16 accepted papers
Real-world autonomous driving, particularly in urban environments with numerous corner cases, requires rigorous testing to ensure product safety and robustness. However, few studies have explored integrating adversarial scenario generation with the training of safety agents in closed-loop testing, e…
Graph anomaly detection is crucial for identifying anomalous nodes within graphs and addressing applications like financial fraud detection and social spam detection. Recent spectral graph neural network methods advance graph anomaly detection by focusing on anomalies that notably affect the distrib…
Cross-speed bearing fault diagnosis based on unsupervised domain adaptation can handle data distribution differences across various operating speeds, supporting intelligent maintenance of equipment like wind turbines with variable operating speeds. Existing methods focus on aligning sample distribut…
Image fusion combines information from multi-modality images to produce high-quality fused images with enhanced clarity, contrast, and informativeness. However, limited ground truth fusion data lead to difficulties in effectively training these fusion models. Moreover, current studies lack of fine-g…
"Currently, there is relatively limited research on the background activity noise of event cameras in different brightness conditions, and the relevant real-world datasets are extremely scarce. This limitation contributes to the lack of robustness in existing event denoising algorithms when applied…
Relational triple extraction is a fundamental task in the field of information extraction, and a promising framework based on table filling has recently gained attention as a potential baseline for entity relation extraction. However, inherent shortcomings such as redundant information and incomplet…
The T2VR task aims to retrieve videos that are semantically relevant to the given query text in a large number of unlabeled videos. Most of the existing methods adopt a representation encoding strategy that can only focus on limited contextual information, and lack the ability to focus on the long m…
The event camera’s low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these appr…
Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone, V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. V2C is more challenging than conventional text-to-…
Deep convolutional networks (CNNs) show their potential in image colorization for producing plausible results. Recently, the attention mechanism further boosts the performances of CNNs by constructing channel and spatial interactions. However, existing attention methods are performed in a single-sca…
User-intended visual content fills the hole regions of an input image in the image editing scenario. The coarse lowlevel inputs, which typically consist of sparse sketch lines and color dots, convey user intentions for content creation (i.e., free-form editing). While existing methods combine an inp…
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence. Existing researches have realized the importance of the aspect for the ABSA task and have derived many interactive learning methods that model context based on specific aspect…
Endowing a chatbot with a personality is essential to deliver more realistic conversations. Various persona-based dialogue models have been proposed to generate personalized and diverse responses by utilizing predefined persona information. However, generating personalized responses is still a chall…
Deep encoder-decoder based CNNs have advanced image inpainting methods for hole filling. While existing methods recover structures and textures step-by-step in the hole regions, they typically use two encoder-decoders for separate recovery. The CNN features of each encoder are learned to capture eit…
The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often generate contents with blurry textures and distorted structures due to the discontinuity of the local pixels. From a semantic…
This paper proposes a rotating coded aperture we called RCA for depth recovery, complementing the previous depth from defocus methods in both recovery accuracy and friendliness for hardware implementation. In the proposed RCA, an optimized coded aperture is rotated around the optical axis, and multi…