomotion-induced perceptual distortion (causing semantic-geometry distortion) and changes within the environment (causing map-reality mismatches). Existing static scene graphs often fail…
Recent Large Audio-Language Models (LALMs) exhibit impressive capabilities in understanding audio content for conversational QA tasks. However, these models struggle to accurately understand timestamps for temporal localization (e.g., Temporal Audio Grounding) and are restricted to short audio perce
Vision transformers (ViTs) have recently been widely applied to 3D point cloud understanding, with masked autoencoding as the predominant pre-training paradigm. However, the challenge of learning dense and informative semantic features from point clouds via standard ViTs remains underexplored. We pr
Multi-annotator learning traditionally aggregates diverse annotations to approximate a single “ground truth”, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground truth, and sparse annotation coverage makes aggregation stat
Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels—a common scenario in real-world crowdsourced datasets where each anno
We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus for joint training. While the standard pretraining teaches LM…
In this letter, a novel hybrid motion optimization framework is proposed for a humanoid upper-body robot with two 7-DOF arms and a 2-DOF waist, to flexibly and safely carry objects in constrained and dynamic environments. The framework consists of <bold xmlns:mml="http://www.w3.org/1998/Math/MathML"
Accurately estimating the 6-DoF pose of objects is a fundamental challenge in computer vision and robotics. While category-level pose estimation based on RGBD data has achieved good performance in recent years, estimating poses solely from RGB images remains a significant challenge. Existing RGB-bas
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational demands. Post-training quantization (PTQ) is considered an effective method to accelerate LLM inference. Despite its growing…
Soft robots have gained widespread attention due to their lightweight nature and inherent safety. Among them, soft growing robots (SGRs) are inspired by the growth mechanism of vines, achieving movement through tip eversion. However, their load-bearing capacity remains a significant challenge due to
A sixteen-joint snake robot with full-body surface pressure sensing capabilities has been developed. A total of 64 thin film pressure sensors are evenly distributed on the surface of the robot. Four intelligent obstacle avoidance movements integrating surface pressure perception were investigated. T
Relevance modeling between queries and items stands as a pivotal component in commercial search engines, directly affecting the user experience. Given the remarkable achievements of large language models (LLMs) in various natural language processing (NLP) tasks, LLM-based relevance modeling is gradu…
Diffusion-based virtual staining methods of histopathology images have demonstrated outstanding potential for stain normalization and cross-dye staining (e.g., hematoxylin-eosin to immunohistochemistry). However, achieving pathology-correct cross-dye virtual staining with versatile tone controls pos…
Dexterous grasping is a crucial technique in humanoid robot manipulation. However, existing methods still fall short in effectively detecting dexterous grasps in cluttered environments. In this work, we propose DexMGNet, a novel multi-mode dexterous grasping framework designed for such challenging s
Motion generation in dynamic environments is crucial for human-machine interaction with redundant manipulators. In this context, we propose the Enhancing Safety and Manipulability (ESM) scheme, which integrates geometry-based dynamic obstacle avoidance, manipulability optimization, trajectory tracki
Lung cancer remains a leading cause of mortality, making accurate subtype identification crucial for effective lung cancer diagnosis and treatment. Recent advancements in medical image classification, particularly through Convolutional Neural Networks (CNNs) and Transformers, have significantly impr…
We introduce *GraphGPT*, a novel self-supervised *generative pre-trained* model for graph learning based on the *Graph Eulerian Transformer* (**GET**). First, we propose **GET**, which combines a standard transformer encoder or decoder architecture with an innovative graph-to-sequence transformation…
Piano-playing tasks, which effectively demonstrate bimanual coordination capabilities in humanoid robots, are increasingly becoming a research focus. However, prior research has predominantly focused on Cartesian space trajectory planning without adequately addressing real-world obstacle avoidance c
Humanoid robots are engineered to navigate terrains akin to those encountered by humans, which necessitates human-like locomotion and perceptual abilities. Currently, the most reliable controllers for humanoid motion rely exclusively on proprioception, a reliance that becomes both dangerous and unre
Cognitive impairment detection through spontaneous speech is a promising avenue for early diagnosis of Alzheimer’s disease (AD) and mild cognitive impairment (MCI), where timely intervention can significantly improve patient outcomes. The PROCESS Grand Challenge at ICASSP 2025 addresses these tasks…
Federated learning is often used in environments with many unverified participants. Therefore, federated learning under adversarial attacks receives significant attention. This paper proposes an algorithmic framework for list-decodable federated learning, where a central server maintains a list of m…
This paper presents a universal LiDAR point cloud global localization framework based on multi-sector overlapping loss to address the localization challenges caused by heterogeneous LiDAR point clouds with varying resolutions, scanning formats, and field of view differences. The proposed method firs
One-shot global localization is crucial in many robotic applications, providing significant advantages during initialization and relocalization processes. However, LiDAR-based one-shot global localization methods encounter challenges, including local feature matching errors, sensitivity to dynamic o
The integration of RGB and depth modalities significantly enhances the accuracy of segmenting complex indoor scenes, with depth data from RGB-D cameras playing a crucial role in this improvement. However, collecting an RGB-D dataset is more expensive than an RGB dataset due to the need for specializ…
Monocular video depth estimation is a key challenge in computer vision, highlighting its importance in visual understanding. Monocular depth estimation models trained on single images achieve impressive results on individual frames but often lack temporal consistency when applied to videos, leading
Natural Human-Robot Interaction (N-HRI) requires robots to recognize human actions at varying distances and states, regardless of whether the robot itself is in motion or stationary. This setup is more flexible and practical than conventional human action recognition tasks. However, existing benchma…
This paper presents a novel one-shot global localization algorithm based on semantic-guided triangle descriptors to address initialization and global localization challenges in GNSSdenied environments. By encoding semantic geometric information into triangle descriptors, the proposed approach achiev
Recently, transformer-based methods have been introduced to estimate 3D human pose from multiple views by aggregating the spatial-temporal information of human joints to achieve the lifting of 2D to 3D. However, previous approaches cannot model the inter-frame correspondence of each view's joint ind…
Despite significant advances in self-supervised monocular depth estimation methods, achieving temporally consistent and accurate depth maps from frame sequences remains a formidable challenge. Existing approaches often estimate depth maps for individual frames in isolation, neglecting the rich geome
Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we propose TCPFormer, which leverages an implicit pose proxy as a…
Unsupervised fault detection in multivariate time series is critical for maintaining the integrity and efficiency of complex systems, with current methodologies largely focusing on statistical and machine learning techniques. However, these approaches often rest on the assumption that data distribut…
In video-based emotion recognition, effective multi-modal fusion techniques are essential to leverage the complementary relationship between audio and visual modalities. Recent attention-based fusion methods are widely leveraged for capturing modal-shared properties. However, they often ignore the m…
Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models…
Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories. To adapt CLAP to downstream tasks, prior works inevitably require labeled domain audios, which limits their sca…
Generating a sequence of intermediate steps, \emph{a.k.a.}, a chain of thought (CoT), is a highly effective method to improve the accuracy of large language models (LLMs) on arithmetics and symbolic reasoning tasks. However, the mechanism behind CoT remains unclear. This work provides a theoretical…
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse nature of facial manipulations. In this paper, we revisit the g…
Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either…
Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posi…
Transformers have been successfully applied in the field of video-based 3D human pose estimation. However the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper we present a plug-and-play pruning-and-recovering framew…
Homography estimation is a fundamental problem in computer vision. Previous works mainly focus on estimating either a single homography, or multiple homographies based on mesh grid division of the image. In practical scenarios, single homography is inadequate and often leads to a compromised result…
Overfitting in adversarial training has attracted the interest of researchers in the community of artificial intelligence and machine learning in recent years. To address this issue, in this paper we begin by evaluating the defense performances of several calibration methods on various robust models…
The construction of large-scale space facilities requires the use of on-orbit construction technology. However, several of its key components, such as standard interface design, compliant control methods, and path planning for multi-branch robots, still need improvement before practical application.…
We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www
Byzantine machine learning has garnered considerable attention in light of the unpredictable faults that can occur in large-scale distributed learning systems. The key to secure resilience against Byzantine machines in distributed learning is resilient aggregation mechanisms. Although abundant resil…
Recent text-to-image (T2I) models have had great success, and many benchmarks have been proposed to evaluate their performance and safety. However, they only consider explicit prompts while neglecting implicit prompts (hint at a target without explicitly mentioning it). These prompts may get rid of…
Learning meaningful frame-wise features on a partially labeled dataset is crucial to semi-supervised sound event detection. Prior works either maintain consistency on frame-level predictions or seek feature-level similarity among neighboring frames, which cannot exploit the potential of unlabeled da…
Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training. Adam and its variants have been state-of-the-art for years, and more sophisticated second-order (Hessian-based) optimize…
Sampling-based motion planning (SBMP) algorithms are renowned for their robust global search capabilities. However, the inherent randomness in their sampling mechanisms often results in inconsistent path quality and limited search efficiency. In response to these challenges, this work proposes a nov
Various applications (e.g., disaster response) put forward higher requirements for the capabilities of robots. However, to date, few platforms can be compatible with the required mobility, stability and dexterity. A major challenge is mobile stability may severely limit the variety of manipulation s
Autonomous navigation of ground robots on uneven terrain is being considered in more and more tasks. However, uneven terrain will bring two problems to motion planning: how to assess the traversability of the terrain and how to cope with the dynamics model of the robot associated with the terrain. T…
Graph Convolutional Network (GCN) has achieved high success in the skeleton-based human action recognition task by modeling the human skeleton as a graph. However, it remains a problem for GCN-based methods to learn distinctive action features from a limited number of training samples. Via taking fu…
Person re-identification (ReID) aims at retrieving a person of interest across multiple cameras. Despite significant progress in person ReID, viewpoint variation remains an obstacle to extracting discriminative features for retrieval. To address this problem, we propose a Viewpoint-Robust Network (V…
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the complex pose and shape parameters from coupled image features, w…
Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos. Federated Learning (FL) has attracted much attention due to its outstanding advantages in privacy-preserving. However, directly app…
3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often le…
3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological…
Previous studies have shown that optimizing the information bottleneck can significantly improve the robustness of deep neural networks. Our study closely examines the information bottleneck principle and proposes an Information Bottleneck Distillation approach. This specially designed, robust disti…
Recently, video question answering has attracted growing attention. It involves answering a question based on a fine-grained understanding of video multi-modal information. Most existing methods have successfully explored the deep understanding of visual modality. We argue that a deep understanding…
Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we propose a novel Interweaved Graph and Attention Network (IGANet)…
Owing to the large distribution gap between the heterogeneous data in Visible-Infrared Person Re-identification (VI Re-ID), we point out that existing paradigms often suffer from the inter-modal semantic misalignment issue and thus fail to align and compare local details properly. In this paper, we…
Multimodal magnetic resonance imaging (MRI) provides complementary information for sub-region analysis of brain tumors. Plenty of methods have been proposed for automatic brain tumor segmentation using four common MRI modalities and achieved remarkable performance. In practice, however, it is common…
Recently, deep learning-based facial landmark detection has achieved significant improvement. However, the semantic ambiguity problem degrades detection performance. Specifically, the semantic ambiguity causes inconsistent annotation and negatively affects the model's convergence, leading to worse a…
Language modeling on large-scale datasets improves performance of various downstream tasks. The validation pre-training loss is often used as the evaluation metric for language models since the pre-training loss tends to be well-correlated with downstream performance (which is itself hard to evaluat…
Sequential recommendation is an important task to predict the next-item to access based on a sequence of interacted items. Most existing works learn user preference as the transition pattern from the previous item to the next one, ignoring the time interval between these two items. However, we obser…
Monocular self-supervised depth estimation can be easily applied in many areas since only a single camera is required. However, current methods do not predict well in depth borders. Besides, factors such as occlusion and texture sparsity can lead to the failure of the photometric consistency, affect…
"Recently, Deepfakes arises as a powerful tool to fool the existing real-world face detection systems, which has received wide attention in both academia and society. Most existing forgery face detection methods use heuristic clues to build a binary forgery detector, which mainly takes advantage of…
"Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic performance degradation. We argue this is due to the lack of rich in…
In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to construct similar positive samples, which limits the ability to ex…
Existing video question answering (video QA) models lack the capacity for deep video understanding and flexible multistep reasoning. We propose for video QA a novel model which performs dynamic multistep reasoning between questions and videos. It creates video semantic representation based on the vi…
Multi-hop Question Answering is an agent task for testing the reasoning ability. With the development of pre-trained models, the implicit reasoning ability has been surprisingly improved and can even surpass human performance. However, the nature of the black box hinders the construction of explaina…
Recently, Biomedical Question Answering (BQA) has attracted growing attention due to its application value and technical challenges. Most existing works treat it as a semantic matching task that predicts answers by computing confidence among questions, options and evidence sentences, which is insuff…
Accurate and robust initialization is crucial in visual-inertial system, which significantly affects the localization accuracy. Most of the existing feature-based initialization methods rely on point features to estimate initial parameters. However, the performance of these methods often decreases i…
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasib…
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of multi-modal signals remains a challenging issue. In this paper,…
Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based method…
Multiple moving sound source localization in real-world scenarios remains a challenging issue due to interaction between sources, time-varying trajectories, distorted spatial cues, etc. In this work, we propose to use deep learning techniques to learn competing and time-varying direct-path phase dif…
Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little about the behavior of SSL. In this work, we systematically inv…
Collision-free motion planning allows robots to perform tasks in complex environments, but the conservative bounding curves during collision detection will reduce the robot's dexterity. This paper presents a novel algorithm for real-time motion planning of non-holonomic robots in dynamic scenes. To
Most existing person re-identification methods are effective in short-term scenarios because of their appearance dependencies. However, these methods may fail in long-term scenarios where people might change their clothes. To this end, we propose an adversarial feature disentanglement network (AFD-N…
Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to narrow the domain shift, which are empirically effective but theoretically challenged by the hardness or impossibility theorems. Recently, self-training has been gaining momentum in UDA, which ex…
In this paper, we propose a domain-general model, termed learning-to-weight (LTW), that guarantees face detection performance across multiple domains, particularly the target domains that are never seen before. However, various face forgery methods cause complex and biased data distributions, making…
Recent advances in person re-identification (re-ID) have led to impressive retrieval accuracy. However, existing re-ID models are challenged by the adversarial examples crafted by adding quasi-imperceptible perturbations. Moreover, re-ID systems face the domain shift issue that training and testing…
RGB-infrared (IR) person re-identification is a challenging task due to the large modality gap between RGB and IR images. Many existing methods bridge the modality gap by style conversion, requiring high-similarity images exchanged by complex CNN structures, like GAN. In this paper, we propose a hig…
Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directl…
Direct-path relative transfer function (DP-RTF) refers to the ratio between the direct-path acoustic transfer functions of two channels. Though DP-RTF fully encodes the sound directional cues and serves as a reliable localization feature, it is often erroneously estimated in the presence of noise an…
Robustness against word substitutions has a well-defined and widely acceptable form, i.e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robustness in natural language processing. Previous defense methods capture word sub…
Single-image super-resolution (SISR) task has witnessed great strides in the past few years with the development of deep learning. However, most existing studies concentrate on exploiting much deeper super-resolution networks, which are not friendly to the constrained computation resources. In this…
Robustness of deep neural network classifiers has been attracting increased attention. As for the robust classification problem, a generative classifier typically models the distribution of inputs and labels, and thus can better handle off-manifold examples at the cost of a concise structure. On the…
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks. In this paper, we defend against adversarial attacks using neural architecture search (NAS) which is based on a comprehensive search of denoising blocks…
Human action recognition aims at assigning an action label to a well-segmented video. Recent work using two-stream or 3D convolutional neural networks achieves high recognition rates at the cost of huge computation complexity, memory footprint, and parameters. In this paper, we propose a lightweight…
We propose a simple but efficient method termed Guided Learning for weakly-labeled semi-supervised sound event detection (SED). There are two sub-targets implied in weakly-labeled SED: audio tagging and boundary detection. Instead of designing a single model by considering a trade-off between the tw…
Domain adaptation aims at knowledge transfer from a labeled source domain to an unlabeled target domain. Current domain adaptation methods have made substantial advances in adapting discrete domains. However, this can be unrealistic in real-world applications, where target data usually comes in an o…
There are two sub-tasks implied in the weakly-supervised SED: audio tagging and event boundary detection. Current methods which combine multi-task learning with SED requires annotations both for these two sub-tasks. Since there are only annotations for audio tagging available in weakly-supervised SE…
Fashion landmark estimation aims at locating functional key points of clothes, which has wide potential applications in electronic commerce. However, due to the occlusion and weak outline information, landmark estimation occurs outliers and duplicate detection problems. To alleviate these issues, we…
Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer from the need for excessive queries, as it is non-trivial to find an appropriate direction to optimize in the high-dimens…
The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is dir…
Visual odometry (VO) is an essence of vision-based localization and mapping system where existing learning-based approaches utilize CNN and RNN to model camera motion and gain promising results. However, these methods lack full use of the relationship between spatial characteristics and temporal clu…
Recently, unsupervised methods for monocular visual odometry (VO), with no need for quantities of expensive labeled ground truth, have attracted much attention. However, these methods are inadequate for long-term odometry task, due to the inherent limitation of only using monocular visual data and t…
Convolutional Neural Network (CNN) can be used to indiscriminately predict dense depth and camera motion from images, however, ignoring the relationship between depth map and camera motion increases the computational burden to label the datasets and limits the accuracy of the results. In this paper,…
Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision tasks. However, it is computationally consuming. Since the…
Domain adaptation has become a resounding success in leveraging labeled data from a source domain to learn an accurate classifier for an unlabeled target domain. When deployed in the wild, the target domain usually contains unknown classes that are not observed in the source domain. Such setting is…
Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems with a new type of feature. Such a setting is obviously inflexible and time/memory consuming, which is indeed mendable if…
Domain adaptation enables knowledge transfer from a labeled source domain to an unlabeled target domain. A mainstream approach is adversarial feature adaptation, which learns domain-invariant representations through aligning the feature distributions of both domains. However, a theoretical prerequis…
Deep learning models have shown their vulnerabilities to universal adversarial perturbations (UAP), which are quasi-imperceptible. Compared to the conventional supervised UAPs that suffer from the knowledge of training data, the data-independent unsupervised UAPs are more applicable. Existing unsupe…
Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has…
Person search is a challenging task that requires to address pedestrian detection and person re- identification simultaneously. Though significant progress has been made in detection and re-identification respectively, the similar appearances of persons, pedestrian misdetections and false alarms sti…
Loop closure detection is essential and important in visual simultaneous localization and mapping (SLAM) systems. Most existing methods typically utilize a separate feature extraction part and a similarity metric part. Compared to these methods, an end-to-end network is proposed in this paper to joi…
Human action recognition based on skeleton sequences has wide applications in human-computer interaction and intelligent surveillance. Although previous methods have successfully applied Long Short-Term Memory(LSTM) networks to model shape evolution of human actions, it still remains a problem to ef…
Most of the existing monocular visual-inertial SLAM techniques assume that the camera-IMU extrinsic parameters are known, therefore these methods merely estimate the initial values of velocity, visual scale, gravity, biases of gyroscope and accelerometer in the initialization stage. However, it's us…
Rain streaks can severely degrade the visibility, which causes many current computer vision algorithms fail to work. So it is necessary to remove the rain from images. We propose a novel deep network architecture based on deep convolutional and recurrent neural networks for single image deraining. A…
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks. Following this line of research, in this paper we introduce a novel approach for monocular depth estimation. Similarly to previous works, our…
How to design a robotic hand for reproducing the move characteristics of human hand joints is a big challenge in robotics. In this paper, we present an approach to determine the actuation configuration based on the statistical results of hand joint angle in different grasps. A relationship between t…
Tracking failure is an inevitable event in real-time monocular simultaneous localization and mapping (SLAM) system. Relocalization procedure that focuses on exploring a visited place to relocalize a camera is usually used to handle this problem. However, this strategy abandons the poses of the frame…
Person re-identification remains a challenging problem due to large variations of poses, occlusions, illumination and camera views. To learn both feature representation and similarity metric simultaneously, deep metric learning methods using triplet convolutional neural network have been applied in…
Binary code learning has been emerging topic in large-scale cross-modality retrieval recently. It aims to map features from multiple modalities into a common Hamming space, where the cross-modality similarity can be approximated efficiently via Hamming distance. To this end, most existing works lear…
Depth motion maps (DMMs) have shown effectiveness in human action recognition, however, they lose the temporal information and suffer from intra-class variations caused by action speed variations. To address these challenges, we propose a novel method for human action recognition. Firstly, Adaptive…
Person re-identification is an important topic in visual surveillance, which aims at recognizing an individual over disjoint camera views. As a major aspect of person re-identification, distance metric learning has been widely studied to seek a discriminative matching metric. However, most existing…
Multiple sound source localization in wireless acoustic sensor networks (WASNs) is a challenging problem. Although compressive sensing based methods have shown effectiveness in uncorrelated sources localization, their performance degrades significantly when they are used to locate multiple speech so…
Facial age estimation is challenging due to complex dynamics in aging process, which render metric regression methods unfavorable. Rankers show better performance by exploiting the ordinal nature of ages. The difficulty of designing a ranker is that each binary classifier of a ranker has to be train…
Sound source localization (SSL) is an essential technique in many applications, such as robot audition, human-robot interaction and speech capturing. However, SSL from a binaural input is still a challenging problem, particularly when multiple sources are active simultaneously. In this work, we prop…
Narrow passages in changing environments create huge difficulties, since locations and shapes of narrow passages in Configuration Space(C-space) change frequently. It is very important for a planner to identify narrow passages in real time and boost valid points within them effectively. A novel narr…
Binaural sound source localization is an important technique involving Human-Robot Interaction (HRI), video conference, speech enhancement, etc. In many real application scenarios, especially for closed environments, the affect of reverberation and noise would degrade the precision of position estim…
Person re-identification is valuable for intelligent video surveillance and has drawn wide attention. Although person re-identification research is making progress, it still faces some challenges such as varying poses, illumination and viewpoints. As a major aspect of person re-identification, featu…