20 accepted papers
Multi-view 3D object detection plays a vital role in autonomous driving systems due to its ability to perceive complex scenes accurately. However, real-world driving data often exhibits a long-tailed distribution, causing significant drops in detection accuracy for rare categories in existing method
While current state-of-the-art Remote Sensing Change Detection (RSCD) methods can achieve impressive results on individual datasets, they become unreliable in unseen environments and imaging conditions, with performance metrics declining by as much as 60% to 80%. Simultaneously, variable environment
Video shadow detection confronts two entwined difficulties: distinguishing shadows from complex backgrounds and modeling dynamic shadow deformations under varying illumination. To address shadow-background ambiguity, we leverage linguistic priors through the proposed Vision-language Match Module (VM
Zero-shot multimodal anomaly detection is critical for identifying structural defects that are often invisible to traditional RGB images, particularly in scenarios lacking target domain samples. However, existing methodologies face two significant impediments: the prohibitive computational overhead
Lifelong person re-identification (LReID) aims to retrieve the target person from sequentially collected data. Due to significant domain gaps between datasets and the continuous increase of training data from different scenarios, weak inter-domain generalization and catastrophic forgetting issues ha
Next POI recommendation contributes to the prosperity of various intelligent location-based services. Existing studies focus on exploring sequential patterns and POI interactions using sequential and graph-based methods to enhance recommendation performance. However, they don't effectively exploit g
Traditional unsupervised domain adaptation (UDA) struggles to extract rich semantics due to backbone limitations. Recent large-scale pre-trained visual-language models (VLMs) have shown strong zero-shot learning capabilities in UDA tasks. However, directly using VLMs results in a mixture of semantic
Oriented object detection has advanced with the development of convolutional neural networks (CNNs) and transformers. However, modern detectors still rely on predefined object candidates, such as anchors in CNN-based methods or queries in transformer-based methods, which struggle to capture spatial
The geometry of terrain is crucial for developing terrain-aware locomotion policies. Recent advancements in quadrupedal locomotion based on learning rely on depth information obtained from LiDARs and depth cameras. Despite the capabilities of these locomotion policies on terrains, they pose challeng
To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label
The diffusion model has been successfully applied to various detection tasks. However, it still faces several challenges when used for oriented object detection: objects that are arbitrarily rotated require the diffusion model to encode their orientation information; uncontrollable random boxes inac…
The Information Bottleneck (IB) principle has emerged as a promising approach for enhancing the generalization, robustness, and interpretability of deep neural networks, demonstrating efficacy across image segmentation, document clustering, and semantic communication. Among IB implementations, the I…
Aspect Sentiment Triple Extraction (ASTE) is an emerging task in fine-grained sentiment analysis. Recent studies have employed Graph Neural Networks (GNN) to model the syntax-semantic relationships inherent in triplet elements. However, they have yet to fully tap into the vast potential of syntactic…
Deep learning models are widely used for speaker recognition and spoofing speech detection. We propose the GMM-ResNet2 for synthesis speech detection. Compared with the previous GMM-ResNet model, GMM-ResNet2 has four improvements. Firstly, the different order GMMs have different capabilities to form…
With the development of deep learning, many different network architectures have been explored in speaker verification. However, most network architectures rely on a single deep learning architecture, and hybrid networks combining different architectures have been little studied in ASV task. In this…
Recently, regression-based methods, which predict parameterized text shapes for text localization, have gained popularity in scene text detection. However, the existing parameterized text shape methods still have limitations in modeling arbitrary-shaped texts due to ignoring the utilization of text-…
Joint activity detection and channel estimation (JADCE) for grant-free random access is a critical issue that needs to be addressed to support massive connectivity in IoT networks. However, the existing model-free learning method can only achieve either activity detection or channel estimation, but…
This paper presents HiFi-SVC, a small cross-domain singing voice conversion model for generating high-fidelity 22.05 kHz singing voices. Building on state-of-the-art neural vocoder HiFi-GAN and a convolution-based module for modeling F0, HiFi-SVC can be trained end-to-end with either speech or singi…
Automatic segmentation of COVID-19 lesions is essential for computer-aided diagnosis. However, this task remains challenging because widely-used supervised based methods require large-scale annotated data that is difficult to obtain. Although an unsupervised method based on anomaly detection has sho…
The transformer-based encoder-decoder framework has shown remarkable performance in image captioning. However, most transformer-based captioning methods ever overlook two kinds of elusive confounders: the visual confounder and the linguistic confounder, which generally lead to harmful bias, induce t…