69 accepted papers
Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently $\textbf{wild}$, being intricate, messy, and flexible. We identify three key challenges from user behaviour: $\textit{compositional tasks}$ th…
Accurate short-term precipitation forecasting is critical for weather-sensitive decision-making in agriculture, transportation, and disaster response. Existing deep learning approaches often struggle to balance global structural consistency with local detail preservation, especially under complex me
Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS,…
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like Engli…
Chlor-alkali production is a large-scale industrial process whose operating conditions and equipment states evolve over time. Its process optimization requires ongoing trade-offs among conflicting objectives such as product yield, energy consumption, and equipment life. Existing optimization approac
Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resulting in high training or inference cost and limited cross-domain stability. To address these limitation…
With the rapid development and adoption of 3D Gaussian Splatting (3DGS), the need for effective copyright protection has become increasingly critical. Existing watermarking techniques for 3DGS mainly focus on protecting rendered images via pre-trained decoders, leaving the underlying 3D Gaussian pri…
The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing. However, existing learning-based approaches often neglect stability constraints and struggle to generalize across diverse bin dimensions. To address this, we propose a novel deep reinforcement learning
Poster generation is a complex task demanding a harmonious integration of visual aesthetics and information hierarchy. While recent text-to-image models have advanced visual synthesis, they remain non-editable and struggle with precise text rendering. Conversely, existing layout-generation methods o…
Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual semantics from visual tokens, they fail to fully leverage this a
Multimodal large language models (MLLMs) that "think with images" can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this work, we first reveal a critical and previously overlooke
The emergence of multimodal technologies has propelled Vision-Language Incremental Learning (VLIL) into a research spotlight. Current VLIL approaches predominantly inherit unimodal paradigms, failing to address fundamental distinctions between visual and linguistic modalities. Crucially, the semanti
With the continuously expanding parameters, efficiently adapting large language models to downstream tasks is crucial in resource-limited conditions. Many parameter-efficient fine-tuning methods have emerged to address this challenge. However, they lack flexibility, like LoRA requires manually selec…
Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this i…
Fine-grained intent detection involves identifying a large number of classes with subtle variations. Recently, generating pseudo samples via large language models has attracted increasing attention to alleviate the data scarcity caused by emerging new intents. However, these methods generate samples…
Existing one-stream trackers have attracted widespread attention. However, they are not applicable in real-time aerial robot tracking systems due to substantial computational overhead, especially when dynamic templates are introduced. To address this issue, we propose a novel Dynamic Compact Consens
Due to the unidirectional masking mechanism, Decoder-Only models propagate information from left to right. LVLMs (Large Vision-Language Models) follow the same architecture, with visual information gradually integrated into semantic representations during forward propagation. Through systematic anal
Multi-label few-shot image classification is a crucial and challenging task due to limited annotated data and elusive category specificity. However, research on this topic is still in the rudimentary stage and few methods are available. Existing methods either leverage data augmentation to alleviate…
Recent advancements in Knowledge Graph Completion (KGC) often adopt a two-stage pipeline that combines triple-based retrieval with text-based re-ranking. However, point-wise re-rankers, which score candidates individually, often fail to capture subtle distinctions between similar candidates due to t…
Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates current resources, it fails to capture dynamic disaster impacts over time. To address this gap, we introduce the Remote Sensi…
As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics an…
Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to effectively preprocess such low-light inputs, as they fail to…
Multi-label document classification (MLDC) aims to allocate more than one label to each document and attracts increasing attention in many practical applications. However, previous studies have failed to pay sufficient attention to the lack of semantic information on labels and the long-tail problem…
Multi-modal large language models (MLLMs) are expanded from large language models (LLMs) with additional capabilities to infer multi-modal data. Current MLLM workflows, when dealing with complex tasks, typically begin by using an LLM to decompose the task into multiple subtasks, then heuristically s…
Few-shot intent detection is a challenging task, particularly in scenarios involving multiple labels and diverse domains. This paper presents a novel prototype learning approach that combines the label synset augmentation and the coarse-to-fine prototype distillation for multi-label few-shot intent…
Recent demosaicing approaches are not effective and efficient enough as they do not make full use of these two factors: (1) Capturing long-range spatial dependencies effiently. (2) Reducing the computational costs when utilizing channel attention. To take them into consideration, we propose an Effic…
Depression detection is a challenging and crucial task in psychological illness diagnosis. Utilizing online user posts to predict whether a user suffers from depression seems an effective and promising direction. However, existing methods suffer from either poor interpretability brought by the black…
"Detecting and magnifying imperceptible high-frequency motions in real-world scenarios has substantial implications for industrial and medical applications. These motions are characterized by small amplitudes and high frequencies. Traditional motion magnification methods rely on costly high-speed ca…
Intent detection aims to identify user goals from utterances, and is a ubiquitous step towards the satisfaction of user desired needs in many interaction systems. As dynamic and varied intents arise, models that are capable of identifying new intents promptly are required. However, existing studies…
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes to unseen classes, they are still limited by (1) In…
Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person…
Most of the previous exposure correction methods learn dense pixel-wise transformations to achieve promising results but consume huge computational resources. Recently Learnable 3D lookup tables (3D LUTs) have demonstrated impressive performance and efficiency for image enhancement. However these me…
The latest research on wildfire forecast and backtracking has adopted AI models, which require a large amount of data from wildfire scenarios to capture fire spread patterns. This paper explores using cost-effective simulated wildfire scenarios to train AI models and apply them to the analysis of re…
While Global Navigation Satellite System (GNSS) is often used to provide global positioning if available, its intermittency and/or inaccuracy calls for fusion with other sensors. In this paper, we develop a novel GNSS-Visual-Inertial Navigation System (GVINS) that fuses visual, inertial, and raw GNS…
Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggle to discern whether a model genuinely possesses the required capabilities or merely memorizes/guesses the answers…
Existing text-based person retrieval datasets often have relatively coarse-grained text annotations. This hinders the model to comprehend the fine-grained semantics of query texts in real scenarios. To address this problem we contribute a new benchmark named UFineBench for text-based person retrieva…
Hyperparameter Optimization (HPO) plays a pivotal role in unleashing the potential of iterative machine learning models. This paper addresses a crucial aspect that has largely been overlooked in HPO: the impact of uncertainty in ML model training. The paper introduces the concept of uncertainty-awar…
The proliferation of open-source large models necessitates dedicated tools for deployment and accessibility. To mitigate the complexities of model serving, we develop Xinference, an open-source library designed to simplify the deployment and management of large models. Xinference effectively simplif…
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain. However, directly applying this ap…
Multi-label intent detection aims to assign multiple labels to utterances and attracts increasing attention as a practical task in task-oriented dialogue systems. As dialogue domains change rapidly and new intents emerge fast, the lack of annotated data motivates multi-label few-shot intent detectio…
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the embryonic stage and only a few methods are available. Nevert…
Most offline video instance segmentation (VIS) methods lack consideration for multi-scale spatio-temporal features, which leads to unstable instance association across frames. To address this problem, we propose IAST that builds Instance Association relying on Spatio-Temporal features for video inst…
Owing to the efficiency in terms of the modeling of long-range dependencies, transformer-based spectral reconstruction methods have produced satisfactory hyperspectral (HS) images from multispectral (MS) images. Some transformer-based methods applied self-attention to all bands in the HS image to mo…
Tone mapping aims to convert high dynamic range (HDR) images to low dynamic range (LDR) representations, a critical task in the camera imaging pipeline. In recent years, 3-Dimensional LookUp Table (3D LUT) based methods have gained attention due to their ability to strike a favorable balance between…
The attention mechanism in Transformer-based HOI models plays important role in the comprehension of human and object interaction. However, most previous Transformer-based models ignore the guidance on the query and attention, which leads to a poor understanding of interaction behaviour. In this pap…
Hard-label textual adversarial attack is a challenging task, as only the predicted label information is available, and the text space is discrete and non-differentiable. Relevant research work is still in fancy and just a handful of methods are proposed. However, existing methods suffer from either…
Modeling and synthesizing low-light raw noise is a fundamental problem for computational photography and image processing applications. Although most recent works have adopted physics-based models to synthesize noise, the signal-independent noise in low-light conditions is far more complicated and v…
We introduce the task of correcting named entity recognition (NER) errors without re-training model. After an NER model is trained and deployed in production,it makes prediction errors, which usually need to be fixed quickly. To address this problem, we firstly construct a gazetteer containing named…
Most video instance segmentation(VIS) models only focused on visual knowledge and ignored intrinsic linguistic knowledge. Based on the observation that incorporating linguistic knowledge can significantly improve the model’s contextual understanding of the video, in this paper, we present a Video In…
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we present a Dynamic lightweight High-Resolution Networ…
The intensive computations in convolutional neural networks (CNNs) pose challenges for resource-constrained devices; eliminating redundant computations from convolution is essential. This paper gives a principled method to detect and avoid transient redundancy, a type of redundancy existing in input…
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emerging new intents and slots, data scarcity issue often…
Hierarchical Text Classification (HTC) is a challenging task that categorizes a textual description within a taxonomic hierarchy. Most of the existing methods focus on modeling the text. Recently, researchers attempt to model the class representations with some resources (e.g., external dictionaries…
Deep neural networks have been widely used in image denoising during the past few years. Even though they achieve great success on this problem, they are computationally inefficient which makes them inappropriate to be implemented in mobile devices. In this paper, we propose an efficient deep neural…
While high accuracy tracking of targets has been extensively explored because of its wide applications, many exiting methods degenerate in the presence of multipath distortions. This paper proposes an accurate and novel multipath-resilient system to track the targets by leveraging the large number o…
Interactions between entities in knowledge graph (KG) provide rich knowledge for language representation learning. However, existing knowledge-enhanced pretrained language models (PLMs) only focus on entity information and ignore the fine-grained relationships between entities. In this work, we prop…
Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for…
Motion detection based on WiFi signals has gained much attention recently. However, most of the existing approaches can only detect motion in a large coverage area without knowing how far the target motion happens. In this paper, we propose two robust and responsive features in the frequency dimensi…
Fall detection systems based on WiFi signals are gaining popularity recently. However, most of the existing works relying on training are environment-dependent. In this paper, we propose DeFall, a novel WiFi-based environment-independent fall detection system by leveraging the features inherently as…
While being the de facto standard coordinate representation for human pose estimation, heatmap has not been investigated in-depth. This work fills this gap. For the first time, we find that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is…
The recently proposed Tensor Nuclear Norm (TNN) minimization has been widely used for tensor completion. However, previous works didn’t consider the structural difference between the observed data and missing data, which widely exists in many applications. In this paper, we propose to incorporate a…
Heading direction information is crucial to many ubiquitous computing applications. The main stream has been resorting to inertial sensors, such as accelerometer, gyroscope and magnetometer, which suffer from severe accumulative errors or large degradations indoors. In this paper, we utilize the rad…
This paper focuses on the recovery of low-tubal-rank tensors from binary measurements under the frame of tensor Singular Value Decomposition. We show that the direction of a tubal-rank-r tensor X ∈ ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n1×n2…
In big cities, there are plenty of parking spaces, but we often find nowhere to park. For example, New York has 1.4 million cars and 4.4 million on-street parking spaces, but it is still not easy to find a parking place near our destination, especially during peak hours. The reason is the lack of pr…
Accurate monitoring of human vital signs (e.g. breathing and heart rates) is crucial in detecting medical problems. In this paper, we propose ViMo, a calibration-free remote Vital sign Monitoring system that can simultaneously monitor multiple users by leveraging the channel impulse response (CIR) o…
Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we inves…
In a rich-scattering environment, radio frequency (RF) devices communicate through multipath channels and the channel state information (CSI) is uniquely determined by the location of the transmitter or receiver devices along with surrounding environments. Whenever one of the devices moves, the CSI…
Motion detection as a key component in modern security systems has received an increasing attention recently, but most existing solutions require special installation, calibration, and only have a limited coverage. In this paper, we propose WiDetect, a highly accurate, calibration-free, and low-comp…
Time-reversal (TR) transmission scheme has attracted more and more attention from both academia and industry due to its ability to focus the energy of a transmitted signal at an intended focal spot, both in the time and spatial domains. Based on the extensive data collected in the real world, we obs…