149 accepted papers
REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuri…
Audio deep reasoning is a challenging task that requires expert-level perception, multi-step logical inference, and the integration of contextual knowledge. However, existing models suffer from a gap between audio perception and reasoning abilities due to the lack of training data with explicit reas…
The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to…
Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue, test-time adaptati
Tracking moving anatomical targets with robotic ultrasound is particularly challenging when the target motion is both fast and large in scale, as the end-to-end latency of existing systems prevents the perception–control loop from closing fast enough. In this paper, we argue that overcoming this lim…
Automatic Cued Speech Recognition (ACSR) is a vital communication system designed to enhance spoken language accessibility for the hearing-impaired by combining lip movements and hand gestures to encode phonemes. Despite its effectiveness, current ACSR methods face significant challenges, including
Disrupted hand motor functions may be restored through exoskeleton-assisted rehabilitation training. However, the variability of soft tissue in human joints or across individuals and development of an exoskeleton that combines human machine motion compatibility and dynamic compliance pose persistent
Accurate and efficient hand-eye calibration (HEC) is crucial for vision-guided robotic machining system, particularly in precision grinding blades. However, existing closed-form solutions are highly susceptible to noise and outliers, while iterative solutions depend on good initial estimates. To ove
Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where node-level features collapse in deep GNN layers. While existin
Cued Speech (CS) is an innovative visual communication system that integrates lip-reading with hand coding, designed to enhance effective communication for individuals with hearing impairments. Automatic CS Recognition (ACSR) refers to the AI-driven process of automatically recognizing hand gestures…
Cross-modal alignment is a promising yet challenging task in multimodal learning. Existing methods typically assess it by measuring the cross-modal semantic similarity from both global and local perspectives. However, these methods often neglect their potential interdependence. Specifically, global
Recent advances in Remote Sensing Foundation Models (RSFMs) have demonstrated considerable potential for Earth Observation (EO) tasks. While adopting natural image foundation models (e.g., DINO) provides a data-efficient strategy for building RSFMs, their strong generalization capability does not fu
Deep learning-based respiratory auscultation is currently hindered by two fundamental challenges: (i) inherent information loss, as converting signals into spectrograms discards transient acoustic events and clinical context; (ii) limited data availability, exacerbated by severe class imbalance. To…
Recent advancements in remote sensing object detection have predominantly focused on oriented bounding box design and small object feature enhancement, while often overlooking the intrinsic geometric properties of remote sensing images, such as rotation invariance and structural symmetry. Many aeria
Large Audio–Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks toward deployment. While safety alignment has made initial a…
In this paper, we show that current approaches using large square kernels or transformer-based global modeling aggregate contextual information uniformly across spatial dimensions, leading to feature dilution and localization errors for elongated targets. To mitigate this issue, we propose Strip R-C
Achieving zero-shot adversarial robustness without sacrificing generalization remains challenging for foundation models such as CLIP, especially under large adversarial perturbations. Through empirical analyses, we identify three critical yet overlooked issues: (1) Logit margins exhibit a stable off
Cued Speech (CS) enhances lipreading via hand coding, offering visual phonemic cues that support precise speech perception for the hearing-impaired. The task of CS Video-to-Speech generation (CSV2S) aims to convert CS videos into intelligible speech signals. Most existing research focuses on CS Reco
This work studies the task of poisoned sample detection for defending against data poisoning based backdoor attacks. Its core challenge is finding a generalizable and discriminative metric to distinguish between clean and various types of poisoned samples (e.g., various triggers, various poisoning r…
Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome this, we introduce AgentThink , a pioneering unified framewor
Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor vulnerability is still in its infancy compared to the extensive…
Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training and inference. Recent methods have tried to solve this issue b…
Wearable Human Activity Recognition (WHAR) is a prominent research area within ubiquitous computing. Multi-sensor synchronous measurement has proven to be more effective for WHAR than using a single sensor. However, existing WHAR methods use shared convolutional kernels for indiscriminate temporal f…
The integration of depth sensing and laser scanning technologies has propelled point cloud data to the forefront of 3D graphical modeling. This paper addresses a critical gap in the literature: the protection of intellectual property in generating point clouds using Diffusion Models (DMs). We introd…
Considering the potential of using multi-frame information to solve the occlusion problem, we introduce a novel idea of multi-frame information integration, which uses the attention mechanism to fuse the temporal information from the previous frame. The idea can effectively improve the estimation ac
Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the more complicated decision boundary caused by the insufficient l…
Audio-Visual Learning (AVL) aims at the audio-visual perception with both audio and vision modalities. AVL also suffers from data insufficiency in many applications as with other unimodal tasks. Concurrently, AVL often needs to continuously learn over time rather than all knowledge simultaneously. C…
Speech-to-portrait generation (S2P) plays a crucial role in speech-driven, human-centered creative content generation, aiming to synthesize a speaker’s face portrait with identity consistency from a given speech clip. However, existing S2P methods can typically only preserve attribute consistency, e…
Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitably rely on the availability of either clean or poisoned data. In contrast, data-free defense techniques have evolved slow…
Backdoor attacks have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the visual domain, the specialized defenses for the audio domain remain empty. Furthermore, the defenses adapted from the v…
This paper considers the challenging problem of 3D Human Pose Estimation (HPE) from a sparse set of Inertial Measurement Units (IMUs). Existing efforts typically reconstruct a pose sequence by either directly tackling whole-body motions or focusing on distinctive spatio-temporal features of local bo…
In the dynamic realm of digital media, latent diffusion models (LDM) have revolutionized the generation of videos, surpassing the capabilities of traditional generative models. This paper presents Stable Video Signature, a pioneering watermarking framework for LDM in video generation. Addressing the…
Cued Speech (CS) is a visual coding system that combines lip movements and hand gestures to represent spoken languages for hearing-impaired people. Automatic Cued Speech Recognition (ACSR) is an emerging research topic, but the cuer (i.e., people who perform CS) generalization problem of ACSR remain…
A major challenge in Fine-Grained Visual Classification (FGVC) is distinguishing various categories with high inter-class similarity by learning the feature that differentiates the details. Conventional cross-entropy trained Convolutional Neural Network (CNN) fails this challenge as they may suffer…
Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus on deterministic pixel-level mappings between paired low/normal-light images, they often neglect the continuous physical…
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this end, we propose an efficient mamba-based tracker, l…
With the rise of the AIGC era, rhythmic music generation has extensive applications, particularly with the surge in motion video creation. However, generating music that is rhythmically synchronized and stylistically aligned with motion video presents significant challenges. Although existing method…
Cued speech (CS) is a novel visual coding system, which combines lip reading with several specific hand codings to help hearing-impaired people to communicate effectively. This work focuses on the audio/text-driven CS gestures (i.e., continuous lip and hand gestures movements) generation. Previous w…
Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, audio diver
Vertical Federated Learning (VFL) is a well-known FL variant that enables multiple parties to collaboratively train a model without sharing their raw data. Existing VFL approaches focus on overlapping samples among different parties, while their performance is constrained by the limited number of th…
Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the speaker's voice identity information, and (2) inadequacy in d…
Scene text image super-resolution (STISR) focuses on enhancing the clarity and readability of low-resolution text images. Existing methods often rely on text probability distribution priors derived from text recognizers to guide the super-resolution process. While effective in capturing general stru…
Multimodal 3D segmentation involves a significant number of 3D convolution operations, which requires substantial computational resources and high-performance computing devices in MRI multimodal brain tumor segmentation. The key challenge in multimodal 3D segmentation is how to minimize network comp…
Semi-supervised methods have recently received significant attention in deep learning because they are able to reduce the dependence on labeled data while ensuring good performance. The pseudo-label based method has been widely used as a classic semi-supervised method but still suffers from the conf…
Fashion image editing is a valuable tool for designers to convey their creative ideas by visualizing design concepts. With the recent advances in text editing methods, significant progress has been made in fashion image editing. However, they face two key challenges: spurious correlations in trainin…
Text-to-speech (TTS) has advanced from generating natural-sounding speech to enabling fine-grained control over attributes like emotion, timbre, and style. Driven by rising industrial demand and breakthroughs in deep learning, e.g., diffusion and large language models (LLMs), controllable TTS has be
Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in parallel to determine whether the drafted tokens should be…
Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection performance by changing its viewpoint. Active Object Detection (AOD)
A key challenge for controllable image editing is that visual attributes with semantic meanings are not always independent, resulting in spurious correlations in model training. However, most existing methods ignore such issues, leading to biased causal visual representation learning and unintended…
Few-shot object detection aims to detect novel classes with limited samples. Recent methods have leveraged the rich semantic representations of pretrained vision transformer (ViT) to overcome the limitations of model fine-tuning, thereby improving the performance on novel classes. However, existing…
The Thinprep Cytologic Test (TCT) is a vital component in the early detection of cervical cancer. However, conventional manual screening methods are hindered by inefficiencies and high levels of subjectivity. This study presents YOLO-TCT, an enhanced YOLOv9 network designed for the automated detecti…
Cued Speech (CS) is an advanced visual phonetic encoding system that integrates lip reading with hand codings, enabling people with hearing impairments to communicate efficiently. CS video generation aims to produce specific lip and gesture movements of CS from audio or text inputs. The main challen…
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained backbone, we pretrain the backbone using image-depth pairs from…
Predicting human falls from wearable devices is a complex task due to the inherent diversity and causality of multivariate physical changes, where each instance exhibits a unique style of motion events and their spatio-temporal causal dependencies. Consequently, we propose a multichannel causal mode…
Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models yet the adversarial examples they produce are easily perceived or defended against. The trade-off between the imperceptibility and adversarial strength leads most point a…
Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usa…
Dealing with noisy labels (LNL) emerges as a critical challenge when applying deep learning (DL) in practical settings. Previous methodologies primarily concentrated on harnessing model predictions to mitigate the impact of noisy labels. Nevertheless, their efficacy is strongly contingent on the acc…
A key challenge in sensor-based fall prediction is the fact that a fall event can often occur in various configurations of fall poses together with their own spatio-temporal dependencies. This leads us to define a spatio-temporal model to explicitly characterize these internal configurations of pose…
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel space for supervision. However, the expensive annotation proc…
In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the suff…
Synthetic Aperture Radar (SAR) object detection has gained significant attention recently due to its irreplaceable all-weather imaging capabilities. However, this research field suffers from both limited public datasets (mostly comprising <2K images with only mono-category objects) and inaccessible…
Recently, lots of works that incorporate external lexicon information into character-level Chinese named entity recognition(NER) to overcome the lackness of natural delimiters of words, have achieved many advanced performance. However, obtaining and maintaining high-quality lexicons is costly, espec…
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently object-free methods have attracted considerable attention. Such methods perceive the world by predicting the semantics of discrete voxel grids but fail to construct continuous and accur…
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense. Additionally, vanilla fine-tuning with those clean data can help rec…
Underwater Object Tracking (UOT) is essential for identifying and tracking submerged objects in underwater videos, but existing datasets are limited in scale, diversity of target categories and scenarios covered, impeding the development of advanced tracking algorithms. To bridge this gap, we take t…
In medical robotics and image-guided surgery (IGS), registration is needed in order to align together the coordinate frames of robots, medical imaging modalities, surgical tools, and patients. Existing registration algorithms often assume one point set to be a noise-free model while the other to con…
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals in taste sensation recognition. This paper proposes a bimodal fusion network (Bi-F…
Automatic Cued Speech Recognition (ACSR) provides an intelligent human-machine interface for visual communications, where the Cued Speech (CS) system utilizes lip movements and hand gestures to code spoken language for hearing-impaired people. Previous ACSR approaches often utilize direct feature co…
Scene Graph Generation (SGG) has already shown its great potential in various downstream tasks, but it comes at the price of a prohibitively expensive annotation process. To reduce the annotation cost, we propose using Active Learning (AL) for sampling the most informative data. However, directly po…
Federated learning (FL) is a prevalent distributed machine learning approach that enables collaborative training of a global model across multiple devices without sharing local data. However, the presence of long-tailed data can negatively deteriorate the model's performance in real-world FL applica…
Graph-structured physical mechanisms are ubiquitous in real-world scenarios, thus revealing underneath formulas is of great importance for scientific discovery. However, classical symbolic regression methods fail on this task since they can only handle input-output pairs that are not graph-structure…
Training a convolutional neural network (CNN) to detect infrared small targets in a fully supervised manner has gained remarkable research interests in recent years, but is highly labor expensive since a large number of per-pixel annotations are required. To handle this problem, in this paper, we ma…
Given one reference facial image and a piece of speech as input, talking head generation aims to synthesize a realistic-looking talking head video. However, generating a lip-synchronized video with natural head movements is challenging. The same speech clip can generate multiple possible lip and hea…
This letter introduces an innovative multi-scale visual servoing framework for optical microscopy, engineered to automatically reposition the microscope for high-magnification target view across multiple magnifications, thereby facilitating repetitive and accurate histologic biopsies. The framework
Deep generative models are effective in style transfer. Previous methods learn one or several specific artist-style from a collection of artworks. These methods not only homogenize the artist-style of different artworks of the same artist but also lack generalization for the unseen artists. To solv…
Intelligent medical diagnosis has shown remarkable progress on the large-scale datasets with full annotations. However, very few labeled images are available due to significantly expensive annotations by experts. To efficiently leverage abundant unlabeled data, we propose a novel Spatio-Temporal Str…
Acoustic-to-articulatory inversion (AAI) aims to estimate the parameters of articulators from speech audio. There are two common challenges in AAI, which are the limited data and the unsatisfactory performance in speaker independent scenario. Most current works focus on extracting features directly…
"Single image super-resolution (SR) has been boosted by deep convolutional neural networks with growing model complexity and computational costs. To deploy existing SR networks onto edge devices, it is necessary to accelerate them for large image (4K) processing. The different areas in an image ofte…
Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals. Until now, achieving a speaker-independent AAI remains a challenge given the limited data. Besides, most current works only use audio speech as input, causing an inevitable performance bottleneck.…
DeepFake is becoming a real risk to society and brings potential threats to both individual privacy and political security due to the DeepFaked multimedia are realistic and convincing. However, the popular DeepFake passive detection is an ex-post forensics countermeasure and failed in blocking the d…
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown. One promising approach to improve atta…
Keypoint extraction including both keypoint detection and description is a fundamental step in a wide range of geometric multimedia applications. In recent years, many learning-based approaches for keypoint extraction emerge and achieve promising results. However, they usually design network archite…
"Recent studies have shown that Deep Neural Networks (DNNs) are vulnerable to the backdoor attacks, which leads to malicious behaviors of DNNs when specific triggers are attached to the input images. It was further demonstrated that the infected DNNs possess a collection of channels, which are more…
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the detection and description steps, directly conducting weakly supervis…
Binary neural networks (BNNs) constrain weights and activations to +1 or -1 with limited storage and computational cost, which is hardware-friendly for portable devices. Recently, BNNs have achieved remarkable progress and been adopted into various fields. However, the performance of BNNs is sensiti…
"Video transformers have achieved impressive results on major video recognition benchmarks, however they suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few informative tokens in both temporal and spatial dimensions conditio…
Image-based survival prediction models can facilitate doctors in diagnosing and treating cancer patients. With the advance of digital pathology technologies, the big whole slide images (WSIs) provide increasing resolution and more details for diagnosis. However, the gigabyte-size WSIs would make mos…
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations. Most previous methods hold the assumption that each instance appears in all views. However, it is not uncommon to see that some views may contain some miss…
Neural network quantization aims at reducing bit-widths of weights and activations for memory and computational efficiency. Since a linear quantizer (i.e., round(*) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use pre-defined functions (e.…
Convolutional neural networks (CNN) can be manipulated to perform specific behaviors when encountering a particular trigger pattern without affecting the performance on normal samples, which is referred to as backdoor attack. The backdoor attack is usually achieved by injecting a small proportion of…
Previous works derive personalized speech features by training the model on a large dataset composed of his/her audio sounds. It was reported that face information has a strong link with the speech sound. Thus in this work, we innovatively extract personalized speech features from human faces to syn…
In this paper, we propose a new minimal path-based framework for minimally interactive tubular structure tracking in conjunction with a perceptual grouping scheme. The minimal path models have shown great advantages in tubular structures tracing. However, they suffer from shortcuts or short branches…
Visual-inertial odometry (VIO) aims to predict trajectory by ego- motion estimation. In recent years, end-to-end VIO has made great progress. However, how to handle visual and inertial measurements and make full use of the complementarity of cameras and inertial sensors remains a challenge. In the p…
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id). Most existing works employ two-stage detectors like Faster-RCNN, yielding encouraging ac…
Autonomous ultrasound (US) acquisition is an important yet challenging task, as it involves interpretation of the highly complex and variable images and their spatial relationships. In this work, we propose a deep reinforcement learning framework to autonomously control the 6-D pose of a virtual US…
Knowledge Distillation has shown very promising ability in transferring learned representation from the larger model (teacher) to the smaller one (student). Despite many efforts, prior methods ignore the important role of retaining inter-channel correlation of features, leading to the lack of captur…
Manufacturing systems involve machines and people. Both productivity and ergonomic performance are of significant importance in manufacturing. However, there is no integrated model to analyze them simultaneously. To bridge this gap, a unified model is introduced to evaluate the productivity and ergo
This letter introduces a novel rigid point set registration (PSR) approach that accurately aligns the pre-operative space and the intra-operative space together in the scenario of computer-assisted orthopedic surgery (CAOS). Motivated by considering anisotropic positional localization noise and util
Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population…
Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (e.g., students) to fully grasp this ability. It would be fascinating if we could train an intelligent agent to help people read and sum…
As a representative of multiple kernel clustering (MKC), simple multiple kernel k-means (SimpleMKKM) is recently put forward to boosting the clustering performance by optimally fusing a group of pre-specified kernel matrices. Despite achieving significant improvement in a variety of applications, we…
The rapid development of machine learning (ML) technology has introduced substantial impact on ergonomics research in manufacturing. Numerous studies and practices have been carried out to apply ML techniques to address manufacturing ergonomics issues, which has brought extensive opportunities as we
Existing late fusion multi-view clustering (LFMVC) optimally integrates a group of pre-specified base partition matrices to learn a consensus one. It is then taken as the input of the widely used k-means to generate the cluster labels. As observed, the learning of the consensus partition matrix and…
Existing non-negative matrix factorization based multi-view clustering algorithms compute multiple coefficient matrices respect to different data views, and learn a common consensus concurrently. The final partition is always obtained from the consensus with classical clustering techniques, such as…
Metastatic involvement of lymph nodes is one of the most important prognostic variables for many cancers. Several deep learning based algorithms have been developed to segment metastatic regions in pathological images to help predict prognosis. However, the training of these methods requires a large…
Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy…
Active wireless capsule endoscopy (WCE) under magnetic actuation is a promising technology to reduce the inspection time and relieve the burden of physicians. In this paper, we propose a reciprocally rotating magnetic actuation method for trajectory following of a capsule and develop its dynamic mod…
In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize two views to train the depth estimation network and use one single view to make predictions. Compared with static view…
Batch Normalization (BN) is extensively employed in various network architectures by performing standardization within mini-batches. A full understanding of the process has been a central target in the deep learning communities. Unlike existing works, which usually only analyze the standardization o…
Conventional unsupervised hashing methods usually take advantage of similarity graphs, which are either pre-computed in the high-dimensional space or obtained from random anchor points. On the one hand, existing methods uncouple the procedures of hash function learning and graph construction. On the…
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's…
Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolutional networks, which has been widely adopted in compact network architecture designs. However, existing group convolutions undermine the original network structures b…
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently. However, the underlying drawbacks of GANs and VAEs (e.g., the hardness of training with ZSL-oriented regularizers and the limited generation quality) hinder the existing generative ZSL models from fully bypas…
State-of-the-art single depth image-based 3D hand pose estimation methods are based on dense predictions, including voxel-to-voxel predictions, point-to-point regression, and pixel-wise estimations. Despite the good performance, those methods have a few issues in nature, such as the poor trade-off b…
Conditioning analysis uncovers the landscape of an optimization objective by exploring the spectrum of its curvature matrix. This has been well explored theoretically for linear models. We extend this analysis to deep neural networks (DNNs) in order to investigate their learning dynamics. To this en…
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR). Different from existing multi-view based methods, HEAR develops a unified framework to address both multi-view redundancy and single-view incompleteness. Specifically,…
Video-based person re-identification (re-ID) is an important research topic in computer vision. The key to tackling the challenging task is to exploit both spatial and temporal clues in video sequences. In this work, we propose a novel graph-based framework, namely Multi-Granular Hypergraph (MGH), t…
One fundamental problem in deep learning is understanding the outstanding performance of deep Neural Networks (NNs) in practice. One explanation for the superiority of NNs is that they can realize a large class of complicated functions, i.e., they have powerful expressivity. The expressivity of a Re…
Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from global features or image parts (regions) to the semantic space, which, however, fail to capture the appearance relationships between different local regions within a single image. In this paper, to model the relati…
The label-free nature of unsupervised cross-modal hashing hinders models from exploiting the exact semantic data similarity. Existing research typically simulates the semantics by a heuristic geometric prior in the original feature space. However, this introduces heavy bias into the model as the ori…
Zero-shot learning (ZSL) aims to classify images from unseen categories, by merely utilizing seen class images as the training data. Existing works on ZSL mainly leverage the global features or learn the global regions, from which, to construct the embeddings to the semantic space. However, few of t…
Semantic segmentation is an important computer vision task, which aims to allocate a semantic label to each pixel in an image. When training a segmentation model, it is common to fine-tune a classification network pre-trained on a large-scale dataset. However, as an intrinsic property of the classif…
Medical image analysis has two important research areas: disease grading and fine-grained lesion segmentation. Although the former problem often relies on the latter, the two are usually studied separately. Disease severity grading can be treated as a classification problem, which only requires imag…
Sketch-based 3D shape retrieval has been extensively studied in recent works, most of which focus on improving the retrieval accuracy, whilst neglecting the efficiency. In this paper, we propose a novel framework for efficient sketch-based 3D shape retrieval, i.e., Deep Sketch-Shape Hashing (DSSH),…
In this paper, we present a novel, simple but effective approach for dynamic texture recognition using 3D random features. Compared with the existing dynamic texture recognition approaches using carefully designed features for high performance, our method use only a few 3D random filters to extract…
Batch Normalization (BN) is ubiquitously employed for accelerating neural network training and improving the generalization capability by performing standardization within mini-batches. Decorrelated Batch Normalization (DBN) further boosts the above effectiveness by whitening. However, DBN relies…
Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restricts their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they…
The data streams arising in many applications can be modeled as a union of low-dimensional subspaces known as multi-subspace data streams (MSDSs). Clustering MSDSs according to their underlying low-dimensional subspaces is a challenging problem which has not been resolved satisfactorily by existing…
Learning the probability distribution of high-dimensional data is a challenging problem. To solve this problem, we formulate a deep energy adversarial network (DEAN), which casts the energy model learned from real data into an optimization of a goodness-of-fit (GOF) test statistic. DEAN can be inter…
In the context of Cued Speech (CS) recognition, the recognition of lips and hand movements is a key task. As we know, a good temporal segmentation is necessary for the supervised recognition system. However, lips and hand streams cannot share the same temporal segmentation since they are not synchro…
Facial expression recognition is a topical task. However, very little research investigates subtle expression recognition, which is important for mental activity analysis, deception detection, etc. We address subtle expression recognition through convolutional neural networks (CNNs) by developing mu…
Due to the succinct nature of free-hand sketch drawings, sketch-based image retrieval (SBIR) has abundant practical use cases in consumer electronics. However, SBIR remains a long-standing unsolved problem mainly due to the significant discrepancy between the sketch domain and the image domain. In t…
Understanding the image formation inside plenoptic cameras is significant for the investigations of improving the low spatial resolution. Most researches explore the image formation from the perspective of geometric optics. However, as the hardware components in combination with low-aperture optical…
How to economically cluster large-scale multi-view images is a long-standing problem in computer vision. To tackle this challenge, this paper introduces a novel approach named Highly-economized Scalable Image Clustering (HSIC) that radically surpasses conventional image clustering methods via binary…
Unsupervised cross-database facial expression recognition (FER) is a challenging problem, in which the training and testing samples belong to different facial expression databases. For this reason, the training (source) and testing (target) facial expression samples would have different feature dist…
Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e.g., portable or smart wearable devices). Recent advancements in binarized networks have demonst…
In this paper, we investigate an interesting problem, i.e., unsupervised cross-corpus speech emotion recognition (SER), in which the training and testing speech signals come from two different speech emotion corpora. Meanwhile, the training speech signals are labeled, while the label information of…
Recent studies show that large-scale sketch-based image retrieval (SBIR) can be efficiently tackled by cross-modal binary representation learning methods, where Hamming distance matching significantly speeds up the process of similarity search. Providing training and test data subjected to a fixed s…
In this paper, a novel automatic approach to extract the inner lips contour of speakers without using artifices is proposed. This method is based on a recent facial contour extraction model developed in computer vision, called Constrained Local Neural Field (CLNF), which provides 8 characteristic po…
Traditional action recognition methods aim to recognize actions with complete observations/executions. However, it is often difficult to capture fully executed actions due to occlusions, interruptions, etc. Meanwhile, action prediction/recognition in advance based on partial observations is essentia…
Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a novel deep model based on 3D CNN (convolutional neural network) and LSTM (long short-term memory) module with a multi-task learning manner for effective Deep Action Par…
Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image repr…
Free-hand sketch-based image retrieval (SBIR) is a specific cross-view retrieval task, in which queries are abstract and ambiguous sketches while the retrieval database is formed with natural images. Work in this area mainly focuses on extracting representative and shared features for sketches and n…
Learning to hash has been recognized to accomplish highly efficient storage and retrieval for large-scale visual data. Particularly, ranking-based hashing techniques have recently attracted broad research attention because ranking accuracy among the retrieved data is well explored and their objectiv…
Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency. Recently, several hashing based approaches have been developed to make re-identification more scalable for large-scale gallery sets. Despite their efficiency, these works ignore c…
Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) fr…
Flexible manipulator enables curvilinear accessibility through small incisions or natural orifices for minimally invasive surgery and diagnosis, which makes it a good choice for minimally invasive surgery. In order to control the robot precisely and safely, the real-time position and shape informati…
Recently, zero-shot action recognition (ZSAR) has emerged with the explosive growth of action categories. In this paper, we explore ZSAR from a novel perspective by adopting the Error-Correcting Output Codes (dubbed ZSECOC). Our ZSECOC equips the conventional ECOC with the additional capability of Z…
Recently, very high-dimensional feature representations, e.g., Fisher Vector, have achieved excellent performance for visual recognition and retrieval. However, these lengthy representations always cause extremely heavy computational and storage costs and even become unfeasible in some large-scale a…