相关论文: Detection, Retrieval, and Explanation Unified: A V…

As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact…

Deep neural networks often achieve high accuracy, but ensuring their reliability under adversarial and distributional shifts remains a pressing challenge. We propose TriGuard, a unified safety evaluation framework that combines (1) formal…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals.…

Violence detection has been studied in computer vision for years. However, previous work are either superficial, e.g., classification of short-clips, and the single scenario, or undersupplied, e.g., the single modality, and hand-crafted…

In the last few years, there has been a surge of interest in learning representations of entitiesand relations in knowledge graph (KG). However, the recent availability of temporal knowledgegraphs (TKGs) that contain time information for…

As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existing machine learning models often rely only on a single…

Diffusion-based text-to-video generation (T2V) or image-to-video (I2V) generation have emerged as a prominent research focus. However, there exists a challenge in integrating the two generative paradigms into a unified model. In this paper,…

Recognition and generation are two fundamental tasks in computer vision, which are often investigated separately in the exiting literature. However, these two tasks are highly correlated in essence as they both require understanding the…

Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generation (RAG) systems help language models access external knowledge, but traditional vector…

Video text-based visual question answering (Video TextVQA) aims to answer questions by explicitly reading and reasoning about the text involved in a video. Most works in this field follow a frame-level framework which suffers from redundant…

Learning-based methods have become increasingly popular for solving vehicle routing problems due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation…

Comprehending long videos remains a significant challenge for Large Multi-modal Models (LMMs). Current LMMs struggle to process even minutes to hours videos due to their lack of explicit memory and retrieval mechanisms. To address this…

We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion or additional building blocks. Our approach employs…

Wide usage of social media platforms has increased the risk of aggression, which results in mental stress and affects the lives of people negatively like psychological agony, fighting behavior, and disrespect to others. Majority of such…

The Text-to-Video Retrieval (T2VR) task aims to retrieve unlabeled videos by textual queries with the same semantic meanings. Recent CLIP-based approaches have explored two frameworks: Two-Tower versus Single-Tower framework, yet the former…

One of the main challenges in managing traffic at multilane intersections is ensuring smooth coordination between human-driven vehicles (HDVs) and connected autonomous vehicles (CAVs). This paper presents a novel traffic signal control…

Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open-domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection…

Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…

Violence and abnormal behavior detection research have known an increase of interest in recent years, due mainly to a rise in crimes in large cities worldwide. In this work, we propose a deep learning architecture for violence detection…