88 accepted papers
The astonishing proficiency and unprecedented level of realism of diffusion models in creating and manipulating images have undoubtedly drawn concerns.Many methods have been proposed to detect generated images. Typically, they usually take RGB images as input, and use backbones like ResNet, CLIP vis
Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, negl
Marginal Fisher Analysis (MFA) is a classical dimensionality reduction (DR) method that leverages dual graphs to capture intra-class compactness and inter-class separability. However, MFA’s reliance on high-quality labels limits its practical application. For another, existing unsupervised DR method
In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with both accurate layout and high fidelity to the text description.(e.g., spatial relationship), and grounding the image robustly at the same time. We believe that
Federated Multi-View Clustering has gained increasing attention for its ability to discover complementary clustering structures of distributed multi-view data while preserving data privacy. However, real-world clients often only have access to partial views, and the view incompleteness poses great c
The rapid development of deepfake generation techniques necessitates robust face forgery detection algorithms. While methods based on Convolutional Neural Networks (CNNs) and Transformers are effective, there is still room for improvement in modeling the highly complex and non-linear nature of forge…
Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. We contend that this discrepancy is largely related to differing lighting conditions, including differences in light wavelength and light source type. Recentl
Recent writing assistants are increasingly shifting from passive, prompt-driven interaction to proactive, suggestion-based completion, which integrates localized continuations into the writing flow and reduces coordination burden. However, existing evaluations simply focus on output quality, failing
Discovering physical laws directly from high-dimensional visual data is a long-standing human pursuit but remains a formidable challenge for machines, representing a fundamental goal of scientific intelligence. This task is inherently difficult because physical knowledge is low-dimensional and struc
Text-Image Person Re-Identification (TI-ReID) is widely deployed in intelligent surveillance. Built on deep neural networks and vision-language models, TI-ReID models inherit vulnerabilities to adversarial attacks, posing security risks. Yet its security remains less explored than retrieval accuracy
Mitigating noisy correspondence in cross-modal matching poses a serious challenge due to the problem of error accumulation. Existing methods primarily attribute this accumulation to errors caused by noisy sample pairs. However, a novel source of error from clean sample pairs (also termed anchor pair
3D Gaussian representations have emerged as a powerful paradigm for digital head modeling, achieving photorealistic quality with real-time rendering. However, intuitive and interactive creation or editing of 3D Gaussian head models remains challenging. Although 2D sketches provide an ideal interacti
The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level—from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suff…
The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training. In single-label scenarios, such as binary and multi-class classification tasks, it has been demonstrated that batch selection algorithms preferring samples with higher un…
Aerial-Ground Person Re-Identification (AG-ReID) is a practical yet challenging task that involves cross-platform matching between aerial and ground cameras. Existing person Re-Identification (Re-ID) methods are primarily designed for homogeneous camera settings, such as ground-to-ground or aerial-t…
Combination usage of LiDAR and RGB cameras for gait recognition can achieve cross space recognition and privacy protection. In addition, the widespread application of LiDAR cameras with 3D geometry information and the large amount of RGB gaits has led to the demand for cross-modality gait recognitio…
Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is challenging since the models need to generalize to anomalies across different domains. Recently, CLIP-based anomaly detection methods,…
Current image forensics methods often utilize image features from various frequency domains. However, the effective use of these features frequently depends on complex network architectures and a large number of parameters. In this paper, we introduce a lightweight Multi-Clue image forgery detection…
The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional p…
Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to capture the inherent complexity, subtlety, and multi-apprai…
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, researchers have been actively investigating effective self-supervised pre-training strategies. For example, MAMP shows that i…
The core task of recommender systems is to learn user preferences from historical user-item interactions. With the rapid development of large language models (LLMs), recent research has explored leveraging the reasoning capabilities of LLMs to enhance rating prediction tasks. However, existing disti…
In real applications, person re-identification (ReID) expects to retrieve the target person at any time, including both daytime and nighttime, ranging from short-term to long-term. However, existing ReID tasks and datasets cannot meet this requirement, as they are constrained by available time and o
Knowledge Distillation (KD) aims to enhance the performance of student models by transferring knowledge from teacher models. While reaping the benefits of KD, the intellectual property risks associated with it cannot be ignored. Even if models are released without training data or provided as a serv…
Open-vocabulary semantic segmentation (OVSS) aims to segment images of arbitrary categories specified by class labels. While previous approaches relied on extensive image-text pairs or dense semantic annotations, recent training-free methods attempted to overcome these limitations by constructing se…
A primary impediment to scaling reinforcement learning (RL) for large language model (LLM) training is the substantial computational cost, predominantly arising from the necessity of multi-sampling for policy optimization and evaluation. This underscores the critical yet challenging nature of effici…
Recent advancements in in-context segmentation generalists have demonstrated significant success in performing various image segmentation tasks using a limited number of labeled example images. However, real-world applications present challenges due to the variability of support examples, which ofte…
Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input single-output (MISO) paradigm. We show that this paradigm fundamentally limits performance in multi-input multi-output (MI
Automatic anime sketch colorization aims to generate a color image from a sketch image, which is challenging due to limited structure and semantic understanding, leading to constrained style, and semantic color inconsistency. In this paper, we introduce a sketch to color diffusion model with semanti…
Open-World Few-Shot Learning (OFSL) is a crucial research field dedicated to accurately identifying target samples in scenarios where data is limited and labels are unreliable. This research holds significant practical implications and is highly relevant to real-world applications. Recently, the adv…
Secret image sharing (SIS) schemes have undergone significant development. However, to the best of our knowledge, none of the existing schemes has considered the deniable property during secret sharing. This presents a problem when we need to share secret images through an untrusted and supervised c…
Existing semi-supervised domain adaptation (SSDA) models have exhibited impressive performance on the target domain by effectively utilizing few labeled target samples per class (e.g., 3 samples per class). To guarantee an equal number of labeled target samples for each class, however, they require…
AI-synthesized text and images have gained significant attention, particularly due to the widespread dissemination of multi-modal manipulations on the internet, which has resulted in numerous negative impacts on society. Existing methods for multi-modal manipulation detection and grounding primarily…
Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic e…
As a manner to augment pretrained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied. While most current approaches, including parameter-efficient fine-tuning (PEFT) and block expansion methods, uniformly apply knowledge a…
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only…
Urban migration is a significant aspect of a city's economy. The exploration of the underlying determinants of housing purchases among current residents contributes to the study of future trends in urban migration, enabling governments to formulate appropriate policies to guide future economic growt…
Partial-label learning (PLL) is an important branch of weakly supervised learning where the single ground truth resides in a set of candidate labels, while the research rarely considers the label imbalance. A recent study for imbalanced PLL propose that the combinatorial challenge of partial-label l…
Secret image sharing (SIS) has made significant progress in research and has found wide applications. However, we note that shadows of traditional SIS contain a large amount of redundancy. A novel Shadow-Embeddable Secret Image Sharing scheme (SE-SIS) leveraging the redundancy in the shadows is prop…
Infrared small target detection (ISTD) is critical to national security and has been extensively applied in military areas. ISTD aims to segment small target pixels from background. Most ISTD networks focus on designing feature extraction blocks or feature fusion modules, but rarely describe the IST…
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently ICL has been employed in visual understanding tasks such as semantic segmentation and image captioning yield…
Text-to-Image person re-identification (TI-ReID) aims to retrieve the images of target identity according to the given textual description. The existing methods in TI-ReID focus on aligning the visual and textual modalities through contrastive feature alignment or reconstructive masked language mode…
Existing image-level self-supervised learning (SSL) methods pre-trained on natural scene data can have difficulty in adating to dense prediction tasks. However, scene images contain multiple varied instances. We devise two techniques to craft high-quality scene and instance views for instance-level…
We study stochastic delayed feedback in general single-agent and multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs). We propose a novel reduction-based framework, which turns any multi-batched algorithm for sequential…
Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate label set. To address this c…
Infrared small target detection (ISTD) is indispensable in remote sensing and military surveillance. Existing ISTD methods can discover regularly-shaped and clear objects well, but tend to overlook the tough-to-detect ones, such as targets with irregular shapes or blurry boundaries, causing inaccura…
Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models(DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the exist…
Weakly-supervised Temporal Action Localization (WTAL) aims at localizing actions in untrimmed videos with only video-level labels. Most existing methods embrace a "localization by classification" paradigm and adopt a model that pre-trained with recognition task for feature extraction. The gap betwee…
Unsupervised Domain Adaptative person re-identification (UDA ReID) aims to transfer the knowledge of pre-trained model from labeled source domain to unlabeled target domain. Although the current clustering-based methods have achieved promising success, they neglect the tolerance of the model to cope…
Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space. However, current transformer-based methods do not fully exploit the prior knowledge of the human skeleton provided by the kinematic structure. In this paper, we propos…
Most infrared small target detection (ISTD) networks focus on building effective neural blocks or feature fusion modules but none describes the ISTD process from the image evolution perspective. The directional evolution of image pixels influenced by convolution, pooling and surrounding pixels is an…
We conduct a quantitative analysis of the development of the industry chain from the environmental, social, and governance (ESG) perspective, which is an overall measure of sustainability. Factors that may impact the performance of the industrial chain have been studied in the literature, such as g…
We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1. The Euclidian distance between full (float or double) precision weights and the ternary weights along with a scaling factor is minimized in training stage. Besides, a threshold-ba…
Out-of-distribution (OOD) detection is critical to building reliable machine learning systems in the open world. Researchers have proposed various strategies to reduce model overconfidence on OOD data. Among them, ReAct is a typical and effective technique to deal with model overconfidence, which tr…
"Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger features. But we find existing graph-based methods in the vis…
The novel coronavirus disease (COVID-19) was declared a pandemic by the World Health Organization. The cumulative number of deaths is more than 4.8 million. Epidemiology experts concur that mass testing is essential for isolating infected individuals, contact tracing, and slowing the progression of…
Semantic image synthesis, translating semantic layouts to photo-realistic images, is a one-to-many mapping problem. Though impressive progress has been recently made, diverse semantic synthesis that can efficiently produce semantic-level multimodal results, still remains a challenge. In this paper,…
Co-occurrent visual pattern makes aggregating contextual information a common paradigm to enhance the pixel representation for semantic image segmentation. The existing approaches focus on modeling the context from the perspective of the whole image, i.e., aggregating the image-level contextual info…
Unsupervised pretraining has achieved great success and many recently works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets. But in this paper, we find this conclusion may not hold when…
Visible-infrared cross modality person re-identification (VI-ReID) is a core but challenging technology in the 24-hours intelligent surveillance system. How to eliminate the large modality gap lies in the heart of VI-ReID. Conventional methods mainly focus on directly aligning the heterogeneous moda…
Physiological studies have shown that differences in facial activities between depressed patients and normal individuals are manifested in different local facial regions and the durations of these activities are not the same. But most previous works extract features from the entire facial region at…
Speech Emotion Recognition (SER) requires a thorough understanding of both the linguistic content of an utterance (i.e., textual information) and how the speaker utters it (i.e., acoustic information). The one vital challenge in SER is how to effectively fuse these two kinds of information. In this…
Cross-modality person re-identification (cm-ReID) is a challenging but key technology for intelligent video analysis. Existing works mainly focus on learning modality-shared representation by embedding different modalities into a same feature space, lowering the upper bound of feature distinctivenes…
This paper is concerned with sequential state filtering in the presence of nonlinearity, non-Gaussianity and model uncertainty. For this problem, the Bayesian model averaged particle filter (BMAPF) is perhaps one of the most efficient solutions. Major advances of BMAPF have been made, while it still…
Semi-supervised learning (SSL) has been extensively studied to improve the generalization ability of deep neural networks for visual recognition. To involve the unlabelled data, most existing SSL methods are based on common density-based cluster assumption: samples lying in the same high-density reg…
The popular tracking-by-detection paradigm for multi-object tracking (MOT) focuses on solving data association problem, of which a robust similarity model lies in the heart. Most previous works make effort to improve feature representation for individual object while leaving the relations among obje…
We propose to learn distributed sentence representation using text’s visual features as input. Different from the existing methods that render the words or characters of a sentence into images separately, we further fold these images into a 3-dimensional sentence tensor. Then, multiple 3-dimensional…
Multimodal fusion increases the performance of emotion recognition because of the complementarity of different modalities. Compared with decision level and feature level fusion, model level fusion makes better use of the advantages of deep neural networks. In this work, we utilize the Transformer mo…
In this paper, we unconventionally propose to adopt appropriate negative-margin to softmax loss for few-shot classification, which surprisingly works well for the open-set scenarios of few-shot classification. We then provide the intuitive explanation and the theoretical proof to understand why nega…
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual-branch non-parametric fashion, PIC directly performs a one-branch parametric instance classification, revealing a s…
Video object detection is a challenging problem in computer vision. In this paper, we propose a novel spatial-temporal feature aggregation network to deal with this issue. Specifically, we present a novel instance-level feature aggregation module as complementary to traditional pixel-level feature a…
Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language. Previous studies have shown remarkable progresses, but they are often vulnerable to the aperture problem that a caption generated b…
Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-…
Keyword spotting (KWS) system constitutes a critical component of human-computer interfaces, which detects the specific keyword from a continuous stream of audio. The goal of KWS is providing a high detection accuracy at a low false alarm rate while having small memory and computation requirements.…
Learning discriminative image feature embeddings is of great importance to visual recognition. To achieve better feature embeddings, most current methods focus on designing different network structures or loss functions, and the estimated feature embeddings are usually only related to the input imag…
Synthesizing photo-realistic images from text descriptions is a challenging problem. Previous studies have shown remarkable progresses on visual quality of the generated images. In this paper, we consider semantics from the input text descriptions in helping render photo-realistic images. However, d…
In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a well-designed speech enhancement approach as the front-end of…
Cross-modal hashing enables similarity retrieval across different content modalities, such as searching relevant images in response to text queries. It provides with the advantages of computation efficiency and retrieval quality for multimedia retrieval. Hamming space retrieval enables efficient con…
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, H…
Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep l…
This paper is concerned with dynamic system state estimation based on a series of noisy measurement with the presence of outliers. An incremental learning assisted particle filtering (ILAPF) method is presented, which can learn the value range of outliers incrementally during the process of particle…
Detecting and localizing anomalies in surveillance videos is an ongoing challenge. Most existing methods are patch or trajectory-based, which lack semantic understanding of scenes and may split targets into pieces. To handle this problem, this paper proposes a novel and effective algorithm by incorp…
Recognizing visual relationships
Pitch is an important characteristic of speech and is useful for many applications. However, it is still challenging to estimate pitch in strong noise. In this paper, we propose a joint training approach to determinate pitch. First, a Bidirectional Long Short-Term Memory Recurrent Neural Networks (B…
In this paper, we propose a CNN-based framework for online MOT. This framework utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame. Simply applying single object tracker for MOT will encounter the problem in computational efficiency…
State filtering is a key problem in many signal processing applications. From a series of noisy measurement, one would like to estimate the state of some dynamic system. Existing techniques usually adopt a Gaussian noise assumption which may result in a major degradation in performance when the meas…
Real-time magnetic resonance imaging (rtMRI) is becoming a practical tool in speech production research and language pathology observation. It is still a challenge to extract the tongue contour accurately in rtMRI sequences, since tongue is a soft tissue and often touches other organs such as lips a…
This paper presents our work on acoustic-to-articulatory inversion mapping, in which, the articulatory data is the MRI series for articulators on mid-sagittal plan. Deep architectures based on restricted Boltzmann machine (RBM) and linear regression are employed to construct the audio-visual mapping…