51 accepted papers
We present ARTrack-AC, a new step in the autoregressive tracking paradigm that introduces adaptive capacity inference to achieve both temporal consistency and dynamic efficiency. While existing autoregressive trackers predict object states sequentially with fixed inference capacity, they fail to acc
Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and sign
Visual prompted object detection enables interactive and flexible definition of target categories, thereby facilitating open-vocabulary detection. Since visual prompts are derived directly from image features, they often outperform text prompts in recognizing rare categories. Nevertheless, research…
Monocular dense SLAM faces significant challenges in low-texture environments and under rapid camera motions. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems employ end-to-end optimiza…
Recent studies have shown that unsupervised graph contrastive learning (GCL) is vulnerable to adversarial attacks. Automatic adversarial augmentation techniques are proposed to improve both the effectiveness and robustness of GCL. Existing methods typically regard unsupervised contrastive loss as th
Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on resource-constrained devices. To alleviate this issue, we propose $\tex…
Dynamic graph learning, which focuses on modeling the merging, vanishing, and reconnection of nodes and edges, is crucial for real-world applications. In dynamic graphs, node neighborhoods often exhibit diverse and time-evolving topologies, including hierarchical, grid-like, and cyclic patterns. Exi…
While Vision-Language Models (VLMs) excel at semantic understanding, they struggle to comprehend 3D spatial relationships from limited views. Their reliance on implicit geometric encoding often leads to severe hallucinations and inconsistencies in spatial reasoning tasks. To address this, we introdu
Vision-and-Language Navigation (VLN) requires an embodied agent to navigate through unseen environments, guided by natural language instructions and a continuous video stream. Recent advances in VLN have been driven by the powerful semantic understanding of Multimodal Large Language Models (MLLMs).…
Industrial Anomaly Detection (IAD) has attracted significant attention and witnessed rapid development. However, the advancement in this field is hindered by two key issues: the performance saturation of existing benchmarks, limiting discriminative evaluation of different IAD methods, and the absenc
Safe autonomous driving requires both accurate HD map construction and persistent awareness of traffic rules, even when their associated signs are no longer visible. However, existing methods either focus solely on geometric elements or treat rules as temporary classifications, failing to capture th
High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges. The online construction of HD maps using on-board sensors has emerged as a promising solution; however
Multi-modal 3D semantic occupancy prediction remains challenged by two fundamental issues: (i) geometric--semantic misalignment introduced by fixed-neighborhood fusion under heterogeneous sensing distributions, and (ii) feature degradation with prediction inconsistency in dynamic scenes caused by sp…
Recent advancements in visual object tracking have shifted towards a sequential generation paradigm, where object deformation and motion exhibit strong temporal dependencies. Despite the importance of these dependencies, widely adopted image-level pretrained backbones barely capture the dynamics in…
Monocular dense SLAM faces significant challenges in low-texture environments and under rapid camera motions. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems employ end-to-end optimiza
Ensuring adherence to traffic sign regulations is essential for both human and autonomous vehicle navigation. While current online mapping solutions often prioritize the construction of the geometric and connectivity layers of HD maps, overlooking the construction of the traffic regulation layer wit…
Non-exemplar Class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars, addressing privacy and storage issues. However, the absence of data from earlier tasks exacerbates the challenge of catastrophic forgetti…
Recently, the mutual combination of Neural Radiance Fields (NeRF) and Segment Anything Model (SAM) in 3D semantic segmentation has achieved impressive results. However, they face the challenge of accurately and consistently segmenting objects in complex scenarios. To address this issue, we introduce…
Language-image pre-training faces significant challenges due to limited data in specific formats and the constrained capacities of text encoders. While prevailing methods attempt to address these issues through data augmentation and architecture modifications, they continue to struggle with processi…
Vision–Language–Action (VLA) models are increasingly used for end-to-end driving due to their world knowledge and reasoning ability. Most prior work, however, inserts textual chains-of-thought (CoT) as intermediate steps tailored to the current scene. Such symbolic compressions can blur spatio-tempo…
Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations--such as signal attenuation, multi-path interference (MPI), and temporal noise--that significantly compromise de…
Unsupervised Domain Adaptation for image classification aims to adapt models trained on a labeled source domain to an unlabeled target domain, improving target domain classification performance. However, previous UDA classification researches tend to assume the two domain distributions after domain…
Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs) due to their message-passing mechanisms, but their training heavily relies on the human-annotated labels. Moreover, the complex and diverse local topologies of nodes of real-world TAGs make it challenging for a single…
Fine-tuning a minimal subset of parameters in large well-trained models has emerged as a popular paradigm for transforming prior knowledge to address downstream tasks in computer vision. Although it has shown promising performance in certain vision tasks such as classification, parameter-efficient t…
Accurate lane topology is essential for autonomous driving, yet traditional methods struggle to model the complex, non-linear structures--such as loops and bidirectional lanes--prevalent in real-world road structure. We present SeqGrowGraph, a novel framework that learns lane topology as a chain of…
In this paper we focus on a challenging Online Task-Free Class Incremental Learning (OTFCIL) problem. Different from the existing methods that continuously learn the feature space from data streams we propose a novel compute-and-align paradigm for the OTFCIL. It first computes an optimal geometry i.…
Recent studies have demonstrated the potency of leveraging prompts in Transformers for continual learning (CL). Nevertheless, employing a discrete key-prompt bottleneck can lead to selection mismatches and inappropriate prompt associations during testing. Furthermore, this approach hinders adaptive…
"In this paper, we propose Neural Spectrum Decomposition, a generic decomposition framework for dataset distillation. Unlike previous methods, we consider the entire dataset as a high-dimensional observation that is low-rank across all dimensions. We aim to discover the low-rank representation of th…
Wi-Fi signals in contrast to cameras offer privacy protection and occlusion resilience for some practical scenarios such as smart homes elderly care and virtual reality. Recent years have seen remarkable progress in the estimation of single-person 2D pose single-person 3D pose and multi-person 2D po…
Efficiently estimating the full-body pose with minimal wearable devices presents a worthwhile research direction. Despite significant advancements in this field, most current research neglects to explore full-body avatar estimation under low-quality signal conditions, which is prevalent in practica…
Unsupervised domain adaptation (UDA) aims to transfer knowledge from the labeled source domain to the fully-unlabeled target domain, thus improving the classification performance of the target domain. Recently, self-training has shown its effectiveness on UDA. However, the feature space for generati…
Unsupervised domain adaptation aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain, thereby improving the classification performance of the target domain. Recent methods use contrastive learning to optimize this task, however, these methods only focus…
Deep neural networks suffer from catastrophic forgetting in class incremental learning, where the classification accuracy of old classes drastically deteriorates when the networks learn the knowledge of new classes. Many works have been proposed to solve the class incremental learning problem. Howev…
Network binarization (i.e., binary neural networks, BNNs) can efficiently compress deep neural networks and accelerate model inference but cause severe accuracy degradation. Existing BNNs are mainly implemented based on the commonly used full-precision network backbones, and then the accuracy is imp…
Hyperspectral image (HSI) denoising has achieved promising results with the development of deep learning. A mainstream class of methods exploits the spatial-spectral correlations and recovers each band with the aids of neighboring bands, collectively referred to as spectral auxiliary networks. Howev…
Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic…
Current 6D pose estimation methods focus on handling objects that are previously trained, which limits their applications in real dynamic world. To this end, we propose a geometry correspondence-based framework, termed GCPose, to estimate 6D pose of arbitrary unseen objects without any re-training.…
The success of deep learning relies heavily on large and diverse datasets, but the storage, preprocessing, and training of such data present significant challenges. To address these challenges, dataset distillation techniques have been proposed to obtain smaller synthetic datasets that capture the e…
Current methods of multi-person pose estimation typically treat the localization and association of body joints separately. In this paper, we propose the first fully end-to-end multi-person Pose Estimation framework with TRansformers, termed PETR. Our method views pose estimation as a hierarchical s…
This paper presents an end-to-end instance segmentation framework, termed SOIT, that Segments Objects with Instance-aware Transformers. Inspired by DETR, our method views instance segmentation as a direct set prediction problem and effectively removes the need for many hand-crafted components like R…
Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to…
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…
This paper focuses on the unsupervised domain adaptation problem for video-based crowd counting, in which we use labeled data as source domain and unlabelled video data as target domain. It is challenging as there is a huge gap between the source and the target domain and no annotations of samples a…
In this paper, we focus on the challenging few-shot class incremental learning (FSCIL) problem, which requires to transfer knowledge from old tasks to new ones and solves catastrophic forgetting. We propose the exemplar relation distillation incremental learning framework to balance the tasks of old…
Counting dense crowds through computer vision technology has attracted widespread attention. Most crowd counting datasets use point annotations. In this paper, we formulate crowd counting as a measure regression problem to minimize the distance between two measures with different supports and unequa…
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets. We dissect that the crux of this problem is the catastrophic sensitivity of crowd counters to scale shift, which is very common in the real world and caused by factors suc…
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from ve…
A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network's recognition performance on old classes degrades severely when incrementally learning new classes. To alleviate forgetting, we put forward to preserve the old class knowledge by maintainin…
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map estimation, which convert the sparse point annotations into a "ground…
Designing discriminative and invariant features is the key to visual recognition. Recently, the bilinear pooled feature matrix of Convolutional Neural Network (CNN) has shown to achieve state-of-the-art performance on a range of fine-grained visual recognition tasks. The bilinear feature matrix coll…
Representing local image patches in an invariant and discriminative manner is an active research topic in computer vision. It has recently been demonstrated that local feature learning based on deep Convolutional Neural Network (CNN) can significantly improve the matching performance. Previous works…