19 accepted papers
Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the scientific domain have played an important role in assessing the r
While adversarial attacks can effectively deceive deep neural networks, their real-world applicability is often limited by complex and conspicuous patterns that reveal their attack intent to human observers. To overcome this limitation, we propose UYE, a novel camouflage framework designed to simult
Obtaining labeled data in the field of industrial anomaly detection is challenging, which necessitates the development of label-free frameworks. However, current methods mainly focus on the unsupervised paradigm, which uses a large number of normal samples of the same category to train the model, an…
Industrial anomaly detection (IAD) plays a crucial role in large-scale industrial manufacturing. Recently, numerous unsupervised algorithms have been proposed and achieved remarkable performance on benchmark datasets. Given the high homogeneity of samples during training and testing, it appears that…
Adversarial attacks pose a significant challenge in deep learning, as carefully crafted perturbations can severely degrade even the most advanced models. In real-world scenarios, where the target models are often unknown, previous works often focus on creating adversarial patterns for specific known…
Large visual-language models (LVLMs) have achieved great success in multiple applications. However, they still encounter challenges in complex scenes, especially those involving camouflaged objects. This is primarily due to the lack of samples related to camouflaged scenes in the training dataset. T…
RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules should be jointly optimized to achieve optimal performance. To demonstrate this, we design a specific pipeline called Sm…
Existing fine-tuning paradigms are predominantly characterized by Full Parameter Tuning (FPT) and Parameter-Efficient Tuning (PET). FPT fine-tunes all parameters of a pre-trained model on downstream tasks, whereas PET freezes the pre-trained model and employs only a minimal number of learnable param…
Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal in the reasoning process. Specifically, process RMs evaluat…
Understanding student behavior in educational settings is critical in improving both the quality of pedagogy and the level of student engagement. While various AI-based models exist for classroom analysis, they tend to specialize in limited tasks and lack generalizability across diverse educational…
With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws inspiration from natural language processing (NLP), has made s…
As an important and challenging task in video understanding, Temporal Action Detection (TAD) has been deeply studied in recent years. However, current works mainly tackle this task with visual information, while neglecting to explore the potential of the audio modality. To address this challenge, in…
Human pose estimation has long been motivated for its application in human behavior understanding and activity recognition. Despite recent advances in multi-person pose estimation, existing solutions remain challenging in crowded scenes, especially in classroom scenarios where students are extremely…
Open-domain dialogue systems have made promising progress in recent years. While the state-of-the-art dialogue agents are built upon large-scale social media data and large pre-trained models, there is no guarantee these agents could also perform well in fast-growing scenarios, such as live streamin…
The integral flexible tail has the potential advantage of lifelike undulating motion. However, due to the complex manufacturing process and difficult modification of structural parameters, its application in robotic fish encounters many challenges. Combining rigid structure and flexible material, th
Scene editing has attracted increasing research interests owing to its valuable applications in the field of photography and entertainment. With style-based GAN being proposed, images can be reasonably edited on specific semantics by manipulating in latent space of the generator. However, existing d…
Deep learning-based methods for human pose estimation require large volumes of training data to achieve superior performance. However, data acquisition in classroom environments raises privacy concerns, which will undoubtedly hinder the development of the latest deep learning techniques in education…
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers. The unsupervised pre-training method based on transformer structure combined with fine-tuning of downstream tasks has achieved great success in the field of text summarizatio…
Person re-identification (re-ID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data, which benefits from the popularity of synthetic data engine, has achieved remarkable performance. However, in pursuit of high accuracy, res…