中文
相关论文

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

200 篇论文

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient…

人工智能 · 计算机科学 2021-05-11 Jiapeng Wu , Yishi Xu , Yingxue Zhang , Chen Ma , Mark Coates , Jackie Chi Kit Cheung

Detecting human-object interactions (HOIs) is an intricate challenge in the field of computer vision. Existing methods for HOI detection heavily rely on appearance-based features, but these may not fully capture all the essential…

计算机视觉与模式识别 · 计算机科学 2023-07-04 Lijing Zhu , Qizhen Lan , Alvaro Velasquez , Houbing Song , Acharya Kamal , Qing Tian , Shuteng Niu

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed. Specifically, the frame sampling policy uses weighted…

计算机视觉与模式识别 · 计算机科学 2023-01-19 Nikolaos Gkalelis , Dimitrios Daskalakis , Vasileios Mezaris

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Nikolaos Gkalelis , Dimitrios Daskalakis , Vasileios Mezaris

Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Wenping Jin , Li Zhu , Jing Sun

This paper introduces TACTIC-GRAPHS, a system that combines spectral graph theory and multimodal graph neural reasoning for semantic understanding and threat detection in tactical video under high noise and weak structure. The framework…

计算机与社会 · 计算机科学 2025-07-30 Wei Meng

Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid expansion of online video. Over the past six years, research has produced…

The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Xing Yi , Jinyang Huang , Feng-Qi Cui , Anyang Tong , Ruimin Wang , Liu Liu , Dan Guo

In the domain of intelligent transportation systems (ITS), collaborative perception has emerged as a promising approach to overcome the limitations of individual perception by enabling multiple agents to exchange information, thus enhancing…

多智能体系统 · 计算机科学 2023-05-04 Ahmed N. Ahmed , Siegfried Mercelis , Ali Anwar

The increasing global crime rate, coupled with substantial human and property losses, highlights the limitations of traditional surveillance methods in promptly detecting diverse and unexpected acts of violence. Addressing this pressing…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Aritra Dutta , Pushpita Boral , G Suseela

Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate the processes of understanding and generation, which limits…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Yuanhuiyi Lyu , Chi Kit Wong , Chenfei Liao , Lutao Jiang , Xu Zheng , Zexin Lu , Linfeng Zhang , Xuming Hu

Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects via inferring triplets of < human, verb, object >. However, recent HOI detection methods mostly rely on additional annotations (e.g.,…

计算机视觉与模式识别 · 计算机科学 2020-07-15 Dongming Yang , Yuexian Zou

The Controller Area Network (CAN) protocol is widely adopted for in-vehicle communication but lacks inherent security mechanisms, making it vulnerable to cyberattacks. This paper introduces KD-GAT, an intrusion detection framework that…

机器学习 · 计算机科学 2026-04-01 Robert Frenken , Sidra Ghayour Bhatti , Hanqin Zhang , Qadeer Ahmed

With the rapid growth of surveillance cameras in many public places to mon-itor human activities such as in malls, streets, schools and, prisons, there is a strong demand for such systems to detect violence events automatically. Au-tomatic…

计算机视觉与模式识别 · 计算机科学 2022-04-18 Heyam M. Bin Jahlan , Lamiaa A. Elrefaei

Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…

计算机视觉与模式识别 · 计算机科学 2025-08-11 Yuchen Guan , Chong Sun , Canmiao Fu , Zhipeng Huang , Chun Yuan , Chen Li

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and…

机器学习 · 计算机科学 2024-12-25 Haowen Xu , Ali Boyaci , Jianming Lian , Aaron Wilson

This paper addresses the challenge of automated violence detection in video frames captured by surveillance cameras, specifically focusing on classifying scenes as "fight" or "non-fight." This task is critical for enhancing unmanned…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Gourang Pathak , Abhay Kumar , Sannidhya Rawat , Shikha Gupta

Achieving visual semantic understanding requires a unified framework that simultaneously handles object detection, category prediction, and attribute recognition. However, current advanced approaches rely on global similarity and struggle…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Xinyu Nan , Lingtao Mao , Huangyu Dai , Zexin Zheng , Xinyu Sun , Zihan Liang , Ben Chen , Yuqing Ding , Chenyi Lei , Wenwu Ou , Han Li

Temporal Sentence Grounding in Videos (TSGV) aims to detect the event timestamps described by the natural language query from untrimmed videos. This paper discusses the challenge of achieving efficient computation in TSGV models while…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Renjie Liang , Yiming Yang , Hui Lu , Li Li

Unified multimodal models integrating visual understanding and generation face a fundamental challenge: visual generation incurs substantially higher computational costs than understanding, particularly for video. This imbalance motivates…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Luozheng Qin , Jia Gong , Qian Qiao , Tianjiao Li , Li Xu , Haoyu Pan , Chao Qu , Zhiyu Tan , Hao Li
‹ 上一页 1 2 3 10 下一页 ›